From 654753afd84efe4adea452f17659d00cfec0ec4a Mon Sep 17 00:00:00 2001 From: ai-bankofai Date: Tue, 31 Mar 2026 19:30:13 +0800 Subject: [PATCH 01/46] Update API.md Server url fix --- docs/llmservice/api/API.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/llmservice/api/API.md b/docs/llmservice/api/API.md index 8c8526e5..fca81762 100644 --- a/docs/llmservice/api/API.md +++ b/docs/llmservice/api/API.md @@ -8,7 +8,7 @@ Chat completion. Auth: Bearer token. Non-stream: JSON with choices[].content. St | URL | Description | |-----|-------------| -| `https://api.bankofai.com` | Production | +| `https://api.bankofai.io` | Production | ## Authentication From f218a0e5262ff3d529ee6f5aa5fce9772dac24a3 Mon Sep 17 00:00:00 2001 From: ai-bankofai Date: Fri, 3 Apr 2026 12:58:31 +0800 Subject: [PATCH 02/46] Update API.md bug fix --- docs/llmservice/api/API.md | 622 +++++++++++++++++++++---------------- 1 file changed, 350 insertions(+), 272 deletions(-) diff --git a/docs/llmservice/api/API.md b/docs/llmservice/api/API.md index fca81762..cf58d1f8 100644 --- a/docs/llmservice/api/API.md +++ b/docs/llmservice/api/API.md @@ -1,342 +1,420 @@ -# AI API +# AI API (OpenAI Compatible) Chat completion. Auth: Bearer token. Non-stream: JSON with choices[].content. Stream: SSE chunks with choices[].delta.content. - **Version:** 1.0 +- **Base URL:** `https://api.ainft.com` +- **OpenAPI:** 3.1.0 -## Servers - -| URL | Description | -|-----|-------------| -| `https://api.bankofai.io` | Production | +--- ## Authentication -### Bearer Auth +### Bearer Token -- **Type:** HTTP Bearer -- **Format:** JWT -- **Description:** Bearer \, e.g. `Bearer sk-xxx` +- **Type:** HTTP Bearer (JWT) +- **Header:** `Authorization: Bearer ` +- **Example:** `Bearer sk-xxx` -### API Key Auth +### API Key (Messages endpoint only) - **Type:** API Key -- **In:** Header -- **Name:** `x-api-key` -- **Description:** API Key authentication, e.g. `x-api-key: your-api-key` +- **Header:** `x-api-key: ` --- ## Endpoints -### Model List +### 1. List Models -#### `GET /v1/models` - List models (OpenAI compatible) +`GET /v1/models` -List available models. Auth: Bearer token. Response: object, success, data. +List available models. Auth: Bearer token. -**Authentication:** Bearer Auth +**Auth:** Bearer Token -**Responses:** +**Response 200:** -| Status Code | Description | -|-------------|-------------| -| 200 | object: list; success: true; data: array of { id, object, created, owned_by } | +```json +{ + "object": "list", + "success": true, + "data": [ + { + "id": "gpt-5.2", + "object": "model", + "created": 1626777600, + "owned_by": "openai", + "supported_endpoint_types": ["openai", "anthropic"] + } + ] +} +``` + +| Status | Description | +|--------|-------------| +| 200 | Success - list of models | | 400 | Bad Request - invalid parameters or malformed body | | 401 | Unauthorized - invalid or missing authentication | | 403 | Forbidden - access denied, insufficient quota, or banned | | 429 | Too Many Requests - rate limit exceeded | | 500 | Internal Server Error | -**200 Response Schema:** [V1ModelsResponse](#v1modelsresponse) - -**Error Response Schema:** [ErrorResponse](#errorresponse) - --- -### Messages - -#### `POST /v1/messages` - Send a message (Claude compatible) - -Accepts a list of messages and returns a model-generated response. Supports both single-turn and multi-turn conversations. Authenticate via x-api-key header. Responses can be streamed (SSE) or returned as a single JSON object. - -**Authentication:** API Key Auth (`x-api-key`) - -**Request Body:** [ChatCompletionsRequest](#chatcompletionsrequest) (required, `application/json`) - -**Responses:** - -| Status Code | Description | -|-------------|-------------| -| 200 | Success. Schema differs by stream mode. | +### 2. Chat Completions (OpenAI Compatible) + +`POST /v1/chat/completions` + +Accepts a list of messages and returns a model-generated response. Supports both single-turn and multi-turn conversations. Responses can be streamed (SSE) or returned as a single JSON object. + +**Auth:** Bearer Token + +#### Request Body + +| Parameter | Type | Required | Description | +|-----------|------|----------|-------------| +| `model` | string | **Yes** | ID of the model to use (e.g. `gpt-5.2`). | +| `messages` | array | **Yes** | List of messages in the conversation. See [ChatMessage](#chatmessage). | +| `stream` | boolean | No | If true, partial message deltas will be sent as server-sent events. Default `false`. | +| `max_tokens` | integer | No | Maximum number of tokens that can be generated in the completion. | +| `temperature` | number | No | Sampling temperature between 0 and 2. Higher = more random. Default `1`. | +| `top_p` | number | No | Nucleus sampling: consider tokens with top_p probability mass. Default `1`. | +| `stop` | string \| string[] | No | Up to 4 sequences where the API will stop generating. | +| `n` | integer | No | How many chat completion choices to generate. Default `1`. | +| `frequency_penalty` | number | No | -2.0 to 2.0. Penalize repeated tokens. Default `0`. | +| `presence_penalty` | number | No | -2.0 to 2.0. Penalize tokens that appear in the text so far. Default `0`. | +| `seed` | integer | No | Random seed for deterministic sampling (if supported by model). | +| `response_format` | object | No | Specify output format: `{ "type": "text" }` or `{ "type": "json_object" }` or `json_schema`. | +| `tools` | array | No | List of tools the model may call. See [ChatTool](#chattool). | +| `tool_choice` | string \| object | No | `"auto"`, `"none"`, `"required"`, or `{ "type": "function", "function": { "name": "..." } }`. | +| `user` | string | No | Optional end-user identifier for abuse monitoring. | +| `web_search_options` | object | No | Enables web search for supported models. See [WebSearchOptions](#websearchoptions). | + +#### Request Example + +```json +{ + "model": "gpt-5.2", + "messages": [ + { "role": "system", "content": "You are a helpful assistant." }, + { "role": "user", "content": "Hello" } + ], + "stream": false, + "max_tokens": 1024, + "temperature": 1 +} +``` + +#### Response (Non-stream) + +```json +{ + "id": "chatcmpl-xxx", + "object": "chat.completion", + "created": 1677652288, + "model": "gpt-5.2", + "choices": [ + { + "index": 0, + "message": { + "role": "assistant", + "content": "Hello! How can I help you?", + "refusal": null, + "annotations": [] + }, + "finish_reason": "stop" + } + ], + "usage": { + "prompt_tokens": 12, + "completion_tokens": 8, + "total_tokens": 20, + "prompt_tokens_details": { "cached_tokens": 0, "audio_tokens": 0 }, + "completion_tokens_details": { + "reasoning_tokens": 0, + "audio_tokens": 0, + "accepted_prediction_tokens": 0, + "rejected_prediction_tokens": 0 + } + } +} +``` + +#### Response (Stream) + +Each SSE chunk has `object: "chat.completion.chunk"` with `choices[].delta.content` containing incremental text. The final chunk includes `usage` and `finish_reason`. + +| Status | Description | +|--------|-------------| +| 200 | Success | | 400 | Bad Request - invalid parameters, malformed body, or invalid request | -| 401 | Unauthorized - invalid or missing API key | +| 401 | Unauthorized - invalid or missing authentication | | 403 | Forbidden - access denied, insufficient quota, or model access restricted | | 429 | Too Many Requests - rate limit exceeded | | 500 | Internal Server Error | | 502 | Bad Gateway - upstream service error | | 503 | Service Unavailable - overloaded or no available channel | -**200 Response Content Types:** -- `application/json`: [ChatCompletionsResponse](#chatcompletionsresponse) -- `text/event-stream`: [ChatCompletionsResponse](#chatcompletionsresponse) - -**Error Response Schema:** [ErrorResponse](#errorresponse) - --- -### Chat Completions - -#### `POST /v1/chat/completions` - Create a chat completion (OpenAI compatible) - -Accepts a list of messages and returns a model-generated response. Supports both single-turn and multi-turn conversations. Authenticate via Bearer token. Responses can be streamed (SSE) or returned as a single JSON object. - -**Authentication:** Bearer Auth - -**Request Body:** [ChatCompletionsRequest](#chatcompletionsrequest) (required, `application/json`) - -**Responses:** - -| Status Code | Description | -|-------------|-------------| -| 200 | Success. Schema differs by stream mode. | +### 3. Messages (Claude Compatible) + +`POST /v1/messages` + +Accepts a list of messages and returns a model-generated response. Supports both single-turn and multi-turn conversations. Authenticate via `x-api-key` header or Bearer token. Responses can be streamed (SSE) or returned as a single JSON object. + +**Auth:** API Key (`x-api-key`) or Bearer Token + +#### Request Body + +| Parameter | Type | Required | Description | +|-----------|------|----------|-------------| +| `model` | string | **Yes** | ID of the model (e.g. `claude-sonnet-4-6`, `claude-opus-4-6`, `claude-haiku-4-5`). | +| `max_tokens` | integer | **Yes** | Maximum number of tokens to generate. Different models have different maximum values. | +| `messages` | array | **Yes** | Input messages. Alternating user/assistant turns. Limit: 100,000 messages. See [MessagesMessageItem](#messagesmessageitem). | +| `system` | string \| array | No | System prompt. Can be a plain string or an array of text blocks (for `cache_control`). | +| `stream` | boolean | No | Whether to stream the response using SSE. Default `false`. | +| `temperature` | number | No | Randomness (0.0 - 1.0). Use ~0.0 for analytical tasks, ~1.0 for creative tasks. Default `1`. | +| `top_p` | number | No | Nucleus sampling. Default `1`. | +| `top_k` | integer | No | Only sample from the top K options. Default disabled. | +| `stop_sequences` | string[] | No | Custom text sequences that cause the model to stop generating. | +| `metadata` | object | No | Request metadata. Supports `user_id` (opaque identifier). | +| `thinking` | object | No | Extended thinking config. See [ThinkingConfig](#thinkingconfig). | +| `tools` | array | No | Tool definitions the model may use. See [Tool](#tool-anthropic). | +| `tool_choice` | object | No | How the model should use tools: `auto`, `any`, `tool`, or `none`. | + +#### Request Example + +```json +{ + "model": "claude-sonnet-4-6", + "max_tokens": 1024, + "messages": [ + { "role": "user", "content": "Hello, Claude!" } + ], + "system": "You are a helpful assistant.", + "temperature": 1.0 +} +``` + +#### Response (Non-stream) + +```json +{ + "id": "chatcmpl-xxx", + "type": "message", + "role": "assistant", + "content": [ + { "type": "text", "text": "Hello! How can I help you?" } + ], + "stop_reason": "end_turn", + "model": "gpt-5", + "usage": { + "input_tokens": 4, + "cache_creation_input_tokens": 0, + "cache_read_input_tokens": 0, + "output_tokens": 12, + "claude_cache_creation_5_m_tokens": 0, + "claude_cache_creation_1_h_tokens": 0 + } +} +``` + +#### Response (Stream - SSE Events) + +Stream responses emit the following event types: + +| Event Type | Description | Key Fields | +|------------|-------------|------------| +| `message_start` | Initial message metadata | `message` (id, model, role, usage) | +| `content_block_start` | New content block begins | `index`, `content_block` (type, text) | +| `content_block_delta` | Incremental content | `index`, `delta` (type: `text_delta`, text) | +| `content_block_stop` | Content block ends | `index` | +| `message_stop` | Message complete | - | + +| Status | Description | +|--------|-------------| +| 200 | Success | | 400 | Bad Request - invalid parameters, malformed body, or invalid request | -| 401 | Unauthorized - invalid or missing authentication | +| 401 | Unauthorized - invalid or missing API key | | 403 | Forbidden - access denied, insufficient quota, or model access restricted | | 429 | Too Many Requests - rate limit exceeded | | 500 | Internal Server Error | | 502 | Bad Gateway - upstream service error | | 503 | Service Unavailable - overloaded or no available channel | -**200 Response Content Types:** -- `application/json`: [ChatCompletionsResponse](#chatcompletionsresponse) -- `text/event-stream`: [ChatCompletionsResponse](#chatcompletionsresponse) - -**Error Response Schema:** [ErrorResponse](#errorresponse) - --- -## Schemas - -### ErrorResponse - -| Field | Type | Description | -|-------|------|-------------| -| `error` | object | Error details | -| `error.message` | string | Error message | -| `error.type` | string | Error type (e.g. invalid_request_error) | -| `error.param` | string \| null | Related parameter | -| `error.code` | string \| null | Error code | - ---- - -### V1ModelsResponse - -| Field | Type | Example | Description | -|-------|------|---------|-------------| -| `object` | string | `"list"` | | -| `success` | boolean | `true` | | -| `data` | array | | Array of [V1ModelItem](#v1modelitem) | - ---- - -### V1ModelItem - -| Field | Type | Example | Description | -|-------|------|---------|-------------| -| `id` | string | `"gpt-5.2"` | | -| `object` | string | `"model"` | | -| `created` | integer | `1626777600` | | -| `owned_by` | string | `"openai"` | | - ---- - -### ChatCompletionsRequest - -**Required fields:** `model`, `messages` - -| Field | Type | Description | Example | -|-------|------|-------------|---------| -| `model` | string | ID of the model to use (e.g. gpt-5.2). | `"gpt-5.2"` | -| `messages` | array | List of messages in the conversation. Array of [ChatMessage](#chatmessage). | | -| `stream` | boolean | If true, partial message deltas will be sent as server-sent events. Default false. | | -| `max_tokens` | integer | Maximum number of tokens that can be generated in the completion. | | -| `temperature` | number | Sampling temperature between 0 and 2. Higher = more random. Default 1. | | -| `top_p` | number | Nucleus sampling: consider tokens with top_p probability mass. Default 1. | | -| `stop` | string \| string[] | Up to 4 sequences where the API will stop generating. String or array of strings. | | -| `n` | integer | How many chat completion choices to generate. Default 1. | | -| `frequency_penalty` | number | -2.0 to 2.0. Penalize repeated tokens. Default 0. | | -| `presence_penalty` | number | -2.0 to 2.0. Penalize tokens that appear in the text so far. Default 0. | | -| `seed` | integer | Random seed for deterministic sampling (if supported by model). | | -| `response_format` | object | [ChatResponseFormat](#chatresponseformat). Specify output format. | | -| `tools` | array | List of tools the model may call. Array of [ChatTool](#chattool). Each has type "function" and function { name, description?, parameters? }. | | -| `tool_choice` | string \| object | `"auto"` \| `"none"` \| `"required"` \| [ToolChoiceObject](#toolchoiceobject). | | -| `user` | string | Optional end-user identifier for abuse monitoring. | | -| `web_search_options` | object | [WebSearchOptions](#websearchoptions). Optional web search configuration. | | - ---- - -### WebSearchOptions - -Optional. Enables web search for models that support it (OpenAI Chat Completions). When present, this gateway treats the request as web-search-enabled; model allowlists may apply. Field names align with OpenAI `web_search_options`. - -| Field | Type | Description | Example | -|-------|------|-------------|---------| -| `search_context_size` | string | Guidance for how much context window space to use for web search results. Enum: `"low"`, `"medium"`, `"high"`. | `"medium"` | -| `user_location` | object | Approximate user location to refine search results (e.g. country as ISO 3166-1 alpha-2, city, region, timezone). Structure follows OpenAI documentation. | | - ---- +## Data Models ### ChatMessage -| Field | Type | Description | Example | -|-------|------|-------------|---------| -| `role` | string | `"system"` \| `"user"` \| `"assistant"` \| `"tool"`. System sets behavior; user/assistant are conversation; tool is tool result. | `"user"` | -| `content` | string | Message content. For tool role, the result of the tool call. | `"Hello"` | -| `name` | string | Optional name for the message author (e.g. to disambiguate multiple users). | | -| `tool_call_id` | string | When role is "tool", the id of the tool call this result is for. Required for tool messages. | | -| `tool_calls` | array | When role is "assistant" and the model called tools, array of [ChatToolCallItem](#chattoolcallitem). | | - ---- - -### ChatResponseFormat - -Specify output format: `{ "type": "text" }` or `{ "type": "json_object" }` or json_schema. - -| Field | Type | Description | -|-------|------|-------------| -| `type` | string | `"text"` or `"json_object"`. | -| `json_schema` | any | When type is json_schema, optional schema for the output. | - ---- +| Field | Type | Required | Description | +|-------|------|----------|-------------| +| `role` | string | **Yes** | `"system"`, `"user"`, `"assistant"`, or `"tool"` | +| `content` | string | **Yes** | Message content. For tool role, the result of the tool call. | +| `name` | string | No | Optional name for the message author. | +| `tool_call_id` | string | No | When role is `"tool"`, the ID of the tool call this result is for. | +| `tool_calls` | array | No | When role is `"assistant"` and the model called tools. Array of `{ id, type, function: { name, arguments } }`. | + +### MessagesMessageItem + +| Field | Type | Required | Description | +|-------|------|----------|-------------| +| `role` | string | **Yes** | `"user"` or `"assistant"` (no `"system"` - use top-level `system` parameter). | +| `content` | string \| array | **Yes** | Text string or array of content blocks (text, image, tool_use, tool_result). | + +### Content Block Types (Messages API) + +#### TextBlockParam + +```json +{ "type": "text", "text": "Hello, Claude!", "cache_control": { "type": "ephemeral" } } +``` + +#### ImageBlockParam + +Base64 source: +```json +{ + "type": "image", + "source": { + "type": "base64", + "media_type": "image/jpeg", + "data": "/9j/4AAQSkZJRg..." + } +} +``` + +URL source: +```json +{ + "type": "image", + "source": { + "type": "url", + "url": "https://example.com/image.jpg" + } +} +``` + +Supported media types: `image/jpeg`, `image/png`, `image/gif`, `image/webp` + +#### ToolUseBlockParam (from assistant) + +```json +{ + "type": "tool_use", + "id": "toolu_01D7FLrfh4GYq7yT1ULFeyMV", + "name": "get_stock_price", + "input": { "ticker": "AAPL" } +} +``` + +#### ToolResultBlockParam (from user) + +```json +{ + "type": "tool_result", + "tool_use_id": "toolu_01D7FLrfh4GYq7yT1ULFeyMV", + "content": "259.75 USD", + "is_error": false +} +``` + +### ThinkingConfig + +Enable extended thinking to let Claude show its reasoning process. + +**Enabled:** +```json +{ "type": "enabled", "budget_tokens": 1024 } +``` +- `budget_tokens`: Must be >= 1024 and less than `max_tokens`. + +**Disabled:** +```json +{ "type": "disabled" } +``` + +### Tool (Anthropic) + +```json +{ + "name": "get_stock_price", + "description": "Get the current stock price for a given ticker symbol.", + "input_schema": { + "type": "object", + "properties": { + "ticker": { "type": "string" } + }, + "required": ["ticker"] + } +} +``` + +### ToolChoice (Anthropic) + +| Type | Description | +|------|-------------| +| `{ "type": "auto" }` | Model decides whether to use tools. Supports `disable_parallel_tool_use`. | +| `{ "type": "any" }` | Model will use any available tool. Supports `disable_parallel_tool_use`. | +| `{ "type": "tool", "name": "..." }` | Model will use the specified tool. Supports `disable_parallel_tool_use`. | +| `{ "type": "none" }` | Model will not use tools. | ### ChatTool -| Field | Type | Description | Example | -|-------|------|-------------|---------| -| `type` | string | Must be `"function"`. | `"function"` | -| `function` | object | [ChatToolFunction](#chattoolfunction). Function definition (name, description, parameters). | | - ---- - -### ChatToolFunction - -| Field | Type | Description | -|-------|------|-------------| -| `name` | string | Name of the function. | -| `description` | string | Optional description for the model. | -| `parameters` | any | Optional JSON schema for the function arguments. | - ---- - -### ChatToolCallItem - -| Field | Type | Description | Example | -|-------|------|-------------|---------| -| `id` | string | ID of the tool call. | | -| `type` | string | `"function"`. | `"function"` | -| `function` | object | [ChatToolCallFunction](#chattoolcallfunction). Name and arguments of the call. | | - ---- - -### ChatToolCallFunction - -| Field | Type | Description | -|-------|------|-------------| -| `name` | string | Name of the function to call. | -| `arguments` | string | JSON string of the arguments. | - ---- - -### ToolChoiceObject +```json +{ + "type": "function", + "function": { + "name": "get_weather", + "description": "Get weather for a location", + "parameters": { + "type": "object", + "properties": { + "location": { "type": "string" } + }, + "required": ["location"] + } + } +} +``` -Precise mode: specifies the particular function to call. - -**Required fields:** `type`, `function` - -| Field | Type | Description | Example | -|-------|------|-------------|---------| -| `type` | string | Must be `"function"`. Enum: `"function"`. | `"function"` | -| `function` | object | [ToolChoiceFunction](#toolchoicefunction). Function definition to call. | | - ---- - -### ToolChoiceFunction - -**Required fields:** `name` +### WebSearchOptions | Field | Type | Description | |-------|------|-------------| -| `name` | string | Name of the function to call. | +| `search_context_size` | string | `"low"`, `"medium"`, or `"high"` - how much context window for web search results. | +| `user_location` | object | Approximate user location (country ISO 3166-1 alpha-2, city, region, timezone). | ---- - -### ChatCompletionsResponse - -Non-stream: object=chat.completion, choices[].message, usage. Stream: object=chat.completion.chunk, choices[].delta; final chunk has usage. - -| Field | Type | Description | Example | -|-------|------|-------------|---------| -| `id` | string | | `"chatcmpl-xxx"` | -| `object` | string | `"chat.completion"` (non-stream) or `"chat.completion.chunk"` (stream). | | -| `created` | integer | | `1677652288` | -| `model` | string | | `"gpt-5.2"` | -| `service_tier` | string | | `"default"` | -| `system_fingerprint` | string \| null | | | -| `choices` | array | Empty in final usage chunk. Array of [ChatChoice](#chatchoice). | | -| `usage` | null \| object | [ChatUsage](#chatusage). Non-stream: always present. Stream: null until final chunk. | | -| `obfuscation` | string | | | - ---- - -### ChatMessageContent - -Non-stream choices[].message. Full assistant message with role, content, refusal, annotations. - -| Field | Type | Description | Example | -|-------|------|-------------|---------| -| `role` | string | | `"assistant"` | -| `content` | string | Assistant reply text. | | -| `refusal` | string \| null | Refusal reason when model declines; null otherwise. | | -| `annotations` | array | Citations, references, etc. | | - ---- - -### ChatChoice - -Non-stream: message. Stream: delta. finish_reason null until last content chunk. +### ChatResponseFormat | Field | Type | Description | |-------|------|-------------| -| `index` | integer | | -| `message` | object | [ChatMessageContent](#chatmessagecontent). Non-stream only. Full assistant message. | -| `delta` | object | [ChatChoiceDelta](#chatchoicedelta). Stream only. Incremental content; empty {} on stop. | -| `finish_reason` | string \| null | Null until done; e.g. `"stop"`, `"length"`, `"tool_calls"`. | +| `type` | string | `"text"` or `"json_object"` | +| `json_schema` | object | When type is `json_schema`, optional schema for the output. | --- -### ChatChoiceDelta - -| Field | Type | Description | -|-------|------|-------------| -| `content` | string | | -| `role` | string | | -| `tool_calls` | array | Array of [ChatToolCallItem](#chattoolcallitem). | +## Error Response ---- +All error responses follow this format: -### ChatUsage +```json +{ + "error": { + "message": "Error message", + "type": "invalid_request_error", + "param": null, + "code": null + } +} +``` | Field | Type | Description | |-------|------|-------------| -| `prompt_tokens` | integer | Number of tokens in the prompt. | -| `completion_tokens` | integer | Number of tokens in the completion. | -| `total_tokens` | integer | Total tokens (prompt + completion). | -| `prompt_tokens_details` | object | See below. | -| `prompt_tokens_details.cached_tokens` | integer | | -| `prompt_tokens_details.audio_tokens` | integer | | -| `completion_tokens_details` | object | See below. | -| `completion_tokens_details.reasoning_tokens` | integer | | -| `completion_tokens_details.audio_tokens` | integer | | -| `completion_tokens_details.accepted_prediction_tokens` | integer | | -| `completion_tokens_details.rejected_prediction_tokens` | integer | | +| `message` | string | Error message | +| `type` | string | Error type (e.g. `invalid_request_error`) | +| `param` | string \| null | Related parameter | +| `code` | string \| null | Error code | From c7cda530dc04e2e685bb388728ec9b499eb5997f Mon Sep 17 00:00:00 2001 From: ai-bankofai Date: Fri, 3 Apr 2026 12:59:05 +0800 Subject: [PATCH 03/46] Update API.md --- docs/llmservice/api/API.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/llmservice/api/API.md b/docs/llmservice/api/API.md index cf58d1f8..0d9caa9c 100644 --- a/docs/llmservice/api/API.md +++ b/docs/llmservice/api/API.md @@ -1,4 +1,4 @@ -# AI API (OpenAI Compatible) +# AI API Chat completion. Auth: Bearer token. Non-stream: JSON with choices[].content. Stream: SSE chunks with choices[].delta.content. From 9846a0777a7c6826cbf990fa02a583df62f9e558 Mon Sep 17 00:00:00 2001 From: ai-bankofai Date: Fri, 3 Apr 2026 20:01:26 +0800 Subject: [PATCH 04/46] Update API.md fix baseurl --- docs/llmservice/api/API.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/llmservice/api/API.md b/docs/llmservice/api/API.md index 0d9caa9c..b638cdf3 100644 --- a/docs/llmservice/api/API.md +++ b/docs/llmservice/api/API.md @@ -3,7 +3,7 @@ Chat completion. Auth: Bearer token. Non-stream: JSON with choices[].content. Stream: SSE chunks with choices[].delta.content. - **Version:** 1.0 -- **Base URL:** `https://api.ainft.com` +- **Base URL:** `https://api.bankofai.io` - **OpenAPI:** 3.1.0 --- From d3a6138f0f19feed0c78cb7fb2f077340b10771e Mon Sep 17 00:00:00 2001 From: ai-bankofai Date: Sat, 4 Apr 2026 21:41:24 +0800 Subject: [PATCH 05/46] Create gpt-5-4.md --- docs/llmservice/models/gpt-5-4.md | 36 +++++++++++++++++++++++++++++++ 1 file changed, 36 insertions(+) create mode 100644 docs/llmservice/models/gpt-5-4.md diff --git a/docs/llmservice/models/gpt-5-4.md b/docs/llmservice/models/gpt-5-4.md new file mode 100644 index 00000000..1785360c --- /dev/null +++ b/docs/llmservice/models/gpt-5-4.md @@ -0,0 +1,36 @@ +## Overview + +GPT-5.4 is OpenAI's flagship frontier model released on March 5, 2026, the first mainline model to unify reasoning, coding (GPT-5.3-Codex), and computer use into a single architecture. With up to 1,050,000 tokens of context and 128,000 tokens of max output, it is OpenAI's most capable and versatile model to date. + +## Key Features + +- **Unified Architecture**: Merges reasoning, coding, and computer use into one model — no need to switch between specialized models. +- **Configurable Reasoning Effort**: Five discrete reasoning levels (none, low, medium, high, xhigh) let developers control thinking depth and cost per query. +- **Computer Use API**: A new Computer Use API enables the model to see screens, move cursors, click elements, type text, and interact with desktop applications. +- **Tool Search**: Deferred tool loading mechanism that fetches tool definitions only when needed, reducing total token usage by 47% while maintaining the same accuracy. +- **1M+ Context Window**: Supports up to 1,050,000 tokens of context (922K input + 128K output), enabling analysis of entire codebases or document collections in a single request. + +## Best Use Cases + +- **Agentic Coding Assistants**: Scores 57.7% on SWE-Bench Pro, ideal for complex multi-step coding tasks and autonomous code repair. +- **Desktop Automation & RPA**: OSWorld score of 75% surpasses the human expert baseline of 72.4%, suitable for browser navigation, form filling, and desktop application control. +- **Knowledge-Intensive Work**: GDPval score of 83% with 33% fewer factual errors per claim than GPT-5.2, ideal for research analysis, document processing, and professional Q&A. +- **Long-Context Analysis**: The 1M token context window is perfect for legal document review, large-scale code audits, and cross-document correlation analysis. + +## Capabilities and Limitations + +| Capability | Detailed Description | +| :--- | :--- | +| **Reasoning Ability** | SWE-Bench Pro 57.7%, SWE-Bench Verified ~80%, high GPQA Diamond scores, with five configurable reasoning levels. | +| **Creative Ability** | Excellent long-form text and code generation with 128K max output supporting whole-project generation. | +| **Multimodal Ability** | Supports text and image input with text output; MMMU Pro score of 81.2%. | +| **Response Speed** | As a flagship model, moderate inference speed; higher latency in xhigh reasoning mode, near real-time in none mode. | +| **Context Window** | Standard 272K tokens; expandable to 1,050,000 tokens (requires explicit configuration). | +| **Max Output** | 128,000 tokens | +| **Knowledge Cutoff** | August 31, 2025 | + +## Credits and Pricing + +| Model | Input (per 1M tokens) | Output (per 1M tokens) | +| :--- | :--- | :--- | +| GPT-5.4 | $2.50 | $15.00 | From e4955d8153c9789c941b097e06ae0eb888cbb783 Mon Sep 17 00:00:00 2001 From: ai-bankofai Date: Sat, 4 Apr 2026 21:44:53 +0800 Subject: [PATCH 06/46] Create gpt-5-4.md --- .../current/llmservice/models/gpt-5-4.md | 36 +++++++++++++++++++ 1 file changed, 36 insertions(+) create mode 100644 i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gpt-5-4.md diff --git a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gpt-5-4.md b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gpt-5-4.md new file mode 100644 index 00000000..b0b42350 --- /dev/null +++ b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gpt-5-4.md @@ -0,0 +1,36 @@ +## 概述 + +GPT-5.4 是 OpenAI 于 2026 年 3 月 5 日发布的旗舰级前沿模型。它是首个将推理（Reasoning）、编程（源自 GPT-5.3-Codex）和计算机操作（Computer Use）统一到单一架构中的主流模型。该模型支持高达 1,050,000 token 的上下文窗口以及 128,000 token 的最大输出，是 OpenAI 迄今为止功能最强、用途最广的模型。 + +## 核心特性 + +- **统一架构**：将推理、编程和计算机操作集成于一体，开发者无需在特定模型间切换。 +- **可配置推理强度**：提供五个离散的推理等级（none, low, medium, high, xhigh），允许开发者根据任务需求灵活控制思考深度与查询成本。 +- **计算机操作 API**：新增的 Computer Use API 使模型能够识别屏幕、移动光标、点击元素、输入文本，并与桌面应用程序进行交互。 +- **工具搜索（Tool Search）**：采用延迟加载机制，仅在需要时获取工具定义，在保持准确性的同时将总 token 消耗降低了 47%。 +- **百万级上下文窗口**：支持高达 1,050,000 token 的上下文（922K 输入 + 128K 输出），支持在单次请求中分析整个代码库或庞大的文档集。 + +## 最佳应用场景 + +- **智能编程助手**：在 SWE-Bench Pro 测试中得分 57.7%，非常适合处理复杂的多步编程任务和自主代码修复。 +- **桌面自动化与 RPA**：OSWorld 评分为 75%，超过了人类专家 72.4% 的基准线，适用于浏览器导航、表单填写和桌面应用控制。 +- **知识密集型工作**：GDPval 评分为 83%，每项声明的事实错误比 GPT-5.2 少 33%，是研究分析、文档处理和专业问答的理想选择。 +- **长文本分析**：100万 token 的上下文窗口完美契合法律文件审查、大规模代码审计以及跨文档的相关性分析。 + +## 能力与限制 + +| 能力维度 | 详细说明 | +| :--- | :--- | +| **推理能力** | SWE-Bench Pro 57.7%，SWE-Bench Verified 约 80%，GPQA Diamond 高分，支持五级可调推理。 | +| **创作能力** | 卓越的长文本和代码生成能力，支持 128K 最大输出，可生成整个项目。 | +| **多模态能力** | 支持文本和图像输入，文本输出；MMMU Pro 评分为 81.2%。 | +| **响应速度** | 作为旗舰模型，推理速度中等；xhigh 推理模式延迟较高，none 模式接近实时响应。 | +| **上下文窗口** | 标准为 272K token；最高可扩展至 1,050,000 token（需显式配置）。 | +| **最大输出** | 128,000 token | +| **知识截止日期** | 2025 年 8 月 31 日 | + +## 额度与计费 + +| 模型名称 | 输入 (每 100 万 token) | 输出 (每 100 万 token) | +| :--- | ---: | ---: | +| GPT-5.4 | $2.50 | $15.00 | From f29be07d22357b72593e8fb0a143fe040d0c2474 Mon Sep 17 00:00:00 2001 From: ai-bankofai Date: Sat, 4 Apr 2026 21:53:06 +0800 Subject: [PATCH 07/46] Create gpt-5-4-mini.md --- docs/llmservice/models/gpt-5-4-mini.md | 36 ++++++++++++++++++++++++++ 1 file changed, 36 insertions(+) create mode 100644 docs/llmservice/models/gpt-5-4-mini.md diff --git a/docs/llmservice/models/gpt-5-4-mini.md b/docs/llmservice/models/gpt-5-4-mini.md new file mode 100644 index 00000000..ae0dd65e --- /dev/null +++ b/docs/llmservice/models/gpt-5-4-mini.md @@ -0,0 +1,36 @@ +## Overview + +GPT-5.4 Mini is OpenAI's high-performance compact model released on March 17, 2026, an efficient distillation of GPT-5.4. It significantly improves over GPT-5 Mini across coding, reasoning, multimodal understanding, and tool use while running 2x+ faster, at roughly 1/6 the cost of the standard model — ideal for high-volume workloads. + +## Key Features + +- **Near-Flagship Performance**: Scores 54.38% on SWE-Bench Pro, remarkably close to the standard model's 57.7%, at roughly 1/6 the cost. +- **Strong Scientific Reasoning**: Achieves 87.5% on GPQA Diamond, excelling at graduate-level scientific reasoning tasks. +- **Full Tool Support**: Supports tool use, web search, image analysis, and Native Computer Use — full capability retention. +- **2x+ Speed Improvement**: Runs 2x+ faster than GPT-5 Mini, suitable for latency-sensitive workloads. +- **400K Context Window**: Supports a 400,000 token context window with vision input, suitable for medium-scale long document processing. + +## Best Use Cases + +- **Coding Assistants & Sub-Agents**: Approaches flagship-level performance on coding benchmarks, delivering reliable code generation and repair at significantly lower cost. +- **Real-Time AI Applications**: 2x speed improvement makes it ideal for chatbots, real-time translation, and interactive coding assistance. +- **High-Throughput Data Processing**: Low-cost, high-performance combination suits large-scale document classification, content moderation, and data extraction pipelines. +- **Desktop Automation Agents**: Full Native Computer Use support for building moderately complex desktop automation workflows. + +## Capabilities and Limitations + +| Capability | Detailed Description | +| :--------------------- | :------------------------------------------------------------------------------------------------------------------------------------- | +| **Reasoning Ability** | SWE-Bench Pro 54.38%, GPQA Diamond 87.5%; strong reasoning but slightly behind standard on the most complex multi-step problems. | +| **Creative Ability** | Good text and code generation for most everyday creative tasks; less capable than standard for creation requiring very deep reasoning. | +| **Multimodal Ability** | Supports text and image input with text output; significantly improved multimodal understanding and image analysis over GPT-5 Mini. | +| **Response Speed** | Fast — 2x+ faster than GPT-5 Mini, suitable for latency-sensitive scenarios. | +| **Context Window** | 400,000 tokens | +| **Max Output** | Not officially specified, estimated 16,000–32,000 tokens | +| **Knowledge Cutoff** | August 31, 2025 | + +## Credits and Pricing + +| Model | Input (per 1M tokens) | Output (per 1M tokens) | +| :----------- | --------------------: | ---------------------: | +| GPT-5.4 Mini | $0.75 | $4.50 | From 36446b77d2d0019c9e5c5b3f791917e6a9f5869d Mon Sep 17 00:00:00 2001 From: ai-bankofai Date: Sat, 4 Apr 2026 21:55:03 +0800 Subject: [PATCH 08/46] Create gpt-5-4-mini.md --- .../current/llmservice/models/gpt-5-4-mini.md | 36 +++++++++++++++++++ 1 file changed, 36 insertions(+) create mode 100644 i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gpt-5-4-mini.md diff --git a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gpt-5-4-mini.md b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gpt-5-4-mini.md new file mode 100644 index 00000000..1d17fffd --- /dev/null +++ b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gpt-5-4-mini.md @@ -0,0 +1,36 @@ +## 概述 + +GPT-5.4 Mini 是 OpenAI 于 2026 年 3 月 17 日发布的一款高性能轻量模型，可视为 GPT-5.4 的高效蒸馏版本。它在编程、推理、多模态理解和工具使用等方面相较 GPT-5 Mini 有显著提升，同时运行速度提升超过 2 倍，成本约为标准版模型的 1/6，非常适合高吞吐量场景。 + +## 核心特性 + +- **接近旗舰级性能**：在 SWE-Bench Pro 上达到 54.38%，与标准版模型的 57.7% 非常接近，而成本仅约为其 1/6。 +- **强大的科学推理能力**：在 GPQA Diamond 上达到 87.5%，擅长研究生水平的科学推理任务。 +- **完整工具支持**：支持工具调用、联网搜索、图像分析以及原生计算机操作（Native Computer Use），完整保留核心能力。 +- **速度提升超过 2 倍**：相比 GPT-5 Mini，运行速度提升超过 2 倍，适用于对延迟敏感的场景。 +- **400K 上下文窗口**：支持 400,000 token 的上下文窗口，并支持视觉输入，适合处理中等规模的长文档。 + +## 最佳使用场景 + +- **编程助手与子代理（Sub-Agents）**：在编程基准测试中接近旗舰模型性能，能够以更低成本提供可靠的代码生成与修复能力。 +- **实时 AI 应用**：速度提升超过 2 倍，使其非常适合聊天机器人、实时翻译和交互式编程助手等场景。 +- **高吞吐数据处理**：兼具低成本与高性能，适合大规模文档分类、内容审核和数据提取流水线。 +- **桌面自动化代理**：完整支持原生计算机操作能力，可用于构建中等复杂度的桌面自动化工作流。 + +## 能力与局限 + +| 能力 | 详细说明 | +| :--- | :--- | +| **推理能力** | SWE-Bench Pro 54.38%，GPQA Diamond 87.5%；推理能力很强，但在最复杂的多步骤问题上仍略逊于标准版模型。 | +| **创作能力** | 能够胜任大多数日常文本与代码生成任务；但对于需要极深层推理的创作任务，能力仍弱于标准版模型。 | +| **多模态能力** | 支持文本和图像输入、文本输出；相比 GPT-5 Mini，在多模态理解和图像分析方面有显著提升。 | +| **响应速度** | 很快——相比 GPT-5 Mini 提升超过 2 倍，适合对延迟敏感的应用场景。 | +| **上下文窗口** | 400,000 tokens | +| **最大输出** | 官方尚未明确公布，估计约为 16,000–32,000 tokens | +| **知识截止时间** | 2025 年 8 月 31 日 | + +## 积分与定价 + +| 模型 | 输入（每 100 万 tokens） | 输出（每 100 万 tokens） | +| :--- | ----------------------: | ----------------------: | +| GPT-5.4 Mini | $0.75 | $4.50 | From 5a2589075a4b68fd0134119c21e0cf9c07150cfb Mon Sep 17 00:00:00 2001 From: ai-bankofai Date: Sat, 4 Apr 2026 21:57:43 +0800 Subject: [PATCH 09/46] Create gpt-5-4-nano.md --- docs/llmservice/models/gpt-5-4-nano.md | 36 ++++++++++++++++++++++++++ 1 file changed, 36 insertions(+) create mode 100644 docs/llmservice/models/gpt-5-4-nano.md diff --git a/docs/llmservice/models/gpt-5-4-nano.md b/docs/llmservice/models/gpt-5-4-nano.md new file mode 100644 index 00000000..8169bd05 --- /dev/null +++ b/docs/llmservice/models/gpt-5-4-nano.md @@ -0,0 +1,36 @@ +## Overview + +GPT-5.4 Nano is the smallest and most cost-effective variant in the GPT-5.4 family, released on March 17, 2026, designed for speed-critical and cost-sensitive scenarios. At just $0.20/$1.25 per MTok, it delivers reasoning capabilities with an Intelligence Index of 44.4, far above the median of 20 among similarly-priced models — ideal for classification, data extraction, ranking, and sub-agent tasks at scale. + +## Key Features + +- **Extreme Cost Efficiency**: $0.20/1M input + $1.25/1M output, blended rate (3:1 input-to-output ratio) of just $0.46/1M tokens — the most affordable option in the GPT-5.4 family. +- **High-Speed Inference**: ~221.8 tokens/second generation speed with 3.72-second time to first token, suitable for real-time systems. +- **Reasoning Model**: Despite being the smallest variant, GPT-5.4 Nano is still a reasoning model with extended thinking / chain-of-thought reasoning. +- **Multimodal Input**: Supports text and image input, suitable for lightweight multimodal tasks like visual classification and image analysis. +- **400K Context Window**: Same 400,000 token context window as Mini, providing ample input capacity. + +## Best Use Cases + +- **Classification & Data Extraction**: OpenAI's officially recommended core use case, delivering reliable performance for structured data processing, text classification, and information extraction. +- **Coding Sub-Agents**: Suitable for handling simpler supporting tasks in multi-agent architectures, such as code formatting, linting, and small code generation. +- **Real-Time Systems & High-Throughput Pipelines**: Ultra-low latency and cost combination makes it perfect for background tasks, real-time ranking, and large-scale automation pipelines. +- **Distributed Agent Architectures**: Serves as edge execution nodes in distributed agent systems, minimizing per-call cost and latency. + +## Capabilities and Limitations + +| Capability | Detailed Description | +| :--------------------- | :------------------------------------------------------------------------------------------------------------------------------------------------------------------- | +| **Reasoning Ability** | Intelligence Index 44.4 (median 20 for similar price tier), with chain-of-thought reasoning, but less capable than Mini and Standard on complex multi-step problems. | +| **Creative Ability** | Suitable for short text generation and template filling; not suited for long-form writing or creation requiring deep reasoning. | +| **Multimodal Ability** | Supports text and image input with text output; suitable for basic image classification and recognition, complex image analysis is better handled by larger models. | +| **Response Speed** | Very fast — ~221.8 tokens/second, 3.72s time to first token, the fastest model in the GPT-5.4 family. | +| **Context Window** | 400,000 tokens | +| **Max Output** | Not officially specified | +| **Knowledge Cutoff** | August 31, 2025 | + +## Credits and Pricing + +| Model | Input (per 1M tokens) | Output (per 1M tokens) | +| :----------- | --------------------: | ---------------------: | +| GPT-5.4 Nano | $0.20 | $1.2 | From 5771d735a774337f53391e5d1b1962b9f0eafcdb Mon Sep 17 00:00:00 2001 From: ai-bankofai Date: Sat, 4 Apr 2026 22:02:01 +0800 Subject: [PATCH 10/46] Create gpt-5-4-nano.md --- .../current/llmservice/models/gpt-5-4-nano.md | 36 +++++++++++++++++++ 1 file changed, 36 insertions(+) create mode 100644 i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gpt-5-4-nano.md diff --git a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gpt-5-4-nano.md b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gpt-5-4-nano.md new file mode 100644 index 00000000..6b89b31d --- /dev/null +++ b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gpt-5-4-nano.md @@ -0,0 +1,36 @@ +## 概述 + +GPT-5.4 Nano 是 GPT-5.4 系列中体量最小、成本最低的版本，于 2026 年 3 月 17 日发布，面向对速度敏感、对成本敏感的使用场景。其价格仅为每百万 tokens 输入 $0.20、输出 $1.25，同时具备推理能力，Intelligence Index 达到 44.4，远高于同价位模型 20 的中位数——非常适合大规模分类、数据提取、排序以及子代理任务。 + +## 核心特性 + +- **极致成本效率**：每 100 万输入 tokens $0.20 + 每 100 万输出 tokens $1.25，按 3:1 输入输出比例计算，综合成本仅为每 100 万 tokens $0.46——是 GPT-5.4 系列中最便宜的选项。 +- **高速推理**：生成速度约为 221.8 tokens/秒，首 token 时间为 3.72 秒，适合实时系统。 +- **推理模型**：尽管是最小版本，GPT-5.4 Nano 仍然是一个具备延展思考 / chain-of-thought 推理能力的推理模型。 +- **多模态输入**：支持文本和图像输入，适用于轻量级多模态任务，例如视觉分类和图像分析。 +- **400K 上下文窗口**：与 Mini 相同，支持 400,000 token 的上下文窗口，具备充足的输入容量。 + +## 最佳使用场景 + +- **分类与数据提取**：这是 OpenAI 官方推荐的核心使用场景，在结构化数据处理、文本分类和信息提取方面表现可靠。 +- **代码子代理**：适合在多代理架构中处理较简单的辅助任务，例如代码格式化、lint 检查和小规模代码生成。 +- **实时系统与高吞吐流水线**：超低延迟与低成本的组合，使其非常适合后台任务、实时排序和大规模自动化流水线。 +- **分布式代理架构**：可作为分布式代理系统中的边缘执行节点，尽可能降低单次调用成本与延迟。 + +## 能力与局限 + +| 能力 | 详细说明 | +| :--- | :--- | +| **推理能力** | Intelligence Index 为 44.4（同价位模型中位数为 20），具备 chain-of-thought 推理能力，但在复杂多步问题上弱于 Mini 和 Standard。 | +| **创作能力** | 适合短文本生成和模板填充；不适合长文本写作或需要深度推理的创作任务。 | +| **多模态能力** | 支持文本和图像输入、文本输出；适合基础图像分类和识别，更复杂的图像分析更适合由更大的模型处理。 | +| **响应速度** | 非常快——约 221.8 tokens/秒，首 token 时间 3.72 秒，是 GPT-5.4 系列中速度最快的模型。 | +| **上下文窗口** | 400,000 tokens | +| **最大输出** | 官方未明确说明 | +| **知识截止时间** | 2025 年 8 月 31 日 | + +## Credits 与定价 + +| 模型 | 输入（每 100 万 tokens） | 输出（每 100 万 tokens） | +| :--- | -----------------------: | -----------------------: | +| GPT-5.4 Nano | $0.20 | $1.2 | From 7011184da8d8f4e3810e9b8a08947b99d2249604 Mon Sep 17 00:00:00 2001 From: ai-bankofai Date: Mon, 6 Apr 2026 16:50:16 +0800 Subject: [PATCH 11/46] Create memory.md --- docs/llmservice/memory.md | 39 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 39 insertions(+) create mode 100644 docs/llmservice/memory.md diff --git a/docs/llmservice/memory.md b/docs/llmservice/memory.md new file mode 100644 index 00000000..610394f1 --- /dev/null +++ b/docs/llmservice/memory.md @@ -0,0 +1,39 @@ +# Memory Service + +## Introduction + +By default, Large Language Models (LLMs) are stateless—treating every new interaction as a blank slate. The **Memory** service bridges this gap by providing AI agents with long-term continuity. It enables models to retain context, learn user preferences, and deliver a highly personalized experience across multiple sessions, eliminating the need for users to repeat information. + +--- + +## Core Capabilities + +### 1. Smart Auto-Learning +When Memory is active, the system seamlessly evolves through daily interactions. It intelligently identifies and records key user preferences, stylistic choices, and critical facts directly from the conversation stream, building a persistent personalized profile over time. + +### 2. External History Import +To accelerate the personalization process, users can import existing chat histories. By providing exported logs from other applications, the AI can automatically parse, extract, and populate the **Memory Vault** with relevant historical context. + +### 3. Absolute User Control +Transparency and agency are central to our Memory architecture. Through a dedicated management interface, users have full authority to: +* **Review:** View exactly what information the AI has retained. +* **Curate:** Manually add custom instructions or specific context. +* **Manage:** Edit or delete existing memory nodes at any time. + +### 4. Incognito Mode +Privacy is built-in. Users can toggle Memory **OFF** to start an incognito session. In this state, the AI will not retrieve past memories nor record any new data from the ongoing conversation. + +--- + +## Key Advantages + +### ⚡ Lightning-Fast & Token-Efficient +Unlike traditional systems that inject massive history into every prompt, our **Progressive Loading** architecture utilizes a lightweight indexing system. It fetches specific memory nodes **on-demand** only when relevant, ensuring minimal latency and optimal token consumption. + +### 🎯 Tailored Companion Experience +The AI transcends being a generic assistant to become a specialized companion. By remembering project-specific details, formatting rules, and personal workflows, it significantly boosts productivity and interaction quality. + +### 🛡️ Zero-Hallucination Recall +By leveraging exact, user-curated memory nodes rather than broad semantic approximations, the system ensures high-fidelity recall. This prevents the AI from mixing up details or hallucinating past events, providing a "Source of Truth" for user context. + +--- From fbd0422796417c5f57c731fc09c779a8433f028c Mon Sep 17 00:00:00 2001 From: ai-bankofai Date: Mon, 6 Apr 2026 16:51:57 +0800 Subject: [PATCH 12/46] Create memory.md --- .../current/llmservice/memory.md | 35 +++++++++++++++++++ 1 file changed, 35 insertions(+) create mode 100644 i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/memory.md diff --git a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/memory.md b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/memory.md new file mode 100644 index 00000000..208f64f1 --- /dev/null +++ b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/memory.md @@ -0,0 +1,35 @@ +# Memory 记忆服务 + +## 简介 (Introduction) + +默认情况下，AI 模型是“无状态”的——它们将每一次新对话都视为白纸。**Memory（记忆）** 功能填补了这一空白，赋予 AI Agent 连续性。它允许 AI 保留上下文、学习用户偏好，并在多个会话中提供高度个性化的体验，用户无需反复重复相同的信息。 + +--- + +## 核心功能 (Core Capabilities) + +### 1. 智能自主学习 +当记忆功能开启时，AI 会从日常互动中无缝学习。它能智能地识别并记录对话中的关键用户偏好、风格选择和重要事实，随着时间的推移构建出个性化的用户画像。 + +### 2. 外部历史导入 +用户无需从零开始。该功能支持导入外部记忆：只需将其他应用的聊天记录导出并发送给 AI，系统便会自动解析数据、提取关键背景，并立即填充到用户的“记忆库”中。 + +### 3. 绝对的用户控制权 +透明度是记忆服务的核心。用户拥有专门的管理界面，可以清晰地查看 AI 记住了什么，并拥有完整的权限进行： +* **新增：** 手动添加自定义指令或背景信息。 +* **编辑/删除：** 随时修改或清除任何现有记忆。 + +### 4. 隐身模式 (Incognito Mode) +隐私保护触手可及。用户可以随时关闭记忆功能。在此状态下，当前的对话将作为“无痕会话”进行——AI 不会调用过去的记忆，也不会保存当前对话中的任何新偏好。 + +--- + +## 关键优势 (Key Advantages) + +* **极速响应与 Token 高效（渐进式加载）：** 传统的记忆系统往往会将所有历史记录塞进每一个 Prompt 中，导致响应缓慢且成本高昂。我们的记忆功能采用“渐进式加载”架构，AI 仅维护一个轻量级的索引，只有在与当前话题相关时才会按需提取详细的记忆节点。这确保了极快的响应速度，并最大程度地节省了 Token 消耗。 + +* **高度个性化的上下文：** AI 从一个通用的助手转变为量身定制的伙伴。它能记住项目细节、格式规范和个人习惯，从而实现更自然、更高效的工作流。 + +* **针对历史背景的“零幻觉”：** 由于系统依赖于精确的、用户策展的记忆节点，而非模糊的语义搜索，AI 能够准确地还原事实，避免混淆细节或虚构过去发生的事情。 + +--- From ec387cc8c4a2b78d69a639165f6799919ab16364 Mon Sep 17 00:00:00 2001 From: ai-bankofai Date: Mon, 6 Apr 2026 17:08:03 +0800 Subject: [PATCH 13/46] Rename gpt-5-4-mini.md to chatgpt-5-4-mini.md --- docs/llmservice/models/{gpt-5-4-mini.md => chatgpt-5-4-mini.md} | 0 1 file changed, 0 insertions(+), 0 deletions(-) rename docs/llmservice/models/{gpt-5-4-mini.md => chatgpt-5-4-mini.md} (100%) diff --git a/docs/llmservice/models/gpt-5-4-mini.md b/docs/llmservice/models/chatgpt-5-4-mini.md similarity index 100% rename from docs/llmservice/models/gpt-5-4-mini.md rename to docs/llmservice/models/chatgpt-5-4-mini.md From 5934bfff6ec8116234bf529405157923b6aa5c44 Mon Sep 17 00:00:00 2001 From: ai-bankofai Date: Mon, 6 Apr 2026 17:08:25 +0800 Subject: [PATCH 14/46] Rename gpt-5-4-nano.md to chatgpt-5-4-nano.md --- docs/llmservice/models/{gpt-5-4-nano.md => chatgpt-5-4-nano.md} | 0 1 file changed, 0 insertions(+), 0 deletions(-) rename docs/llmservice/models/{gpt-5-4-nano.md => chatgpt-5-4-nano.md} (100%) diff --git a/docs/llmservice/models/gpt-5-4-nano.md b/docs/llmservice/models/chatgpt-5-4-nano.md similarity index 100% rename from docs/llmservice/models/gpt-5-4-nano.md rename to docs/llmservice/models/chatgpt-5-4-nano.md From 1b4a17f7e106f2f37192a0d936657a76fd1b1a9e Mon Sep 17 00:00:00 2001 From: ai-bankofai Date: Mon, 6 Apr 2026 17:08:40 +0800 Subject: [PATCH 15/46] Rename gpt-5-4.md to chatgpt-5-4.md --- docs/llmservice/models/{gpt-5-4.md => chatgpt-5-4.md} | 0 1 file changed, 0 insertions(+), 0 deletions(-) rename docs/llmservice/models/{gpt-5-4.md => chatgpt-5-4.md} (100%) diff --git a/docs/llmservice/models/gpt-5-4.md b/docs/llmservice/models/chatgpt-5-4.md similarity index 100% rename from docs/llmservice/models/gpt-5-4.md rename to docs/llmservice/models/chatgpt-5-4.md From f30f6ef291826f0ec52571bcdda0c94cca41e246 Mon Sep 17 00:00:00 2001 From: ai-bankofai Date: Mon, 6 Apr 2026 17:10:20 +0800 Subject: [PATCH 16/46] Rename gpt-5-4-mini.md to chatgpt-5-4-mini.md --- .../llmservice/models/{gpt-5-4-mini.md => chatgpt-5-4-mini.md} | 0 1 file changed, 0 insertions(+), 0 deletions(-) rename i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/{gpt-5-4-mini.md => chatgpt-5-4-mini.md} (100%) diff --git a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gpt-5-4-mini.md b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/chatgpt-5-4-mini.md similarity index 100% rename from i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gpt-5-4-mini.md rename to i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/chatgpt-5-4-mini.md From e788c30396d8c7b24e2005daf2a2a5df7b30c03c Mon Sep 17 00:00:00 2001 From: ai-bankofai Date: Mon, 6 Apr 2026 17:10:39 +0800 Subject: [PATCH 17/46] Rename gpt-5-4-nano.md to chatgpt-5-4-nano.md --- .../llmservice/models/{gpt-5-4-nano.md => chatgpt-5-4-nano.md} | 0 1 file changed, 0 insertions(+), 0 deletions(-) rename i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/{gpt-5-4-nano.md => chatgpt-5-4-nano.md} (100%) diff --git a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gpt-5-4-nano.md b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/chatgpt-5-4-nano.md similarity index 100% rename from i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gpt-5-4-nano.md rename to i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/chatgpt-5-4-nano.md From 3f387eb62c0e9df88505f79236b1e2f218b7f070 Mon Sep 17 00:00:00 2001 From: ai-bankofai Date: Mon, 6 Apr 2026 17:10:54 +0800 Subject: [PATCH 18/46] Rename gpt-5-4.md to chatgpt-5-4.md --- .../current/llmservice/models/{gpt-5-4.md => chatgpt-5-4.md} | 0 1 file changed, 0 insertions(+), 0 deletions(-) rename i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/{gpt-5-4.md => chatgpt-5-4.md} (100%) diff --git a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gpt-5-4.md b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/chatgpt-5-4.md similarity index 100% rename from i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gpt-5-4.md rename to i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/chatgpt-5-4.md From 7b57c36a43f36416f34069307863ac0c6c7c4be4 Mon Sep 17 00:00:00 2001 From: ai-bankofai Date: Mon, 6 Apr 2026 17:19:04 +0800 Subject: [PATCH 19/46] Update and rename chatgpt-5-2.md to gpt-5-2.md --- docs/llmservice/models/{chatgpt-5-2.md => gpt-5-2.md} | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) rename docs/llmservice/models/{chatgpt-5-2.md => gpt-5-2.md} (84%) diff --git a/docs/llmservice/models/chatgpt-5-2.md b/docs/llmservice/models/gpt-5-2.md similarity index 84% rename from docs/llmservice/models/chatgpt-5-2.md rename to docs/llmservice/models/gpt-5-2.md index a098e9c1..ea0f7a35 100644 --- a/docs/llmservice/models/chatgpt-5-2.md +++ b/docs/llmservice/models/gpt-5-2.md @@ -1,7 +1,7 @@ -# ChatGPT-5.2 +# GPT-5.2 ## Overview -ChatGPT-5.2 is the latest generation of the flagship large language model developed by OpenAI. Building upon the powerful capabilities of the 5.1 version, it further optimizes the speed of multimodal processing and the execution efficiency of complex tasks, making it the ideal choice for professional users seeking ultimate performance and efficiency. +GPT-5.2 is the latest generation of the flagship large language model developed by OpenAI. Building upon the powerful capabilities of the 5.1 version, it further optimizes the speed of multimodal processing and the execution efficiency of complex tasks, making it the ideal choice for professional users seeking ultimate performance and efficiency. ## Key Features * **Efficient Multimodal Processing:** Significantly improves the parsing and generation speed of image and video content compared to 5.1, achieving a smoother multimodal interaction experience. From 7146b07e39393dff07df9d4289c73c34ecf5ea88 Mon Sep 17 00:00:00 2001 From: ai-bankofai Date: Mon, 6 Apr 2026 17:19:30 +0800 Subject: [PATCH 20/46] Rename chatgpt-5-4-mini.md to gpt-5-4-mini.md --- docs/llmservice/models/{chatgpt-5-4-mini.md => gpt-5-4-mini.md} | 0 1 file changed, 0 insertions(+), 0 deletions(-) rename docs/llmservice/models/{chatgpt-5-4-mini.md => gpt-5-4-mini.md} (100%) diff --git a/docs/llmservice/models/chatgpt-5-4-mini.md b/docs/llmservice/models/gpt-5-4-mini.md similarity index 100% rename from docs/llmservice/models/chatgpt-5-4-mini.md rename to docs/llmservice/models/gpt-5-4-mini.md From 69575d440d2ffc693ec3770fcbb9373a2e25c493 Mon Sep 17 00:00:00 2001 From: ai-bankofai Date: Mon, 6 Apr 2026 17:19:49 +0800 Subject: [PATCH 21/46] Rename chatgpt-5-4-nano.md to gpt-5-4-nano.md --- docs/llmservice/models/{chatgpt-5-4-nano.md => gpt-5-4-nano.md} | 0 1 file changed, 0 insertions(+), 0 deletions(-) rename docs/llmservice/models/{chatgpt-5-4-nano.md => gpt-5-4-nano.md} (100%) diff --git a/docs/llmservice/models/chatgpt-5-4-nano.md b/docs/llmservice/models/gpt-5-4-nano.md similarity index 100% rename from docs/llmservice/models/chatgpt-5-4-nano.md rename to docs/llmservice/models/gpt-5-4-nano.md From fa0360a5e5bffd149c44e145b7f2f2fc46d430e7 Mon Sep 17 00:00:00 2001 From: ai-bankofai Date: Mon, 6 Apr 2026 17:20:08 +0800 Subject: [PATCH 22/46] Rename chatgpt-5-4.md to gpt-5-4.md --- docs/llmservice/models/{chatgpt-5-4.md => gpt-5-4.md} | 0 1 file changed, 0 insertions(+), 0 deletions(-) rename docs/llmservice/models/{chatgpt-5-4.md => gpt-5-4.md} (100%) diff --git a/docs/llmservice/models/chatgpt-5-4.md b/docs/llmservice/models/gpt-5-4.md similarity index 100% rename from docs/llmservice/models/chatgpt-5-4.md rename to docs/llmservice/models/gpt-5-4.md From 39d0d97eaebce08ba1d228eebd9fefae0978b130 Mon Sep 17 00:00:00 2001 From: ai-bankofai Date: Mon, 6 Apr 2026 17:20:28 +0800 Subject: [PATCH 23/46] Update and rename chatgpt-5-mini.md to gpt-5-mini.md --- docs/llmservice/models/{chatgpt-5-mini.md => gpt-5-mini.md} | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) rename docs/llmservice/models/{chatgpt-5-mini.md => gpt-5-mini.md} (99%) diff --git a/docs/llmservice/models/chatgpt-5-mini.md b/docs/llmservice/models/gpt-5-mini.md similarity index 99% rename from docs/llmservice/models/chatgpt-5-mini.md rename to docs/llmservice/models/gpt-5-mini.md index 2cfa3b82..f8abb6f5 100644 --- a/docs/llmservice/models/chatgpt-5-mini.md +++ b/docs/llmservice/models/gpt-5-mini.md @@ -1,4 +1,4 @@ -# ChatGPT-5-mini +# GPT-5-mini ## Overview ChatGPT-5-mini is an efficient and economical lightweight language model. It is optimized for fast, smooth daily conversations and general tasks, making it a premier choice for cost-effective AI interaction within the Bank of AI ecosystem. From eb1786693137e3bd577099bb979191e2c9537ab9 Mon Sep 17 00:00:00 2001 From: ai-bankofai Date: Mon, 6 Apr 2026 17:20:47 +0800 Subject: [PATCH 24/46] Update and rename chatgpt-5-nano.md to gpt-5-nano.md --- docs/llmservice/models/{chatgpt-5-nano.md => gpt-5-nano.md} | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) rename docs/llmservice/models/{chatgpt-5-nano.md => gpt-5-nano.md} (99%) diff --git a/docs/llmservice/models/chatgpt-5-nano.md b/docs/llmservice/models/gpt-5-nano.md similarity index 99% rename from docs/llmservice/models/chatgpt-5-nano.md rename to docs/llmservice/models/gpt-5-nano.md index 38dd9559..77c877f8 100644 --- a/docs/llmservice/models/chatgpt-5-nano.md +++ b/docs/llmservice/models/gpt-5-nano.md @@ -1,4 +1,4 @@ -# ChatGPT-5-nano +# GPT-5-nano ## Overview ChatGPT-5-nano is an advanced language model that strikes an excellent balance between performance, speed, and cost. It is designed to provide near-professional AI capabilities at a moderate cost within the Bank of AI ecosystem. From 092c2da7ce8a4f72eb31db078572ecda51616698 Mon Sep 17 00:00:00 2001 From: ai-bankofai Date: Mon, 6 Apr 2026 17:24:17 +0800 Subject: [PATCH 25/46] Update and rename chatgpt-5-2.md to gpt-5-2.md --- .../current/llmservice/models/{chatgpt-5-2.md => gpt-5-2.md} | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) rename i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/{chatgpt-5-2.md => gpt-5-2.md} (86%) diff --git a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/chatgpt-5-2.md b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gpt-5-2.md similarity index 86% rename from i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/chatgpt-5-2.md rename to i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gpt-5-2.md index afdfbb6d..344d2e5a 100644 --- a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/chatgpt-5-2.md +++ b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gpt-5-2.md @@ -1,8 +1,8 @@ -# ChatGPT-5.2 +# GPT-5.2 ## 概述 -ChatGPT-5.2 是 OpenAI 最新一代旗舰大语言模型。在 5.1 的基础上，进一步优化了多模态处理速度与复杂任务执行效率，适合追求高性能与高效率的专业用户。 +GPT-5.2 是 OpenAI 最新一代旗舰大语言模型。在 5.1 的基础上，进一步优化了多模态处理速度与复杂任务执行效率，适合追求高性能与高效率的专业用户。 --- From 61ff0a30fa2abb5d1c93b94f86829154aff058f6 Mon Sep 17 00:00:00 2001 From: ai-bankofai Date: Mon, 6 Apr 2026 17:24:32 +0800 Subject: [PATCH 26/46] Rename chatgpt-5-4-mini.md to gpt-5-4-mini.md --- .../llmservice/models/{chatgpt-5-4-mini.md => gpt-5-4-mini.md} | 0 1 file changed, 0 insertions(+), 0 deletions(-) rename i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/{chatgpt-5-4-mini.md => gpt-5-4-mini.md} (100%) diff --git a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/chatgpt-5-4-mini.md b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gpt-5-4-mini.md similarity index 100% rename from i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/chatgpt-5-4-mini.md rename to i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gpt-5-4-mini.md From 621b795e443ffafacce25fb6f49a5b1fb9302af6 Mon Sep 17 00:00:00 2001 From: ai-bankofai Date: Mon, 6 Apr 2026 17:24:46 +0800 Subject: [PATCH 27/46] Rename chatgpt-5-4-nano.md to gpt-5-4-nano.md --- .../llmservice/models/{chatgpt-5-4-nano.md => gpt-5-4-nano.md} | 0 1 file changed, 0 insertions(+), 0 deletions(-) rename i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/{chatgpt-5-4-nano.md => gpt-5-4-nano.md} (100%) diff --git a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/chatgpt-5-4-nano.md b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gpt-5-4-nano.md similarity index 100% rename from i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/chatgpt-5-4-nano.md rename to i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gpt-5-4-nano.md From 88af7a47bd6f1a4e3b5e9f81c55e7f5c36462360 Mon Sep 17 00:00:00 2001 From: ai-bankofai Date: Mon, 6 Apr 2026 17:25:36 +0800 Subject: [PATCH 28/46] Rename chatgpt-5-4.md to gpt-5-4.md --- .../current/llmservice/models/{chatgpt-5-4.md => gpt-5-4.md} | 0 1 file changed, 0 insertions(+), 0 deletions(-) rename i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/{chatgpt-5-4.md => gpt-5-4.md} (100%) diff --git a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/chatgpt-5-4.md b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gpt-5-4.md similarity index 100% rename from i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/chatgpt-5-4.md rename to i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gpt-5-4.md From 7323802ea556144932912cd66f3e32d567514ff4 Mon Sep 17 00:00:00 2001 From: ai-bankofai Date: Mon, 6 Apr 2026 17:26:05 +0800 Subject: [PATCH 29/46] Update and rename chatgpt-5-mini.md to gpt-5-mini.md --- .../llmservice/models/{chatgpt-5-mini.md => gpt-5-mini.md} | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) rename i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/{chatgpt-5-mini.md => gpt-5-mini.md} (86%) diff --git a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/chatgpt-5-mini.md b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gpt-5-mini.md similarity index 86% rename from i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/chatgpt-5-mini.md rename to i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gpt-5-mini.md index dd550add..88772081 100644 --- a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/chatgpt-5-mini.md +++ b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gpt-5-mini.md @@ -1,8 +1,8 @@ -# ChatGPT-5-mini +# GPT-5-mini ## 概述 -ChatGPT-5-mini 是一款高效、经济的轻量级语言模型，针对日常对话与通用任务进行了优化，是 Bank of AI 生态中性价比极高的选择。 +GPT-5-mini 是一款高效、经济的轻量级语言模型，针对日常对话与通用任务进行了优化，是 Bank of AI 生态中性价比极高的选择。 --- From 0cac3f3446c6fdebf0a0ba3ef231e9521f5373b6 Mon Sep 17 00:00:00 2001 From: ai-bankofai Date: Mon, 6 Apr 2026 17:26:24 +0800 Subject: [PATCH 30/46] Update gpt-5-mini.md --- .../current/llmservice/models/gpt-5-mini.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gpt-5-mini.md b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gpt-5-mini.md index 88772081..e9ff4295 100644 --- a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gpt-5-mini.md +++ b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gpt-5-mini.md @@ -38,4 +38,4 @@ GPT-5-mini 是一款高效、经济的轻量级语言模型，针对日常对话 | 模型 | 输入（积分/Token） | 输出（积分/Token） | | :--- | :--- | :--- | -| **ChatGPT-5-mini** | 0.25 | 2.00 | +| **GPT-5-mini** | 0.25 | 2.00 | From 4c00a65faf1549d97f5363dff01fc58f1840731b Mon Sep 17 00:00:00 2001 From: ai-bankofai Date: Mon, 6 Apr 2026 17:26:54 +0800 Subject: [PATCH 31/46] Update chatgpt-5-nano.md --- .../current/llmservice/models/chatgpt-5-nano.md | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/chatgpt-5-nano.md b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/chatgpt-5-nano.md index 25620e8d..c96cb649 100644 --- a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/chatgpt-5-nano.md +++ b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/chatgpt-5-nano.md @@ -1,8 +1,8 @@ -# ChatGPT-5-nano +# GPT-5-nano ## 概述 -ChatGPT-5-nano 是一款在性能、速度和成本之间取得良好平衡的语言模型。在 Bank of AI 生态中，它以适中的成本提供接近专业级的 AI 能力。 +GPT-5-nano 是一款在性能、速度和成本之间取得良好平衡的语言模型。在 Bank of AI 生态中，它以适中的成本提供接近专业级的 AI 能力。 --- @@ -38,4 +38,4 @@ ChatGPT-5-nano 是一款在性能、速度和成本之间取得良好平衡的 | 模型 | 输入（积分/Token） | 输出（积分/Token） | | :--- | :--- | :--- | -| **ChatGPT-5-nano** | 0.05 | 0.40 | +| **GPT-5-nano** | 0.05 | 0.40 | From 432d13187d18774e5aa8fe6df21710664c129f71 Mon Sep 17 00:00:00 2001 From: ai-bankofai Date: Mon, 6 Apr 2026 17:27:18 +0800 Subject: [PATCH 32/46] Update gpt-5-2.md --- .../current/llmservice/models/gpt-5-2.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gpt-5-2.md b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gpt-5-2.md index 344d2e5a..4df6dc69 100644 --- a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gpt-5-2.md +++ b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gpt-5-2.md @@ -38,4 +38,4 @@ GPT-5.2 是 OpenAI 最新一代旗舰大语言模型。在 5.1 的基础上， | 模型 | 输入（积分/Token） | 输出（积分/Token） | | :--- | :--- | :--- | -| **ChatGPT-5.2** | 1.75 | 14.00 | +| **GPT-5.2** | 1.75 | 14.00 | From 5ee97a9b9d5e5abec0d600e4cd04cfabe6fbe523 Mon Sep 17 00:00:00 2001 From: ai-bankofai Date: Mon, 6 Apr 2026 17:27:59 +0800 Subject: [PATCH 33/46] Update gpt-5-2.md --- docs/llmservice/models/gpt-5-2.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/llmservice/models/gpt-5-2.md b/docs/llmservice/models/gpt-5-2.md index ea0f7a35..7400a7c4 100644 --- a/docs/llmservice/models/gpt-5-2.md +++ b/docs/llmservice/models/gpt-5-2.md @@ -27,4 +27,4 @@ GPT-5.2 is the latest generation of the flagship large language model developed | Model | Input (Credits/Token) | Output (Credits/Token) | | :--- | :--- | :--- | -| **ChatGPT-5.2** | 1.75 | 14.00 | +| **GPT-5.2** | 1.75 | 14.00 | From 135a1527b9f52701feabf0558b29ff5bc4822914 Mon Sep 17 00:00:00 2001 From: ai-bankofai Date: Mon, 6 Apr 2026 17:28:25 +0800 Subject: [PATCH 34/46] Update gpt-5-nano.md --- docs/llmservice/models/gpt-5-nano.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/llmservice/models/gpt-5-nano.md b/docs/llmservice/models/gpt-5-nano.md index 77c877f8..0a4c1b2c 100644 --- a/docs/llmservice/models/gpt-5-nano.md +++ b/docs/llmservice/models/gpt-5-nano.md @@ -27,4 +27,4 @@ ChatGPT-5-nano is an advanced language model that strikes an excellent balance b | Model | Input (Credits/Token) | Output (Credits/Token) | | :--- | :--- | :--- | -| **ChatGPT-5-nano** | 0.05 | 0.40 | +| **GPT-5-nano** | 0.05 | 0.40 | From abd9d80955634c4ef499c77c8502c60d445f68eb Mon Sep 17 00:00:00 2001 From: ai-bankofai Date: Mon, 6 Apr 2026 17:38:57 +0800 Subject: [PATCH 35/46] Update API.md --- .../current/llmservice/api/API.md | 530 ++++++++++++------ 1 file changed, 348 insertions(+), 182 deletions(-) diff --git a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/api/API.md b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/api/API.md index 55ecb3df..9e6d82c9 100644 --- a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/api/API.md +++ b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/api/API.md @@ -1,259 +1,425 @@ # AI API -聊天补全。认证：Bearer token。非流式返回：JSON（choices[].content）。流式返回：SSE（choices[].delta.content）。 +聊天补全。认证方式：Bearer Token。非流式响应为 JSON（`choices[].content`）；流式响应为 SSE 分块（`choices[].delta.content`）。 - **版本：** 1.0 - -## Servers（服务器） - -| URL | 描述 | -|-----|------| -| `https://api.bankofai.com` | 生产环境 | +- **Base URL：** `https://api.bankofai.io` +- **OpenAPI：** 3.1.0 --- -## Authentication（认证） +## 认证 -### Bearer 认证 +### Bearer Token -- **类型：** HTTP Bearer -- **格式：** JWT -- **说明：** Bearer \，例如：`Bearer sk-xxx` +- **类型：** HTTP Bearer（JWT） +- **请求头：** `Authorization: Bearer ` +- **示例：** `Bearer sk-xxx` -### API Key 认证 +### API Key（仅 Messages 端点支持） - **类型：** API Key -- **位置：** Header -- **字段名：** `x-api-key` -- **说明：** API Key 认证，例如：`x-api-key: your-api-key` +- **请求头：** `x-api-key: ` --- -## Endpoints（接口） +## 端点 -### 模型列表 +### 1. 获取模型列表 -#### `GET /v1/models` - 获取模型列表（OpenAI 兼容） +`GET /v1/models` -获取可用模型列表。认证：Bearer token。返回：object，success，data。 +获取可用模型列表。认证方式：Bearer Token。 -**认证方式：** Bearer Auth +**认证：** Bearer Token -**响应：** +**200 响应：** + +```json +{ + "object": "list", + "success": true, + "data": [ + { + "id": "gpt-5.2", + "object": "model", + "created": 1626777600, + "owned_by": "openai", + "supported_endpoint_types": ["openai", "anthropic"] + } + ] +} +``` | 状态码 | 描述 | |--------|------| -| 200 | object: list；success: true；data: 模型数组（包含 id、object、created、owned_by） | -| 400 | 请求错误 - 参数无效或请求体格式错误 | -| 401 | 未授权 - 缺少或无效认证 | -| 403 | 禁止访问 - 权限不足、配额不足或被封禁 | -| 429 | 请求过多 - 触发限流 | +| 200 | 成功 - 返回模型列表 | +| 400 | 错误请求 - 参数无效或请求体格式错误 | +| 401 | 未授权 - 认证无效或缺失 | +| 403 | 禁止访问 - 无权限、额度不足或账号被封禁 | +| 429 | 请求过多 - 超出速率限制 | | 500 | 服务器内部错误 | -**200 响应结构：** [V1ModelsResponse](#v1modelsresponse) - -**错误响应结构：** [ErrorResponse](#errorresponse) - --- -### Messages（消息接口） +### 2. 聊天补全（OpenAI 兼容） -#### `POST /v1/messages` - 发送消息（Claude 兼容） +`POST /v1/chat/completions` -接收消息列表并返回模型生成的响应。支持单轮和多轮对话。使用 x-api-key 认证。支持流式（SSE）和非流式返回。 +接收一组消息并返回模型生成的回复。支持单轮和多轮对话。响应既可以是单个 JSON 对象，也可以通过流式（SSE）返回。 -**认证方式：** API Key（`x-api-key`） +**认证：** Bearer Token -**请求体：** [ChatCompletionsRequest](#chatcompletionsrequest)（必填，`application/json`） +#### 请求体 -**响应：** +| 参数 | 类型 | 必填 | 描述 | +|------|------|------|------| +| `model` | string | **是** | 要使用的模型 ID（例如 `gpt-5.2`）。 | +| `messages` | array | **是** | 对话中的消息列表。参见 [ChatMessage](#chatmessage)。 | +| `stream` | boolean | 否 | 若为 true，将通过 Server-Sent Events 返回部分消息增量。默认值为 `false`。 | +| `max_tokens` | integer | 否 | 本次补全最多可生成的 token 数。 | +| `temperature` | number | 否 | 采样温度，范围 0 到 2。值越高，结果越随机。默认 `1`。 | +| `top_p` | number | 否 | Nucleus Sampling，仅考虑累计概率达到 top_p 的 token。默认 `1`。 | +| `stop` | string \| string[] | 否 | 最多 4 个停止序列，命中后 API 将停止生成。 | +| `n` | integer | 否 | 生成多少个补全选项。默认 `1`。 | +| `frequency_penalty` | number | 否 | 范围 -2.0 到 2.0。用于惩罚重复 token。默认 `0`。 | +| `presence_penalty` | number | 否 | 范围 -2.0 到 2.0。用于惩罚已在文本中出现过的 token。默认 `0`。 | +| `seed` | integer | 否 | 随机种子，用于确定性采样（如果模型支持）。 | +| `response_format` | object | 否 | 指定输出格式：`{ "type": "text" }`、`{ "type": "json_object" }` 或 `json_schema`。 | +| `tools` | array | 否 | 模型可调用的工具列表。参见 [ChatTool](#chattool)。 | +| `tool_choice` | string \| object | 否 | 可选值：`"auto"`、`"none"`、`"required"`，或 `{ "type": "function", "function": { "name": "..." } }`。 | +| `user` | string | 否 | 可选的终端用户标识，用于滥用监控。 | +| `web_search_options` | object | 否 | 为支持的模型开启网页搜索。参见 [WebSearchOptions](#websearchoptions)。 | + +#### 请求示例 + +```json +{ + "model": "gpt-5.2", + "messages": [ + { "role": "system", "content": "You are a helpful assistant." }, + { "role": "user", "content": "Hello" } + ], + "stream": false, + "max_tokens": 1024, + "temperature": 1 +} +``` + +#### 响应（非流式） + +```json +{ + "id": "chatcmpl-xxx", + "object": "chat.completion", + "created": 1677652288, + "model": "gpt-5.2", + "choices": [ + { + "index": 0, + "message": { + "role": "assistant", + "content": "Hello! How can I help you?", + "refusal": null, + "annotations": [] + }, + "finish_reason": "stop" + } + ], + "usage": { + "prompt_tokens": 12, + "completion_tokens": 8, + "total_tokens": 20, + "prompt_tokens_details": { "cached_tokens": 0, "audio_tokens": 0 }, + "completion_tokens_details": { + "reasoning_tokens": 0, + "audio_tokens": 0, + "accepted_prediction_tokens": 0, + "rejected_prediction_tokens": 0 + } + } +} +``` + +#### 响应（流式） + +每个 SSE 分块的 `object` 都是 `"chat.completion.chunk"`，其中 `choices[].delta.content` 包含增量文本。最后一个分块会包含 `usage` 和 `finish_reason`。 | 状态码 | 描述 | |--------|------| -| 200 | 成功（结构取决于是否使用流式） | -| 400 | 请求错误 - 参数或格式错误 | -| 401 | 未授权 - API Key 无效或缺失 | -| 403 | 禁止访问 - 权限不足或模型受限 | -| 429 | 请求过多 - 限流 | +| 200 | 成功 | +| 400 | 错误请求 - 参数无效、请求体格式错误或请求非法 | +| 401 | 未授权 - 认证无效或缺失 | +| 403 | 禁止访问 - 无权限、额度不足或模型访问受限 | +| 429 | 请求过多 - 超出速率限制 | | 500 | 服务器内部错误 | -| 502 | 网关错误 - 上游服务异常 | -| 503 | 服务不可用 - 系统过载或无可用通道 | - -**200 返回类型：** -- `application/json` -- `text/event-stream` - -**错误响应结构：** [ErrorResponse](#errorresponse) +| 502 | 网关错误 - 上游服务错误 | +| 503 | 服务不可用 - 服务过载或无可用通道 | --- -### Chat Completions（聊天补全） +### 3. Messages（Claude 兼容） -#### `POST /v1/chat/completions` - 创建聊天补全（OpenAI 兼容） +`POST /v1/messages` -接收消息列表并返回模型生成结果。支持单轮和多轮对话。使用 Bearer token 认证。支持流式和非流式返回。 +接收一组消息并返回模型生成的回复。支持单轮和多轮对话。可通过 `x-api-key` 请求头或 Bearer Token 进行认证。响应既可以是单个 JSON 对象，也可以通过流式（SSE）返回。 -**认证方式：** Bearer Auth +**认证：** API Key（`x-api-key`）或 Bearer Token -**请求体：** [ChatCompletionsRequest](#chatcompletionsrequest) +#### 请求体 -**响应：** +| 参数 | 类型 | 必填 | 描述 | +|------|------|------|------| +| `model` | string | **是** | 模型 ID（例如 `claude-sonnet-4-6`、`claude-opus-4-6`、`claude-haiku-4-5`）。 | +| `max_tokens` | integer | **是** | 最多生成的 token 数。不同模型的最大值不同。 | +| `messages` | array | **是** | 输入消息。用户与助手轮流出现。上限：100,000 条消息。参见 [MessagesMessageItem](#messagesmessageitem)。 | +| `system` | string \| array | 否 | 系统提示词。可以是纯字符串，也可以是文本块数组（用于 `cache_control`）。 | +| `stream` | boolean | 否 | 是否使用 SSE 流式返回。默认 `false`。 | +| `temperature` | number | 否 | 随机性（0.0 - 1.0）。分析型任务建议接近 0.0，创意型任务建议接近 1.0。默认 `1`。 | +| `top_p` | number | 否 | Nucleus Sampling。默认 `1`。 | +| `top_k` | integer | 否 | 仅从概率最高的前 K 个选项中采样。默认关闭。 | +| `stop_sequences` | string[] | 否 | 自定义停止文本序列，命中后停止生成。 | +| `metadata` | object | 否 | 请求元数据。支持 `user_id`（不透明标识符）。 | +| `thinking` | object | 否 | 扩展思考配置。参见 [ThinkingConfig](#thinkingconfig)。 | +| `tools` | array | 否 | 模型可调用的工具定义。参见 [Tool](#tool-anthropic)。 | +| `tool_choice` | object | 否 | 模型如何使用工具：`auto`、`any`、`tool` 或 `none`。 | + +#### 请求示例 + +```json +{ + "model": "claude-sonnet-4-6", + "max_tokens": 1024, + "messages": [ + { "role": "user", "content": "Hello, Claude!" } + ], + "system": "You are a helpful assistant.", + "temperature": 1.0 +} +``` + +#### 响应（非流式） + +```json +{ + "id": "chatcmpl-xxx", + "type": "message", + "role": "assistant", + "content": [ + { "type": "text", "text": "Hello! How can I help you?" } + ], + "stop_reason": "end_turn", + "model": "gpt-5", + "usage": { + "input_tokens": 4, + "cache_creation_input_tokens": 0, + "cache_read_input_tokens": 0, + "output_tokens": 12, + "claude_cache_creation_5_m_tokens": 0, + "claude_cache_creation_1_h_tokens": 0 + } +} +``` + +#### 响应（流式 - SSE 事件） + +流式响应会发出以下事件类型： + +| 事件类型 | 描述 | 关键字段 | +|----------|------|----------| +| `message_start` | 初始消息元数据 | `message`（id、model、role、usage） | +| `content_block_start` | 开始新的内容块 | `index`、`content_block`（type、text） | +| `content_block_delta` | 增量内容 | `index`、`delta`（type: `text_delta`、text） | +| `content_block_stop` | 内容块结束 | `index` | +| `message_stop` | 消息完成 | - | | 状态码 | 描述 | |--------|------| | 200 | 成功 | -| 400 | 请求错误 | -| 401 | 未授权 | -| 403 | 禁止访问 | -| 429 | 限流 | -| 500 | 服务器错误 | -| 502 | 网关错误 | -| 503 | 服务不可用 | - -**返回类型：** -- `application/json` -- `text/event-stream` +| 400 | 错误请求 - 参数无效、请求体格式错误或请求非法 | +| 401 | 未授权 - API Key 无效或缺失 | +| 403 | 禁止访问 - 无权限、额度不足或模型访问受限 | +| 429 | 请求过多 - 超出速率限制 | +| 500 | 服务器内部错误 | +| 502 | 网关错误 - 上游服务错误 | +| 503 | 服务不可用 - 服务过载或无可用通道 | --- -## Schemas（数据结构） - -### ErrorResponse（错误响应） +## 数据模型 -| 字段 | 类型 | 描述 | -|------|------|------| -| error | object | 错误信息 | -| error.message | string | 错误描述 | -| error.type | string | 错误类型 | -| error.param | string \| null | 相关参数 | -| error.code | string \| null | 错误代码 | - ---- - -### V1ModelsResponse +### ChatMessage -| 字段 | 类型 | 示例 | 描述 | +| 字段 | 类型 | 必填 | 描述 | |------|------|------|------| -| object | string | "list" | | -| success | boolean | true | | -| data | array | | 模型数组 | +| `role` | string | **是** | `"system"`、`"user"`、`"assistant"` 或 `"tool"` | +| `content` | string | **是** | 消息内容。对于 `tool` 角色，这里是工具调用结果。 | +| `name` | string | 否 | 消息作者的可选名称。 | +| `tool_call_id` | string | 否 | 当 `role` 为 `"tool"` 时，对应的工具调用 ID。 | +| `tool_calls` | array | 否 | 当 `role` 为 `"assistant"` 且模型调用了工具时使用。格式为 `{ id, type, function: { name, arguments } }` 的数组。 | ---- - -### V1ModelItem +### MessagesMessageItem -| 字段 | 类型 | 示例 | 描述 | +| 字段 | 类型 | 必填 | 描述 | |------|------|------|------| -| id | string | "gpt-5.2" | | -| object | string | "model" | | -| created | integer | 1626777600 | | -| owned_by | string | "openai" | | - ---- +| `role` | string | **是** | `"user"` 或 `"assistant"`（不支持 `"system"`，请使用顶层 `system` 参数）。 | +| `content` | string \| array | **是** | 文本字符串，或内容块数组（text、image、tool_use、tool_result）。 | + +### 内容块类型（Messages API） + +#### TextBlockParam + +```json +{ "type": "text", "text": "Hello, Claude!", "cache_control": { "type": "ephemeral" } } +``` + +#### ImageBlockParam + +Base64 来源： + +```json +{ + "type": "image", + "source": { + "type": "base64", + "media_type": "image/jpeg", + "data": "/9j/4AAQSkZJRg..." + } +} +``` + +URL 来源： + +```json +{ + "type": "image", + "source": { + "type": "url", + "url": "https://example.com/image.jpg" + } +} +``` + +支持的媒体类型：`image/jpeg`、`image/png`、`image/gif`、`image/webp` + +#### ToolUseBlockParam（来自 assistant） + +```json +{ + "type": "tool_use", + "id": "toolu_01D7FLrfh4GYq7yT1ULFeyMV", + "name": "get_stock_price", + "input": { "ticker": "AAPL" } +} +``` + +#### ToolResultBlockParam（来自 user） + +```json +{ + "type": "tool_result", + "tool_use_id": "toolu_01D7FLrfh4GYq7yT1ULFeyMV", + "content": "259.75 USD", + "is_error": false +} +``` + +### ThinkingConfig + +启用扩展思考，让 Claude 展示其推理过程。 + +**启用：** + +```json +{ "type": "enabled", "budget_tokens": 1024 } +``` + +- `budget_tokens`：必须大于等于 1024，并且小于 `max_tokens`。 + +**禁用：** + +```json +{ "type": "disabled" } +``` + +### Tool（Anthropic） + +```json +{ + "name": "get_stock_price", + "description": "Get the current stock price for a given ticker symbol.", + "input_schema": { + "type": "object", + "properties": { + "ticker": { "type": "string" } + }, + "required": ["ticker"] + } +} +``` + +### ToolChoice（Anthropic） + +| 类型 | 描述 | +|------|------| +| `{ "type": "auto" }` | 模型自行决定是否使用工具。支持 `disable_parallel_tool_use`。 | +| `{ "type": "any" }` | 模型将使用任意可用工具。支持 `disable_parallel_tool_use`。 | +| `{ "type": "tool", "name": "..." }` | 模型将使用指定工具。支持 `disable_parallel_tool_use`。 | +| `{ "type": "none" }` | 模型不会使用工具。 | -### ChatCompletionsRequest - -**必填字段：** `model`, `messages` - -| 字段 | 类型 | 描述 | -|------|------|------| -| model | string | 模型 ID | -| messages | array | 对话消息列表 | -| stream | boolean | 是否流式返回 | -| max_tokens | integer | 最大生成 token | -| temperature | number | 随机性（0-2） | -| top_p | number | 核采样 | -| stop | string \| array | 停止词 | -| n | integer | 返回数量 | -| frequency_penalty | number | 重复惩罚 | -| presence_penalty | number | 出现惩罚 | -| seed | integer | 随机种子 | -| response_format | object | 输出格式 | -| tools | array | 工具调用 | -| tool_choice | string \| object | 工具选择 | -| user | string | 用户标识 | -| web_search_options | object | Web 搜索配置 | +### ChatTool ---- +```json +{ + "type": "function", + "function": { + "name": "get_weather", + "description": "Get weather for a location", + "parameters": { + "type": "object", + "properties": { + "location": { "type": "string" } + }, + "required": ["location"] + } + } +} +``` ### WebSearchOptions | 字段 | 类型 | 描述 | |------|------|------| -| search_context_size | string | 上下文大小（low/medium/high） | -| user_location | object | 用户位置 | - ---- - -### ChatMessage - -| 字段 | 类型 | 描述 | -|------|------|------| -| role | string | system / user / assistant / tool | -| content | string | 消息内容 | -| name | string | 可选 | -| tool_call_id | string | 工具调用 ID | -| tool_calls | array | 工具调用列表 | - ---- +| `search_context_size` | string | `"low"`、`"medium"` 或 `"high"`，表示网页搜索结果占用的上下文大小。 | +| `user_location` | object | 用户的大致位置（国家 ISO 3166-1 alpha-2、城市、地区、时区）。 | ### ChatResponseFormat | 字段 | 类型 | 描述 | |------|------|------| -| type | string | text / json_object | -| json_schema | any | JSON Schema | +| `type` | string | `"text"` 或 `"json_object"` | +| `json_schema` | object | 当 `type` 为 `json_schema` 时，指定可选的输出结构 schema。 | --- -### ChatTool - -| 字段 | 类型 | 描述 | -|------|------|------| -| type | string | function | -| function | object | 函数定义 | +## 错误响应 ---- - -### ChatToolFunction - -| 字段 | 类型 | 描述 | -|------|------|------| -| name | string | 函数名 | -| description | string | 描述 | -| parameters | any | 参数 | - ---- - -### ChatToolCallItem - -| 字段 | 类型 | 描述 | -|------|------|------| -| id | string | 调用 ID | -| type | string | function | -| function | object | 调用函数 | - ---- - -### ChatCompletionsResponse - -| 字段 | 类型 | 描述 | -|------|------|------| -| id | string | 请求 ID | -| object | string | 类型 | -| created | integer | 时间戳 | -| model | string | 模型 | -| choices | array | 返回结果 | -| usage | object | Token 使用情况 | - ---- +所有错误响应都遵循以下格式： -### ChatUsage +```json +{ + "error": { + "message": "Error message", + "type": "invalid_request_error", + "param": null, + "code": null + } +} +``` | 字段 | 类型 | 描述 | |------|------|------| -| prompt_tokens | integer | 输入 token | -| completion_tokens | integer | 输出 token | -| total_tokens | integer | 总 token | -| prompt_tokens_details | object | 输入详情 | -| completion_tokens_details | object | 输出详情 | +| `message` | string | 错误信息 | +| `type` | string | 错误类型（例如 `invalid_request_error`） | +| `param` | string \| null | 相关参数 | +| `code` | string \| null | 错误代码 | From 8455399fb88855b2cd08a6f91b58cf16b8e8778f Mon Sep 17 00:00:00 2001 From: ai-bankofai Date: Mon, 6 Apr 2026 17:49:08 +0800 Subject: [PATCH 36/46] Update pricing-and-usage.md --- docs/llmservice/pricing-and-usage.md | 71 ++++++++++++++++------------ 1 file changed, 40 insertions(+), 31 deletions(-) diff --git a/docs/llmservice/pricing-and-usage.md b/docs/llmservice/pricing-and-usage.md index 11020dc6..a60f92c3 100644 --- a/docs/llmservice/pricing-and-usage.md +++ b/docs/llmservice/pricing-and-usage.md @@ -1,49 +1,58 @@ -# Pricing and Usage - ## Credits & Pricing -The Bank of AI platform utilizes a unified credit system to measure and settle usage for all AI services. +The platform utilizes a unified credit system to measure and settle usage for all AI services. + +**Credit Calculation Rules:** The number of tokens consumed in each interaction with the AI is converted into corresponding credits based on the pricing standards of different models and deducted from your account balance. -* **Credit Calculation Rules:** The number of tokens consumed in each interaction with the AI is converted into corresponding credits based on the pricing standards of different models and deducted from your account balance. -* **Token Consumption Details:** In the AI response details, the platform displays the breakdown of token consumption, helping you understand the specific sources of credit usage and optimize future usage patterns. -* **Pricing for Different Models:** Pricing varies due to differences in capabilities and computational costs among AI models. Generally, more capable models consume more credits. The web search feature incurs an additional fee and is charged on a pay-per-use basis. Some models do not support web search marked as "-". +**Token Consumption Details:** In the AI response details, the platform displays the breakdown of token consumption, helping you understand the specific sources of credit usage and optimize future usage patterns. -### Specific Model Pricing +**Pricing for Different Models:** Pricing varies due to differences in capabilities and computational costs among AI models. Generally, more capable models consume more credits. The web search feature incurs an additional fee and is charged on a pay-per-use basis. Some models do not support web search marked as "-". For specific model pricing, please check here： -| Model | Input (Credits/Token) | Output (Credits/Token) | Web Search (Credits/Use) | -| :--- | :--- | :--- | :--- | -| ChatGPT-5.2 | 1.75 | 14.00 | 10,000 | -| ChatGPT-5-mini | 0.25 | 2.00 | 10,000 | -| ChatGPT-5-nano | 0.05 | 0.40 | - | -| Claude Opus 4.6 | 5.00 | 25.00 | 10,000 | -| Claude Opus 4.5 | 5.00 | 25.00 | 10,000 | -| Claude Sonnet 4.6 | 3.00 | 15.00 | 10,000 | -| Claude Sonnet 4.5 | 3.00 | 15.00 | 10,000 | -| Claude Haiku 4.5 | 1.00 | 5.00 | 10,000 | -| Gemini 3.1 Pro | 2.00 | 12.00 | 14,000 | -| Gemini 3 Flash | 0.50 | 3.00 | 14,000 | +| Model | Input (Credits/Token) | Output (Credits/Token) | Web Search(Credits/Use) | +| :---------------- | --------------------: | ---------------------: | ----------------------: | +| MiniMax-M2.5 | 0.30 | 1.20 | - | +| Kimi-K2.5 | 0.23 | 3.00 | - | +| GLM-5 | 0.30 | 2.55 | - | +| GPT-5.4 | 2.50 | 15.00 | 10,000 | +| GPT-5.2 | 1.75 | 14.00 | 10,000 | +| GPT-5.4-mini | 0.75 | 4.50 | 10,000 | +| GPT-5-mini | 0.25 | 2.00 | 10,000 | +| GPT-5.4-nano | 0.20 | 1.20 | 10,000 | +| GPT-5-nano | 0.05 | 0.40 | - | +| Claude Opus 4.6 | 5.00 | 25.00 | 10,000 | +| Claude Opus 4.5 | 5.00 | 25.00 | 10,000 | +| Claude Sonnet 4.6 | 3.00 | 15.00 | 10,000 | +| Claude Sonnet 4.5 | 3.00 | 15.00 | 10,000 | +| Claude Haiku 4.5 | 1.00 | 5.00 | 10,000 | +| Gemini 3.1 pro | 2.00 | 12.00 | 14,000 | +| Gemini 3 flash | 0.50 | 3.00 | 14,000 | -> **Calculation Example:** If you use a model with a rate of 1.25 (Input) and 10.00 (Output) to ask a question (10 input tokens) and receive a response (50 output tokens), the dialogue consumes **512.5 credits** (10 × 1.25 + 50 × 10). You can check the specific usage by hovering over the model name in the bottom right corner of the chat. +For example, if you use GPT-5.2 to ask a question (10 input tokens) and the AI responds with an answer (50 output tokens), the entire dialogue consumes 512.5 credits (calculated as: 10 × 1.25 + 50 × 10). You can check the specific credit usage by hovering over the model name in the bottom right corner. ## Usage Information -You can view detailed data regarding all your consumption on the **Usage** page via the left navigation bar. +You can view detailed data regarding all your consumption on the **Usage** page via the left navigation bar, ensuring that every expense is transparent and traceable. + +**Usage Overview:** The top of the page displays your credit balance and total consumption for the current month, giving you a clear view of your account status at a glance. + +**Monthly Usage Chart:** Through an intuitive bar chart, you can quickly track usage fluctuations over the past year, facilitating cost analysis and budget planning. -* **Usage Overview:** Displays your credit balance and total consumption for the current month. -* **Monthly Usage Chart:** An intuitive bar chart to track usage fluctuations over the past year. -* **Usage Detail:** Every record corresponds precisely to a single AI interaction, including creation time, model used, token usage, credits consumed, and response time. +**Usage detail:** In the **Usage detail** table, every record corresponds precisely to a single AI interaction. The table lists the creation time, type, model used, token usage, credits consumed, and response time, providing you with the most granular consumption data. ## Deposit -Bank of AI operates on a pre-paid model. Leveraging secure blockchain technology, the platform offers a convenient deposit experience. +The platform operates on a pre-paid model; you must top up your account to obtain credits. Leveraging the advantages of the TRON network, the platform offers a secure and convenient deposit experience. -* **Deposit Process:** On the **Top up** page, the platform will guide you to pay using your connected Web3 wallet. Simply confirm the transaction in the wallet pop-up window to complete it. -* **Supported Token Types:** The platform supports various mainstream tokens on supported networks (including TRON and BNB Chain). -* **Arrival Time:** Once the transaction is confirmed on the blockchain, the system will automatically issue the equivalent value of credits to your account, typically within a few minutes. +**Deposit Process:** On the **Top up** page, the platform will guide you to pay using your connected TronLink wallet. You do not need to manually enter addresses; simply confirm the transaction in the wallet pop-up window to complete it. + +**Supported Token Types:** The platform supports various mainstream tokens within the TRON ecosystem, including TRX, USDT, USDD, and USD1. + +**Arrival Time:** Once the transfer transaction is confirmed on the TRON chain, the system will automatically issue the equivalent value of credits to your account. Typically, this process is completed within a few minutes. ## Billing & Invoices -View your complete deposit history under the **History** tab on the **Top up** page. +You can view your complete deposit history under the **History** tab on the **Top up** page. + +**Deposit Records:** The invoice list clearly displays the creation time, type, transaction hash, token, and other information for each deposit. -* **Deposit Records:** Displays creation time, type, transaction hash, and token information for each deposit. -* **Transparency:** You can click the transaction hash to verify details on the corresponding blockchain explorer (e.g., TRONSCAN or BscScan). +**Transaction Hash Query:** You can click the transaction hash and verify the transaction details to ensure transparency. From 9e2e104ae0a19d24e9c368d701746aaeb03f8fa8 Mon Sep 17 00:00:00 2001 From: ai-bankofai Date: Mon, 6 Apr 2026 17:53:02 +0800 Subject: [PATCH 37/46] Update pricing-and-usage.md --- .../current/llmservice/pricing-and-usage.md | 66 ++++++++++--------- 1 file changed, 34 insertions(+), 32 deletions(-) diff --git a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/pricing-and-usage.md b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/pricing-and-usage.md index ee8d59e7..847fb7e3 100644 --- a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/pricing-and-usage.md +++ b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/pricing-and-usage.md @@ -1,56 +1,58 @@ -# 计费与使用 +## Credits 与定价 -## 积分与定价 +平台采用统一的 Credits 积分系统来计量和结算所有 AI 服务的使用量。 -Bank of AI 平台采用统一的积分（Credits）体系，对所有 AI 服务进行计量与结算。 +**Credits 计算规则：** 每次与 AI 交互所消耗的 token，会根据不同模型的定价标准换算为相应的 Credits，并从你的账户余额中扣除。 -- **计费规则：** 每次与 AI 交互所消耗的 Token，会根据不同模型的定价标准换算为对应积分，并从账户余额中扣除 -- **Token 消耗明细：** 在 AI 回复详情中可查看 Token 使用拆分，帮助理解消耗来源并优化使用策略 -- **模型定价差异：** 不同模型因能力与计算成本不同，价格有所差异。一般来说，能力越强的模型消耗越高 -- **联网搜索费用：** Web 搜索为额外收费功能，按次计费。部分模型不支持该功能（标记为 "-"） +**Token 消耗明细：** 在 AI 响应详情中，平台会展示 token 消耗的拆分明细，帮助你了解 Credits 的具体消耗来源，并优化后续使用方式。 -### 模型定价 +**不同模型的定价：** 由于不同 AI 模型在能力和计算成本上存在差异，其定价也有所不同。通常，能力越强的模型消耗的 Credits 越多。网页搜索功能会产生额外费用，并按次收费。部分模型不支持网页搜索，以 `-` 标记。具体模型定价如下： -| 模型 | 输入（积分/Token） | 输出（积分/Token） | 联网搜索（积分/次） | -| :--- | :--- | :--- | :--- | -| ChatGPT-5.2 | 1.75 | 14.00 | 10,000 | -| ChatGPT-5-mini | 0.25 | 2.00 | 10,000 | -| ChatGPT-5-nano | 0.05 | 0.40 | - | +| 模型 | 输入（Credits/Token） | 输出（Credits/Token） | 网页搜索（Credits/次） | +| :--- | --------------------: | --------------------: | ---------------------: | +| MiniMax-M2.5 | 0.30 | 1.20 | - | +| Kimi-K2.5 | 0.23 | 3.00 | - | +| GLM-5 | 0.30 | 2.55 | - | +| GPT-5.4 | 2.50 | 15.00 | 10,000 | +| GPT-5.2 | 1.75 | 14.00 | 10,000 | +| GPT-5.4-mini | 0.75 | 4.50 | 10,000 | +| GPT-5-mini | 0.25 | 2.00 | 10,000 | +| GPT-5.4-nano | 0.20 | 1.20 | 10,000 | +| GPT-5-nano | 0.05 | 0.40 | - | | Claude Opus 4.6 | 5.00 | 25.00 | 10,000 | | Claude Opus 4.5 | 5.00 | 25.00 | 10,000 | | Claude Sonnet 4.6 | 3.00 | 15.00 | 10,000 | | Claude Sonnet 4.5 | 3.00 | 15.00 | 10,000 | | Claude Haiku 4.5 | 1.00 | 5.00 | 10,000 | -| Gemini 3.1 Pro | 2.00 | 12.00 | 14,000 | -| Gemini 3 Flash | 0.50 | 3.00 | 14,000 | +| Gemini 3.1 pro | 2.00 | 12.00 | 14,000 | +| Gemini 3 flash | 0.50 | 3.00 | 14,000 | -> **计算示例：** 若使用输入价格 1.25、输出价格 10.00 的模型，提问消耗 10 个输入 Token，回复消耗 50 个输出 Token，则总消耗为 **512.5 积分**（10 × 1.25 + 50 × 10）。可在聊天界面右下角悬停模型名称查看具体消耗。 +例如，如果你使用 GPT-5.2 提问（10 个输入 token），AI 返回回答（50 个输出 token），那么整次对话共消耗 717.5 Credits（计算方式：10 × 1.75 + 50 × 14）。你可以将鼠标悬停在右下角的模型名称上，查看具体的 Credits 消耗情况。 ---- +## 使用信息 -## 使用数据 +你可以通过左侧导航栏中的 **Usage** 页面查看所有消费的详细数据，确保每一笔支出都清晰透明、可追踪。 -可在左侧导航栏进入 **使用情况** 页面查看详细数据： +**使用总览：** 页面顶部会显示你的 Credits 余额以及当月总消耗，帮助你快速了解当前账户状态。 -- **使用概览：** 当前积分余额与本月总消耗 -- **月度使用图：** 展示过去一年的使用趋势 -- **使用明细：** 每条记录对应一次 AI 交互，包括时间、模型、Token 用量、积分消耗和响应时间 +**月度使用图表：** 通过直观的柱状图，你可以快速查看过去一年中的使用波动情况，便于进行成本分析和预算规划。 ---- +**使用明细：** 在 **Usage detail** 表格中，每一条记录都精确对应一次 AI 交互。表格会列出创建时间、类型、所用模型、token 使用量、消耗 Credits 以及响应时间，为你提供最细粒度的消费数据。 ## 充值 -Bank of AI 采用预付费模式，基于区块链实现安全便捷的充值体验。 +平台采用预付费模式，你需要先为账户充值以获取 Credits。借助 TRON 网络的优势，平台提供了安全且便捷的充值体验。 -- **充值流程：** 在 **充值** 页面，通过已连接的钱包完成支付确认 -- **支持代币：** 支持多链主流代币（包括 TRON、BNB Chain 等） -- **到账时间：** 区块链确认后自动到账，通常为几分钟内 +**充值流程：** 在 **Top up** 页面中，平台会引导你使用已连接的 TronLink 钱包进行支付。你无需手动输入地址，只需在钱包弹窗中确认交易即可完成充值。 ---- +**支持的代币类型：** 平台支持 TRON 生态中的多种主流代币，包括 TRX、USDT、USDD 和 USD1。 -## 账单与记录 +**到账时间：** 一旦转账交易在 TRON 链上确认，系统会自动将等值 Credits 发放到你的账户。通常，这个过程会在几分钟内完成。 -可在 **充值** 页面中的 **历史记录** 查看完整充值信息： +## 账单与发票 -- **充值记录：** 包括时间、类型、交易哈希、代币信息 -- **透明可查：** 可点击交易哈希，在区块链浏览器（如 TRONSCAN、BscScan）中查看详情 +你可以在 **Top up** 页面的 **History** 标签下查看完整的充值记录。 + +**充值记录：** 发票列表会清晰展示每一笔充值的创建时间、类型、交易哈希、代币种类等信息。 + +**交易哈希查询：** 你可以点击交易哈希，查看并核验交易详情，确保整个过程透明可查。 From 734d634feca8dd58f897557059723eb5b90c26d0 Mon Sep 17 00:00:00 2001 From: ai-bankofai Date: Mon, 6 Apr 2026 17:55:18 +0800 Subject: [PATCH 38/46] Rename chatgpt-5-nano.md to gpt-5-nano.md --- .../llmservice/models/{chatgpt-5-nano.md => gpt-5-nano.md} | 0 1 file changed, 0 insertions(+), 0 deletions(-) rename i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/{chatgpt-5-nano.md => gpt-5-nano.md} (100%) diff --git a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/chatgpt-5-nano.md b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gpt-5-nano.md similarity index 100% rename from i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/chatgpt-5-nano.md rename to i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gpt-5-nano.md From 0d7e96157eea1f2ea7f0b404effd330fbba3c149 Mon Sep 17 00:00:00 2001 From: jerryji-prog Date: Mon, 6 Apr 2026 18:05:45 +0800 Subject: [PATCH 39/46] config --- docs/llmservice/models/gpt-5-2.md | 2 +- docs/llmservice/models/gpt-5-mini.md | 2 +- docs/llmservice/models/gpt-5-nano.md | 2 +- .../current/llmservice/models/gpt-5-2.md | 2 +- .../current/llmservice/models/gpt-5-4-nano.md | 1 + .../current/llmservice/models/gpt-5-mini.md | 2 +- .../current/llmservice/models/gpt-5-nano.md | 2 +- .../docusaurus-plugin-content-docs/current/sidebars.js | 10 +++++++--- sidebars.js | 10 +++++++--- 9 files changed, 21 insertions(+), 12 deletions(-) diff --git a/docs/llmservice/models/gpt-5-2.md b/docs/llmservice/models/gpt-5-2.md index 7400a7c4..d6277d4c 100644 --- a/docs/llmservice/models/gpt-5-2.md +++ b/docs/llmservice/models/gpt-5-2.md @@ -1,4 +1,4 @@ -# GPT-5.2 + ## Overview GPT-5.2 is the latest generation of the flagship large language model developed by OpenAI. Building upon the powerful capabilities of the 5.1 version, it further optimizes the speed of multimodal processing and the execution efficiency of complex tasks, making it the ideal choice for professional users seeking ultimate performance and efficiency. diff --git a/docs/llmservice/models/gpt-5-mini.md b/docs/llmservice/models/gpt-5-mini.md index f8abb6f5..c4bb27cf 100644 --- a/docs/llmservice/models/gpt-5-mini.md +++ b/docs/llmservice/models/gpt-5-mini.md @@ -1,4 +1,4 @@ -# GPT-5-mini + ## Overview ChatGPT-5-mini is an efficient and economical lightweight language model. It is optimized for fast, smooth daily conversations and general tasks, making it a premier choice for cost-effective AI interaction within the Bank of AI ecosystem. diff --git a/docs/llmservice/models/gpt-5-nano.md b/docs/llmservice/models/gpt-5-nano.md index 0a4c1b2c..92c26596 100644 --- a/docs/llmservice/models/gpt-5-nano.md +++ b/docs/llmservice/models/gpt-5-nano.md @@ -1,4 +1,4 @@ -# GPT-5-nano + ## Overview ChatGPT-5-nano is an advanced language model that strikes an excellent balance between performance, speed, and cost. It is designed to provide near-professional AI capabilities at a moderate cost within the Bank of AI ecosystem. diff --git a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gpt-5-2.md b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gpt-5-2.md index 4df6dc69..63030b3f 100644 --- a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gpt-5-2.md +++ b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gpt-5-2.md @@ -1,4 +1,4 @@ -# GPT-5.2 + ## 概述 diff --git a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gpt-5-4-nano.md b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gpt-5-4-nano.md index 6b89b31d..30d611a7 100644 --- a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gpt-5-4-nano.md +++ b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gpt-5-4-nano.md @@ -1,3 +1,4 @@ + ## 概述 GPT-5.4 Nano 是 GPT-5.4 系列中体量最小、成本最低的版本，于 2026 年 3 月 17 日发布，面向对速度敏感、对成本敏感的使用场景。其价格仅为每百万 tokens 输入 $0.20、输出 $1.25，同时具备推理能力，Intelligence Index 达到 44.4，远高于同价位模型 20 的中位数——非常适合大规模分类、数据提取、排序以及子代理任务。 diff --git a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gpt-5-mini.md b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gpt-5-mini.md index e9ff4295..83483a80 100644 --- a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gpt-5-mini.md +++ b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gpt-5-mini.md @@ -1,4 +1,4 @@ -# GPT-5-mini + ## 概述 diff --git a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gpt-5-nano.md b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gpt-5-nano.md index c96cb649..0b47922e 100644 --- a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gpt-5-nano.md +++ b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gpt-5-nano.md @@ -1,4 +1,4 @@ -# GPT-5-nano + ## 概述 diff --git a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/sidebars.js b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/sidebars.js index e8626e73..2d6eeb48 100644 --- a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/sidebars.js +++ b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/sidebars.js @@ -188,9 +188,12 @@ const sidebars = { label: '模型', collapsed: true, items: [ - 'llmservice/models/chatgpt-5-2', - 'llmservice/models/chatgpt-5-mini', - 'llmservice/models/chatgpt-5-nano', + 'llmservice/models/gpt-5-mini', + 'llmservice/models/gpt-5-nano', + 'llmservice/models/gpt-5-2', + 'llmservice/models/gpt-5-4', + 'llmservice/models/gpt-5-4-mini', + 'llmservice/models/gpt-5-4-nano', 'llmservice/models/claude-haiku-4-5', 'llmservice/models/claude-opus-4-5', 'llmservice/models/claude-opus-4-6', @@ -204,6 +207,7 @@ const sidebars = { 'llmservice/models/minimax-m2.5', ], }, + { type: 'doc', id: 'llmservice/memory', label: '记忆服务' }, { type: 'category', label: 'OpenClaw', diff --git a/sidebars.js b/sidebars.js index e16b585a..90ce5dce 100644 --- a/sidebars.js +++ b/sidebars.js @@ -185,9 +185,12 @@ const sidebars = { label: 'Models', collapsed: true, items: [ - 'llmservice/models/chatgpt-5-2', - 'llmservice/models/chatgpt-5-mini', - 'llmservice/models/chatgpt-5-nano', + 'llmservice/models/gpt-5-mini', + 'llmservice/models/gpt-5-nano', + 'llmservice/models/gpt-5-2', + 'llmservice/models/gpt-5-4', + 'llmservice/models/gpt-5-4-mini', + 'llmservice/models/gpt-5-4-nano', 'llmservice/models/claude-haiku-4-5', 'llmservice/models/claude-opus-4-5', 'llmservice/models/claude-opus-4-6', @@ -201,6 +204,7 @@ const sidebars = { 'llmservice/models/minimax-m2.5', ], }, + { type: 'doc', id: 'llmservice/memory', label: 'Memory' }, { type: 'category', label: 'OpenClaw', From a6e808582eab41491cc423cadd151c37478bd6be Mon Sep 17 00:00:00 2001 From: ai-bankofai Date: Mon, 6 Apr 2026 22:27:11 +0800 Subject: [PATCH 40/46] Update gpt-5-mini.md --- docs/llmservice/models/gpt-5-mini.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/docs/llmservice/models/gpt-5-mini.md b/docs/llmservice/models/gpt-5-mini.md index c4bb27cf..d374a91e 100644 --- a/docs/llmservice/models/gpt-5-mini.md +++ b/docs/llmservice/models/gpt-5-mini.md @@ -1,7 +1,7 @@ ## Overview -ChatGPT-5-mini is an efficient and economical lightweight language model. It is optimized for fast, smooth daily conversations and general tasks, making it a premier choice for cost-effective AI interaction within the Bank of AI ecosystem. +GPT-5-mini is an efficient and economical lightweight language model. It is optimized for fast, smooth daily conversations and general tasks, making it a premier choice for cost-effective AI interaction within the Bank of AI ecosystem. ## Key Features * **Extremely Fast Response:** Deeply optimized for low response latency, providing a near real-time conversation experience. @@ -27,4 +27,4 @@ ChatGPT-5-mini is an efficient and economical lightweight language model. It is | Model | Input (Credits/Token) | Output (Credits/Token) | | :--- | :--- | :--- | -| **ChatGPT-5-mini** | 0.25 | 2.00 | +| **GPT-5-mini** | 0.25 | 2.00 | From 82e4b885897dd98b523b262c67162af346301c74 Mon Sep 17 00:00:00 2001 From: ai-bankofai Date: Mon, 6 Apr 2026 22:29:50 +0800 Subject: [PATCH 41/46] Update gpt-5-nano.md --- docs/llmservice/models/gpt-5-nano.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/llmservice/models/gpt-5-nano.md b/docs/llmservice/models/gpt-5-nano.md index 92c26596..bd436f5f 100644 --- a/docs/llmservice/models/gpt-5-nano.md +++ b/docs/llmservice/models/gpt-5-nano.md @@ -1,7 +1,7 @@ ## Overview -ChatGPT-5-nano is an advanced language model that strikes an excellent balance between performance, speed, and cost. It is designed to provide near-professional AI capabilities at a moderate cost within the Bank of AI ecosystem. +GPT-5-nano is an advanced language model that strikes an excellent balance between performance, speed, and cost. It is designed to provide near-professional AI capabilities at a moderate cost within the Bank of AI ecosystem. ## Key Features * **Enhanced Reasoning Ability:** Nano shows significant improvements in logical reasoning, code generation, and multilingual processing compared to lighter models. From a2b2d5ff5161ea574dd876fd91914b1b7e4ddc78 Mon Sep 17 00:00:00 2001 From: ai-bankofai Date: Mon, 6 Apr 2026 22:38:17 +0800 Subject: [PATCH 42/46] Update pricing-and-usage.md --- docs/llmservice/pricing-and-usage.md | 50 ++++++++++++++-------------- 1 file changed, 25 insertions(+), 25 deletions(-) diff --git a/docs/llmservice/pricing-and-usage.md b/docs/llmservice/pricing-and-usage.md index a60f92c3..299101ab 100644 --- a/docs/llmservice/pricing-and-usage.md +++ b/docs/llmservice/pricing-and-usage.md @@ -6,28 +6,28 @@ The platform utilizes a unified credit system to measure and settle usage for al **Token Consumption Details:** In the AI response details, the platform displays the breakdown of token consumption, helping you understand the specific sources of credit usage and optimize future usage patterns. -**Pricing for Different Models:** Pricing varies due to differences in capabilities and computational costs among AI models. Generally, more capable models consume more credits. The web search feature incurs an additional fee and is charged on a pay-per-use basis. Some models do not support web search marked as "-". For specific model pricing, please check here： - -| Model | Input (Credits/Token) | Output (Credits/Token) | Web Search(Credits/Use) | -| :---------------- | --------------------: | ---------------------: | ----------------------: | -| MiniMax-M2.5 | 0.30 | 1.20 | - | -| Kimi-K2.5 | 0.23 | 3.00 | - | -| GLM-5 | 0.30 | 2.55 | - | -| GPT-5.4 | 2.50 | 15.00 | 10,000 | -| GPT-5.2 | 1.75 | 14.00 | 10,000 | -| GPT-5.4-mini | 0.75 | 4.50 | 10,000 | -| GPT-5-mini | 0.25 | 2.00 | 10,000 | -| GPT-5.4-nano | 0.20 | 1.20 | 10,000 | -| GPT-5-nano | 0.05 | 0.40 | - | -| Claude Opus 4.6 | 5.00 | 25.00 | 10,000 | -| Claude Opus 4.5 | 5.00 | 25.00 | 10,000 | -| Claude Sonnet 4.6 | 3.00 | 15.00 | 10,000 | -| Claude Sonnet 4.5 | 3.00 | 15.00 | 10,000 | -| Claude Haiku 4.5 | 1.00 | 5.00 | 10,000 | -| Gemini 3.1 pro | 2.00 | 12.00 | 14,000 | -| Gemini 3 flash | 0.50 | 3.00 | 14,000 | - -For example, if you use GPT-5.2 to ask a question (10 input tokens) and the AI responds with an answer (50 output tokens), the entire dialogue consumes 512.5 credits (calculated as: 10 × 1.25 + 50 × 10). You can check the specific credit usage by hovering over the model name in the bottom right corner. +**Pricing for Different Models:** Pricing varies due to differences in capabilities and computational costs among AI models. Generally, more capable models consume more credits. The web search feature incurs an additional fee and is charged on a pay-per-use basis. Some models do not support web search and are marked with "-". For specific model pricing, please check here: + +| Model | Input (Credits/Token) | Output (Credits/Token) | Web Search (Credits/Use) | +| :---------------- | --------------------: | ---------------------: | -----------------------: | +| MiniMax-M2.5 | 0.30 | 1.20 | - | +| Kimi-K2.5 | 0.23 | 3.00 | - | +| GLM-5 | 0.30 | 2.55 | - | +| GPT-5.4 | 2.50 | 15.00 | 10,000 | +| GPT-5.2 | 1.75 | 14.00 | 10,000 | +| GPT-5.4-mini | 0.75 | 4.50 | 10,000 | +| GPT-5-mini | 0.25 | 2.00 | 10,000 | +| GPT-5.4-nano | 0.20 | 1.20 | 10,000 | +| GPT-5-nano | 0.05 | 0.40 | - | +| Claude Opus 4.6 | 5.00 | 25.00 | 10,000 | +| Claude Opus 4.5 | 5.00 | 25.00 | 10,000 | +| Claude Sonnet 4.6 | 3.00 | 15.00 | 10,000 | +| Claude Sonnet 4.5 | 3.00 | 15.00 | 10,000 | +| Claude Haiku 4.5 | 1.00 | 5.00 | 10,000 | +| Gemini 3.1 Pro | 2.00 | 12.00 | 14,000 | +| Gemini 3 Flash | 0.50 | 3.00 | 14,000 | + +For example, if you use GPT-5.2 to ask a question (10 input tokens) and the AI responds with an answer (50 output tokens), the entire dialogue consumes 717.5 credits (calculated as: 10 × 1.75 + 50 × 14). You can check the specific credit usage by hovering over the model name in the bottom right corner. ## Usage Information @@ -37,11 +37,11 @@ You can view detailed data regarding all your consumption on the **Usage** page **Monthly Usage Chart:** Through an intuitive bar chart, you can quickly track usage fluctuations over the past year, facilitating cost analysis and budget planning. -**Usage detail:** In the **Usage detail** table, every record corresponds precisely to a single AI interaction. The table lists the creation time, type, model used, token usage, credits consumed, and response time, providing you with the most granular consumption data. +**Usage Detail:** In the **Usage Detail** table, every record corresponds precisely to a single AI interaction. The table lists the creation time, type, model used, token usage, credits consumed, and response time, providing you with the most granular consumption data. ## Deposit -The platform operates on a pre-paid model; you must top up your account to obtain credits. Leveraging the advantages of the TRON network, the platform offers a secure and convenient deposit experience. +The platform operates on a pre-paid model, so you must top up your account to obtain credits. Leveraging the advantages of the TRON network, the platform offers a secure and convenient deposit experience. **Deposit Process:** On the **Top up** page, the platform will guide you to pay using your connected TronLink wallet. You do not need to manually enter addresses; simply confirm the transaction in the wallet pop-up window to complete it. @@ -55,4 +55,4 @@ You can view your complete deposit history under the **History** tab on the **To **Deposit Records:** The invoice list clearly displays the creation time, type, transaction hash, token, and other information for each deposit. -**Transaction Hash Query:** You can click the transaction hash and verify the transaction details to ensure transparency. +**Transaction Hash Query:** You can click the transaction hash to verify the transaction details and ensure transparency. From 2a6a7fd8565fdac35098c27585d1e5b362cc0d11 Mon Sep 17 00:00:00 2001 From: ai-bankofai Date: Mon, 6 Apr 2026 22:40:00 +0800 Subject: [PATCH 43/46] Update pricing-and-usage.md --- .../current/llmservice/pricing-and-usage.md | 30 +++++++++---------- 1 file changed, 15 insertions(+), 15 deletions(-) diff --git a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/pricing-and-usage.md b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/pricing-and-usage.md index 847fb7e3..4b8672b6 100644 --- a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/pricing-and-usage.md +++ b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/pricing-and-usage.md @@ -1,12 +1,12 @@ ## Credits 与定价 -平台采用统一的 Credits 积分系统来计量和结算所有 AI 服务的使用量。 +平台采用统一的 Credits 积分系统来衡量并结算所有 AI 服务的使用量。 -**Credits 计算规则：** 每次与 AI 交互所消耗的 token，会根据不同模型的定价标准换算为相应的 Credits，并从你的账户余额中扣除。 +**Credits 计算规则：** 每次与 AI 交互所消耗的 token 数量，会根据不同模型的定价标准换算为相应的 Credits，并从你的账户余额中扣除。 -**Token 消耗明细：** 在 AI 响应详情中，平台会展示 token 消耗的拆分明细，帮助你了解 Credits 的具体消耗来源，并优化后续使用方式。 +**Token 消耗明细：** 在 AI 响应详情中，平台会展示 token 消耗的明细拆分，帮助你了解 Credits 消耗的具体来源，并优化后续使用方式。 -**不同模型的定价：** 由于不同 AI 模型在能力和计算成本上存在差异，其定价也有所不同。通常，能力越强的模型消耗的 Credits 越多。网页搜索功能会产生额外费用，并按次收费。部分模型不支持网页搜索，以 `-` 标记。具体模型定价如下： +**不同模型的定价：** 不同 AI 模型由于能力和计算成本不同，定价也有所差异。通常，能力越强的模型消耗的 Credits 越多。网页搜索功能会产生额外费用，并按次收费。部分模型不支持网页搜索，这些模型以 `"-"` 标记。具体模型定价请查看下表： | 模型 | 输入（Credits/Token） | 输出（Credits/Token） | 网页搜索（Credits/次） | | :--- | --------------------: | --------------------: | ---------------------: | @@ -24,24 +24,24 @@ | Claude Sonnet 4.6 | 3.00 | 15.00 | 10,000 | | Claude Sonnet 4.5 | 3.00 | 15.00 | 10,000 | | Claude Haiku 4.5 | 1.00 | 5.00 | 10,000 | -| Gemini 3.1 pro | 2.00 | 12.00 | 14,000 | -| Gemini 3 flash | 0.50 | 3.00 | 14,000 | +| Gemini 3.1 Pro | 2.00 | 12.00 | 14,000 | +| Gemini 3 Flash | 0.50 | 3.00 | 14,000 | -例如，如果你使用 GPT-5.2 提问（10 个输入 token），AI 返回回答（50 个输出 token），那么整次对话共消耗 717.5 Credits（计算方式：10 × 1.75 + 50 × 14）。你可以将鼠标悬停在右下角的模型名称上，查看具体的 Credits 消耗情况。 +例如，如果你使用 GPT-5.2 提出一个问题（10 个输入 token），AI 返回一个回答（50 个输出 token），那么整段对话共消耗 717.5 Credits（计算方式：10 × 1.75 + 50 × 14）。你可以将鼠标悬停在右下角的模型名称上，查看具体的 Credits 消耗情况。 ## 使用信息 -你可以通过左侧导航栏中的 **Usage** 页面查看所有消费的详细数据，确保每一笔支出都清晰透明、可追踪。 +你可以通过左侧导航栏中的 **Usage** 页面查看所有消费的详细数据，确保每一笔支出都透明且可追踪。 -**使用总览：** 页面顶部会显示你的 Credits 余额以及当月总消耗，帮助你快速了解当前账户状态。 +**使用概览：** 页面顶部会显示你的 Credits 余额以及当月总消耗，让你一目了然地了解当前账户状态。 -**月度使用图表：** 通过直观的柱状图，你可以快速查看过去一年中的使用波动情况，便于进行成本分析和预算规划。 +**月度使用图表：** 通过直观的柱状图，你可以快速追踪过去一年中的使用波动情况，从而便于进行成本分析和预算规划。 -**使用明细：** 在 **Usage detail** 表格中，每一条记录都精确对应一次 AI 交互。表格会列出创建时间、类型、所用模型、token 使用量、消耗 Credits 以及响应时间，为你提供最细粒度的消费数据。 +**使用明细：** 在 **Usage Detail** 表格中，每一条记录都精确对应一次 AI 交互。表格会列出创建时间、类型、所用模型、token 使用量、消耗的 Credits 以及响应时间，为你提供最细粒度的消费数据。 ## 充值 -平台采用预付费模式，你需要先为账户充值以获取 Credits。借助 TRON 网络的优势，平台提供了安全且便捷的充值体验。 +平台采用预付费模式，因此你需要先为账户充值以获取 Credits。借助 TRON 网络的优势，平台提供了安全且便捷的充值体验。 **充值流程：** 在 **Top up** 页面中，平台会引导你使用已连接的 TronLink 钱包进行支付。你无需手动输入地址，只需在钱包弹窗中确认交易即可完成充值。 @@ -51,8 +51,8 @@ ## 账单与发票 -你可以在 **Top up** 页面的 **History** 标签下查看完整的充值记录。 +你可以在 **Top up** 页面的 **History** 标签下查看完整的充值历史记录。 -**充值记录：** 发票列表会清晰展示每一笔充值的创建时间、类型、交易哈希、代币种类等信息。 +**充值记录：** 发票列表会清晰展示每一笔充值的创建时间、类型、交易哈希、代币种类以及其他信息。 -**交易哈希查询：** 你可以点击交易哈希，查看并核验交易详情，确保整个过程透明可查。 +**交易哈希查询：** 你可以点击交易哈希来核验交易详情，确保整个过程透明可查。 From 00441277e8603f15a6e40722c76927afcef81b77 Mon Sep 17 00:00:00 2001 From: ai-bankofai Date: Tue, 7 Apr 2026 22:52:55 +0800 Subject: [PATCH 44/46] Create gpt-5-4-pro.md --- docs/llmservice/models/gpt-5-4-pro.md | 44 +++++++++++++++++++++++++++ 1 file changed, 44 insertions(+) create mode 100644 docs/llmservice/models/gpt-5-4-pro.md diff --git a/docs/llmservice/models/gpt-5-4-pro.md b/docs/llmservice/models/gpt-5-4-pro.md new file mode 100644 index 00000000..0818987f --- /dev/null +++ b/docs/llmservice/models/gpt-5-4-pro.md @@ -0,0 +1,44 @@ +## Overview + +GPT-5.4 Pro is the highest-performance variant in the GPT-5.4 family, allocating more compute for deeper reasoning to produce smarter and more precise answers on complex, high-stakes tasks. Available exclusively via the Responses API, some requests may take several minutes to complete, making it ideal for accuracy-critical professional use cases. + +## Key Features + +- **Enhanced Deep Reasoning**: Allocates significantly more reasoning compute, outperforming the standard model on math, science, and complex coding problems. +- **1M+ Native Context**: Natively supports 1,050,000 token context (922K input + 128K output) without additional configuration. +- **Unified Capability Inheritance**: Inherits all GPT-5.4 capabilities including Computer Use, Tool Search, and configurable reasoning effort. +- **Responses API Exclusive**: Available only via the Responses API, specifically optimized for complex tasks requiring deep thinking. + +## Best Use Cases + +- **High-Stakes Decision Support**: Ideal for financial analysis, legal reasoning, medical diagnostic assistance, and other professional domains requiring extreme accuracy. +- **Complex Research & Analysis**: The 1M+ context window and deep reasoning make it perfect for cross-document research and systematic analysis. +- **Advanced Coding Challenges**: Excels on frontier coding benchmarks, suitable for large-scale code refactoring, architecture design, and complex bug diagnosis. +- **Enterprise AI Agents**: Powers autonomous agent systems requiring the highest reasoning quality, suitable for critical business process automation. + +## Capabilities and Limitations + +| Capability | Detailed Description | +| :--------------------- | :--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | +| **Reasoning Ability** | Strongest reasoning in the GPT-5.4 family; ranks #1 out of 104 models (overall score 92/100). SWE-bench Pro 57.7%, OSWorld 75% (surpassing 72.4% human expert baseline), GDPval 83%. Configurable reasoning effort: medium, high, xhigh. | +| **Creative Ability** | Inherits GPT-5.4's creative capabilities with 128K max output; deeper reasoning improves structured creative tasks like technical writing and system design documents. | +| **Multimodal Ability** | Supports text and image input with text output; image understanding and analysis on par with GPT-5.4 standard. | +| **Tool Use** | Agentic tool use score 88.9 (#1 of 104 models). Supports Computer Use, Tool Search, and multi-step workflow orchestration. | +| **Response Speed** | Slower — some complex requests may take several minutes, not suitable for low-latency scenarios. | +| **Context Window** | 1,050,000 tokens (922K input + 128K output), natively supported without additional configuration. | +| **Max Output** | 128,000 tokens | +| **Knowledge Cutoff** | August 31, 2025 | + +## Credits and Pricing + +| Model | Input (Credits/Token) | Output (Credits/Token) | +| :---------- | --------------------: | ---------------------: | +| GPT-5.4 Pro | 30.00 | 180.00 | + + + +## Limitations + +- **High latency**: Complex requests may take several minutes; not suitable for real-time or low-latency applications. +- **Cost**: It is one of the most expensive API models available. +- **No audio/video input**: Multimodal support is limited to text and image input. From 5328cdaae83b93595d07894174b1b7b313bb8b48 Mon Sep 17 00:00:00 2001 From: ai-bankofai Date: Tue, 7 Apr 2026 22:55:36 +0800 Subject: [PATCH 45/46] Create gpt-5-4-pro.md --- .../current/llmservice/models/gpt-5-4-pro.md | 42 +++++++++++++++++++ 1 file changed, 42 insertions(+) create mode 100644 i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gpt-5-4-pro.md diff --git a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gpt-5-4-pro.md b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gpt-5-4-pro.md new file mode 100644 index 00000000..3a737706 --- /dev/null +++ b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gpt-5-4-pro.md @@ -0,0 +1,42 @@ +## 概述 + +GPT-5.4 Pro 是 GPT-5.4 系列中性能最高的版本，分配了更多计算资源用于更深层次的推理，从而在复杂、高风险任务中提供更智能、更精确的回答。该模型仅通过 Responses API 提供，部分请求可能需要数分钟才能完成，因此非常适合对准确性要求极高的专业使用场景。 + +## 核心特性 + +- **增强的深度推理**：分配了显著更多的推理计算资源，在数学、科学和复杂编程问题上优于标准模型。 +- **原生支持 1M+ 上下文**：原生支持 1,050,000 token 的上下文窗口（922K 输入 + 128K 输出），无需额外配置。 +- **统一能力继承**：继承 GPT-5.4 的全部能力，包括 Computer Use、Tool Search 和可配置的推理强度。 +- **仅限 Responses API**：仅可通过 Responses API 使用，专门针对需要深度思考的复杂任务进行了优化。 + +## 最佳使用场景 + +- **高风险决策支持**：适用于金融分析、法律推理、医疗诊断辅助以及其他对准确性要求极高的专业领域。 +- **复杂研究与分析**：1M+ 的上下文窗口和深度推理能力使其非常适合跨文档研究和系统化分析。 +- **高级编程挑战**：在前沿编程基准测试中表现出色，适用于大规模代码重构、架构设计和复杂 Bug 诊断。 +- **企业级 AI Agent**：可驱动需要最高推理质量的自主 Agent 系统，适用于关键业务流程自动化。 + +## 能力与限制 + +| 能力 | 详细描述 | +| :--- | :--- | +| **推理能力** | GPT-5.4 系列中最强的推理能力；在 104 个模型中排名第 1（综合得分 92/100）。SWE-bench Pro 57.7%，OSWorld 75%（超过 72.4% 的人类专家基线），GDPval 83%。支持可配置推理强度：medium、high、xhigh。 | +| **创意能力** | 继承 GPT-5.4 的创意能力，最大输出为 128K；更深层的推理进一步提升了技术写作和系统设计文档等结构化创意任务的表现。 | +| **多模态能力** | 支持文本和图像输入，以及文本输出；图像理解与分析能力与 GPT-5.4 标准版相当。 | +| **工具使用** | Agent 工具使用得分 88.9（104 个模型中排名第 1）。支持 Computer Use、Tool Search 以及多步骤工作流编排。 | +| **响应速度** | 较慢——部分复杂请求可能需要数分钟，不适合低延迟场景。 | +| **上下文窗口** | 1,050,000 tokens（922K 输入 + 128K 输出），原生支持，无需额外配置。 | +| **最大输出** | 128,000 tokens | +| **知识截止日期** | 2025 年 8 月 31 日 | + +## Credits and Pricing + +| 模型 | 输入（Credits/Token） | 输出（Credits/Token） | +| :--- | --------------------: | --------------------: | +| GPT-5.4 Pro | 30.00 | 180.00 | + +## 限制 + +- **高延迟**：复杂请求可能需要数分钟，不适合实时或低延迟应用场景。 +- **成本**：它是目前最昂贵的 API 模型之一。 +- **不支持音频/视频输入**：多模态支持仅限文本和图像输入。 From c62adf668801a8cde5e98e5b5d135415d813fae6 Mon Sep 17 00:00:00 2001 From: jerryji-prog Date: Wed, 8 Apr 2026 11:11:16 +0800 Subject: [PATCH 46/46] add sidebar --- .../zh-Hans/docusaurus-plugin-content-docs/current/sidebars.js | 3 ++- package.json | 2 +- sidebars.js | 3 ++- 3 files changed, 5 insertions(+), 3 deletions(-) diff --git a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/sidebars.js b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/sidebars.js index 2d6eeb48..21574ba6 100644 --- a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/sidebars.js +++ b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/sidebars.js @@ -193,7 +193,8 @@ const sidebars = { 'llmservice/models/gpt-5-2', 'llmservice/models/gpt-5-4', 'llmservice/models/gpt-5-4-mini', - 'llmservice/models/gpt-5-4-nano', + 'llmservice/models/gpt-5-4-nano', + 'llmservice/models/gpt-5-4-pro', 'llmservice/models/claude-haiku-4-5', 'llmservice/models/claude-opus-4-5', 'llmservice/models/claude-opus-4-6', diff --git a/package.json b/package.json index a26951ad..1ce4cf3e 100644 --- a/package.json +++ b/package.json @@ -1,6 +1,6 @@ { "name": "@x402-tron/docs", - "version": "1.2.6", + "version": "1.2.7", "description": "x402-tron documentation", "license": "MIT", "scripts": { diff --git a/sidebars.js b/sidebars.js index 90ce5dce..986d9f27 100644 --- a/sidebars.js +++ b/sidebars.js @@ -190,7 +190,8 @@ const sidebars = { 'llmservice/models/gpt-5-2', 'llmservice/models/gpt-5-4', 'llmservice/models/gpt-5-4-mini', - 'llmservice/models/gpt-5-4-nano', + 'llmservice/models/gpt-5-4-nano', + 'llmservice/models/gpt-5-4-pro', 'llmservice/models/claude-haiku-4-5', 'llmservice/models/claude-opus-4-5', 'llmservice/models/claude-opus-4-6',