diff --git a/docs/llmservice/models/claude-fable-5.md b/docs/llmservice/models/claude-fable-5.md
new file mode 100644
index 00000000..09e98d52
--- /dev/null
+++ b/docs/llmservice/models/claude-fable-5.md
@@ -0,0 +1,53 @@
+# Claude Fable 5
+
+## Overview
+
+Claude Fable 5 is a high-capability Anthropic model available on B.AI for advanced reasoning, coding, long-context analysis, and agentic workflows. It is designed for complex tasks that require sustained context, tool-assisted execution, and high-quality structured outputs. Specific capabilities, context limits, tool support, and availability may vary by B.AI model catalog and platform configuration.
+
+## Key Features
+
+* **Advanced Reasoning**: Suitable for complex analytical, technical, and professional knowledge tasks.
+* **Software Engineering Workflows**: Designed for coding assistance, debugging, refactoring, code review, and multi-step implementation planning.
+* **Long-Context Tasks**: Supports extended analysis across large codebases, long documents, and multi-turn work sessions when enabled by the platform configuration.
+* **Agentic and Tool-Assisted Workflows**: Suitable for workflows that rely on tool use, function calling, code execution, MCP, or compatible agent environments.
+* **Multimodal Understanding**: Supports text and image input for document, screenshot, chart, and diagram understanding where available.
+
+## Best Use Cases
+
+* **Complex Software Engineering**: Large feature work, repository-scale refactors, migration planning, bug investigation, and code review.
+* **Extended Agentic Workflows**: Multi-step tasks that require planning, tool use, verification, and sustained context over longer sessions.
+* **Research and Knowledge Work**: Analysis and synthesis across technical documents, legal or financial materials, and structured research sources.
+* **Visual Document Analysis**: Understanding screenshots, diagrams, charts, PDFs, and other image-based materials when supported by the workflow.
+
+## Capabilities and Limitations
+
+| Capability         | Description                                                                                         |
+| :----------------- | :-------------------------------------------------------------------------------------------------- |
+| **Reasoning**      | Advanced reasoning for complex professional and technical tasks                                      |
+| **Coding**         | Strong coding, debugging, refactoring, and code review capabilities                                  |
+| **Agentic**        | Suitable for long-running tool workflows and multi-step agent tasks                                  |
+| **Computer Use**   | Can support browser and desktop interaction through compatible tools and environments                |
+| **Multimodal**     | Text and image input; text output                                                                   |
+| **Context Window** | Up to 1,000,000 tokens, subject to platform configuration                                            |
+| **Max Output**     | Up to 128,000 tokens, subject to platform configuration                                              |
+| **Tool Use**       | Function calling, code execution, MCP support, adaptive thinking, and compatible agent workflows     |
+| **Multilingual**   | Strong multilingual performance across major world languages                                         |
+
+### Known Limitations
+
+* Specific capability availability may depend on the B.AI integration, Anthropic platform support, plan settings, and rollout status.
+* Web access, code execution, computer use, and external actions require compatible tools or integrations.
+* Image input is supported, but native audio or video input is not listed for this model.
+* Public evaluations, third-party comparisons, policy behavior, and implementation details may change over time, so they are not treated as fixed guarantees in this documentation.
+
+## Credits Usage
+
+| Model | Input (Credits/Token) | Cache Write (Credits/Token) | Cache Read (Credits/Token) | Output (Credits/Token) | Web Search (Credits/Use) | Billing Notes |
+| :--- | --------------------: | --------------------------: | -------------------------: | ---------------------: | -----------------------: | :--- |
+| **Claude Fable 5** | `10.00` | `12.50` | `1.00` | `50.00` | `10,000` | - |
+
+:::info Pricing note
+Prices shown in the documentation are B.AI standard reference prices for base billing purposes. B.AI may provide lower actual usage costs through top-up bonuses and account benefits. Specific prices, bonus Credits, and account benefits are subject to the platform display and final billing records.
+:::
+
+* **Prompt caching**: Cache writes are charged at 1.25x base input price for the 5-minute TTL option, or 2x base input price for the 1-hour TTL option. Cache reads are charged at 0.1x base input price. Prompt caching requires a minimum of 1,024 tokens.
diff --git a/docs/llmservice/models/claude-haiku-4-5.md b/docs/llmservice/models/claude-haiku-4-5.md
index cd4d1b91..cd7a2e5b 100644
--- a/docs/llmservice/models/claude-haiku-4-5.md
+++ b/docs/llmservice/models/claude-haiku-4-5.md
@@ -28,3 +28,7 @@ Claude Haiku 4.5 is the fastest and most compact AI model developed by Anthropic
 | Model | Input (Credits/Token) | Cache Write (Credits/Token) | Cache Read (Credits/Token) | Output (Credits/Token) | Web Search (Credits/Use) | Billing Notes |
 | :--- | --------------------: | --------------------------: | -------------------------: | ---------------------: | -----------------------: | :--- |
 | **Claude Haiku 4.5** | `1.00` | `1.25` | `0.10` | `5.00` | `10,000` | - |
+
+:::info Pricing note
+Prices shown in the documentation are B.AI standard reference prices for base billing purposes. B.AI may provide lower actual usage costs through top-up bonuses and account benefits. Specific prices, bonus Credits, and account benefits are subject to the platform display and final billing records.
+:::
diff --git a/docs/llmservice/models/claude-opus-4-5.md b/docs/llmservice/models/claude-opus-4-5.md
index 601cf040..1023b382 100644
--- a/docs/llmservice/models/claude-opus-4-5.md
+++ b/docs/llmservice/models/claude-opus-4-5.md
@@ -28,3 +28,7 @@ Claude Opus 4.5 is the flagship AI model developed by Anthropic, integrated into
 | Model | Input (Credits/Token) | Cache Write (Credits/Token) | Cache Read (Credits/Token) | Output (Credits/Token) | Web Search (Credits/Use) | Billing Notes |
 | :--- | --------------------: | --------------------------: | -------------------------: | ---------------------: | -----------------------: | :--- |
 | **Claude Opus 4.5** | `5.00` | `6.25` | `0.50` | `25.00` | `10,000` | - |
+
+:::info Pricing note
+Prices shown in the documentation are B.AI standard reference prices for base billing purposes. B.AI may provide lower actual usage costs through top-up bonuses and account benefits. Specific prices, bonus Credits, and account benefits are subject to the platform display and final billing records.
+:::
diff --git a/docs/llmservice/models/claude-opus-4-6.md b/docs/llmservice/models/claude-opus-4-6.md
index 0540a2b4..52a536f4 100644
--- a/docs/llmservice/models/claude-opus-4-6.md
+++ b/docs/llmservice/models/claude-opus-4-6.md
@@ -30,3 +30,7 @@ Claude Opus 4.6 is a high-end model in Anthropic's Claude Opus series. Building
 | Model | Input (Credits/Token) | Cache Write (Credits/Token) | Cache Read (Credits/Token) | Output (Credits/Token) | Web Search (Credits/Use) | Billing Notes |
 | :--- | --------------------: | --------------------------: | -------------------------: | ---------------------: | -----------------------: | :--- |
 | **Claude Opus 4.6** | `5.00` | `6.25` | `0.50` | `25.00` | `10,000` | - |
+
+:::info Pricing note
+Prices shown in the documentation are B.AI standard reference prices for base billing purposes. B.AI may provide lower actual usage costs through top-up bonuses and account benefits. Specific prices, bonus Credits, and account benefits are subject to the platform display and final billing records.
+:::
diff --git a/docs/llmservice/models/claude-opus-4-7.md b/docs/llmservice/models/claude-opus-4-7.md
index 33e1d4c7..1343e0f1 100644
--- a/docs/llmservice/models/claude-opus-4-7.md
+++ b/docs/llmservice/models/claude-opus-4-7.md
@@ -46,3 +46,7 @@ Claude Opus 4.7, released on April 16, 2026, is Anthropic's most capable publicl
 | Model | Input (Credits/Token) | Cache Write (Credits/Token) | Cache Read (Credits/Token) | Output (Credits/Token) | Web Search (Credits/Use) | Billing Notes |
 | :--- | --------------------: | --------------------------: | -------------------------: | ---------------------: | -----------------------: | :--- |
 | **Claude Opus 4.7** | `5.00` | `6.25` | `0.50` | `25.00` | `10,000` | - |
+
+:::info Pricing note
+Prices shown in the documentation are B.AI standard reference prices for base billing purposes. B.AI may provide lower actual usage costs through top-up bonuses and account benefits. Specific prices, bonus Credits, and account benefits are subject to the platform display and final billing records.
+:::
diff --git a/docs/llmservice/models/claude-opus-4-8.md b/docs/llmservice/models/claude-opus-4-8.md
index dc90cea1..ec8d03b8 100644
--- a/docs/llmservice/models/claude-opus-4-8.md
+++ b/docs/llmservice/models/claude-opus-4-8.md
@@ -46,4 +46,8 @@ Claude Opus 4.8 is an advanced model in Anthropic's Claude Opus series, released
 | :--- | --------------------: | --------------------------: | -------------------------: | ---------------------: | -----------------------: | :--- |
 | **Claude Opus 4.8** | `5.00` | `6.25` | `0.50` | `25.00` | `10,000` | - |
 
+:::info Pricing note
+Prices shown in the documentation are B.AI standard reference prices for base billing purposes. B.AI may provide lower actual usage costs through top-up bonuses and account benefits. Specific prices, bonus Credits, and account benefits are subject to the platform display and final billing records.
+:::
+
 * **Prompt caching**: Cache writes are charged at 1.25x base input price for the 5-minute TTL option, or 2x base input price for the 1-hour TTL option. Cache reads are charged at 0.1x base input price. Prompt caching requires a minimum of 1,024 tokens.
diff --git a/docs/llmservice/models/claude-sonnet-4-5.md b/docs/llmservice/models/claude-sonnet-4-5.md
index a0279ea1..c6c496c6 100644
--- a/docs/llmservice/models/claude-sonnet-4-5.md
+++ b/docs/llmservice/models/claude-sonnet-4-5.md
@@ -28,3 +28,7 @@ Claude Sonnet 4.5 is a balanced AI model developed by Anthropic, integrated into
 | Model | Input (Credits/Token) | Cache Write (Credits/Token) | Cache Read (Credits/Token) | Output (Credits/Token) | Web Search (Credits/Use) | Billing Notes |
 | :--- | --------------------: | --------------------------: | -------------------------: | ---------------------: | -----------------------: | :--- |
 | **Claude Sonnet 4.5** | `3.00` | `3.75` | `0.30` | `15.00` | `10,000` | - |
+
+:::info Pricing note
+Prices shown in the documentation are B.AI standard reference prices for base billing purposes. B.AI may provide lower actual usage costs through top-up bonuses and account benefits. Specific prices, bonus Credits, and account benefits are subject to the platform display and final billing records.
+:::
diff --git a/docs/llmservice/models/claude-sonnet-4-6.md b/docs/llmservice/models/claude-sonnet-4-6.md
index 0251065d..25088fc5 100644
--- a/docs/llmservice/models/claude-sonnet-4-6.md
+++ b/docs/llmservice/models/claude-sonnet-4-6.md
@@ -30,3 +30,7 @@ Claude Sonnet 4.6 is a major upgrade to Anthropic's Sonnet series, designed to d
 | Model | Input (Credits/Token) | Cache Write (Credits/Token) | Cache Read (Credits/Token) | Output (Credits/Token) | Web Search (Credits/Use) | Billing Notes |
 | :--- | --------------------: | --------------------------: | -------------------------: | ---------------------: | -----------------------: | :--- |
 | **Claude Sonnet 4.6** | `3.00` | `3.75` | `0.30` | `15.00` | `10,000` | - |
+
+:::info Pricing note
+Prices shown in the documentation are B.AI standard reference prices for base billing purposes. B.AI may provide lower actual usage costs through top-up bonuses and account benefits. Specific prices, bonus Credits, and account benefits are subject to the platform display and final billing records.
+:::
diff --git a/docs/llmservice/models/deepseek-v3.2.md b/docs/llmservice/models/deepseek-v3.2.md
index caf0ad5d..b6e062db 100644
--- a/docs/llmservice/models/deepseek-v3.2.md
+++ b/docs/llmservice/models/deepseek-v3.2.md
@@ -45,3 +45,7 @@
 | Model | Input (Credits/Token) | Cache Write (Credits/Token) | Cache Read (Credits/Token) | Output (Credits/Token) | Web Search (Credits/Use) | Billing Notes |
 | :--- | --------------------: | --------------------------: | -------------------------: | ---------------------: | -----------------------: | :--- |
 | **DeepSeek V3.2** | `0.29` | `0.29` | `0.145` | `0.44` | `-` | - |
+
+:::info Pricing note
+Prices shown in the documentation are B.AI standard reference prices for base billing purposes. B.AI may provide lower actual usage costs through top-up bonuses and account benefits. Specific prices, bonus Credits, and account benefits are subject to the platform display and final billing records.
+:::
diff --git a/docs/llmservice/models/deepseek-v4-flash.md b/docs/llmservice/models/deepseek-v4-flash.md
index 6ff2b3d6..d9e5f8ed 100644
--- a/docs/llmservice/models/deepseek-v4-flash.md
+++ b/docs/llmservice/models/deepseek-v4-flash.md
@@ -41,3 +41,7 @@ DeepSeek-V4-Flash is DeepSeek's high-efficiency open-source language model, rele
 | Model | Input (Credits/Token) | Cache Write (Credits/Token) | Cache Read (Credits/Token) | Output (Credits/Token) | Web Search (Credits/Use) | Billing Notes |
 | :--- | --------------------: | --------------------------: | -------------------------: | ---------------------: | -----------------------: | :--- |
 | **DeepSeek V4 Flash** | `0.28` | `0.28` | `0.0056` | `0.56` | `-` | - |
+
+:::info Pricing note
+Prices shown in the documentation are B.AI standard reference prices for base billing purposes. B.AI may provide lower actual usage costs through top-up bonuses and account benefits. Specific prices, bonus Credits, and account benefits are subject to the platform display and final billing records.
+:::
diff --git a/docs/llmservice/models/deepseek-v4-pro.md b/docs/llmservice/models/deepseek-v4-pro.md
index f05eeaa2..67a252e2 100644
--- a/docs/llmservice/models/deepseek-v4-pro.md
+++ b/docs/llmservice/models/deepseek-v4-pro.md
@@ -41,3 +41,7 @@ DeepSeek-V4-Pro is DeepSeek's flagship open-source large language model, release
 | Model | Input (Credits/Token) | Cache Write (Credits/Token) | Cache Read (Credits/Token) | Output (Credits/Token) | Web Search (Credits/Use) | Billing Notes |
 | :--- | --------------------: | --------------------------: | -------------------------: | ---------------------: | -----------------------: | :--- |
 | **DeepSeek V4 Pro** | `0.87` | `0.87` | `0.0087` | `1.74` | `-` | - |
+
+:::info Pricing note
+Prices shown in the documentation are B.AI standard reference prices for base billing purposes. B.AI may provide lower actual usage costs through top-up bonuses and account benefits. Specific prices, bonus Credits, and account benefits are subject to the platform display and final billing records.
+:::
diff --git a/docs/llmservice/models/gemini-3-1-pro.md b/docs/llmservice/models/gemini-3-1-pro.md
index ca29188c..9e42ef55 100644
--- a/docs/llmservice/models/gemini-3-1-pro.md
+++ b/docs/llmservice/models/gemini-3-1-pro.md
@@ -29,3 +29,7 @@ Gemini 3.1 pro is a significant upgrade to Google's flagship multimodal model se
 | Model | Input (Credits/Token) | Cache Write (Credits/Token) | Cache Read (Credits/Token) | Output (Credits/Token) | Web Search (Credits/Use) | Billing Notes |
 | :--- | --------------------: | --------------------------: | -------------------------: | ---------------------: | -----------------------: | :--- |
 | **Gemini 3.1 Pro** | `2.00` | `2.00` | `0.20` | `12.00` | `14,000` | - |
+
+:::info Pricing note
+Prices shown in the documentation are B.AI standard reference prices for base billing purposes. B.AI may provide lower actual usage costs through top-up bonuses and account benefits. Specific prices, bonus Credits, and account benefits are subject to the platform display and final billing records.
+:::
diff --git a/docs/llmservice/models/gemini-3-5-flash.md b/docs/llmservice/models/gemini-3-5-flash.md
index 99b0dcea..ed254c49 100644
--- a/docs/llmservice/models/gemini-3-5-flash.md
+++ b/docs/llmservice/models/gemini-3-5-flash.md
@@ -37,3 +37,7 @@ On B.AI, use the model ID `gemini-3.5-flash`.
 | Model | Input (Credits/Token) | Cache Write (Credits/Token) | Cache Read (Credits/Token) | Output (Credits/Token) | Web Search (Credits/Use) | Billing Notes |
 | :--- | --------------------: | --------------------------: | -------------------------: | ---------------------: | -----------------------: | :--- |
 | **Gemini 3.5 Flash** | `1.50` | `1.50` | `0.15` | `9.00` | `14,000` | - |
+
+:::info Pricing note
+Prices shown in the documentation are B.AI standard reference prices for base billing purposes. B.AI may provide lower actual usage costs through top-up bonuses and account benefits. Specific prices, bonus Credits, and account benefits are subject to the platform display and final billing records.
+:::
diff --git a/docs/llmservice/models/gemini-3-flash.md b/docs/llmservice/models/gemini-3-flash.md
index 13510d7e..fb9308cc 100644
--- a/docs/llmservice/models/gemini-3-flash.md
+++ b/docs/llmservice/models/gemini-3-flash.md
@@ -28,3 +28,7 @@ Gemini 3 flash is the fastest and most efficient model in the Gemini 3 series re
 | Model | Input (Credits/Token) | Cache Write (Credits/Token) | Cache Read (Credits/Token) | Output (Credits/Token) | Web Search (Credits/Use) | Billing Notes |
 | :--- | --------------------: | --------------------------: | -------------------------: | ---------------------: | -----------------------: | :--- |
 | **Gemini 3 Flash** | `0.50` | `0.50` | `0.05` | `3.00` | `14,000` | - |
+
+:::info Pricing note
+Prices shown in the documentation are B.AI standard reference prices for base billing purposes. B.AI may provide lower actual usage costs through top-up bonuses and account benefits. Specific prices, bonus Credits, and account benefits are subject to the platform display and final billing records.
+:::
diff --git a/docs/llmservice/models/glm-5-1.md b/docs/llmservice/models/glm-5-1.md
index 62834ed5..084bf0b3 100644
--- a/docs/llmservice/models/glm-5-1.md
+++ b/docs/llmservice/models/glm-5-1.md
@@ -42,3 +42,7 @@ GLM-5.1 is an open-source flagship AI model developed by Z.ai, formerly Zhipu AI
 | Model | Input (Credits/Token) | Cache Write (Credits/Token) | Cache Read (Credits/Token) | Output (Credits/Token) | Web Search (Credits/Use) | Billing Notes |
 | :--- | --------------------: | --------------------------: | -------------------------: | ---------------------: | -----------------------: | :--- |
 | **GLM-5.1** | `1.40` | `1.40` | `0.26` | `4.40` | `-` | - |
+
+:::info Pricing note
+Prices shown in the documentation are B.AI standard reference prices for base billing purposes. B.AI may provide lower actual usage costs through top-up bonuses and account benefits. Specific prices, bonus Credits, and account benefits are subject to the platform display and final billing records.
+:::
diff --git a/docs/llmservice/models/glm-5.md b/docs/llmservice/models/glm-5.md
index b2c8091b..0d43c678 100644
--- a/docs/llmservice/models/glm-5.md
+++ b/docs/llmservice/models/glm-5.md
@@ -41,3 +41,7 @@ Based on a **744B** scale foundation model, combined with asynchronous reinforce
 | Model | Input (Credits/Token) | Cache Write (Credits/Token) | Cache Read (Credits/Token) | Output (Credits/Token) | Web Search (Credits/Use) | Billing Notes |
 | :--- | --------------------: | --------------------------: | -------------------------: | ---------------------: | -----------------------: | :--- |
 | **GLM-5** | `1.00` | `1.00` | `0.20` | `3.20` | `-` | - |
+
+:::info Pricing note
+Prices shown in the documentation are B.AI standard reference prices for base billing purposes. B.AI may provide lower actual usage costs through top-up bonuses and account benefits. Specific prices, bonus Credits, and account benefits are subject to the platform display and final billing records.
+:::
diff --git a/docs/llmservice/models/gpt-5-2.md b/docs/llmservice/models/gpt-5-2.md
index 54dc1c6c..a797ad71 100644
--- a/docs/llmservice/models/gpt-5-2.md
+++ b/docs/llmservice/models/gpt-5-2.md
@@ -28,3 +28,7 @@ GPT-5.2 is an OpenAI large language model optimized for multimodal processing sp
 | Model | Input (Credits/Token) | Cache Write (Credits/Token) | Cache Read (Credits/Token) | Output (Credits/Token) | Web Search (Credits/Use) | Billing Notes |
 | :--- | --------------------: | --------------------------: | -------------------------: | ---------------------: | -----------------------: | :--- |
 | **GPT-5.2** | `1.75` | `1.75` | `0.175` | `14.00` | `10,000` | - |
+
+:::info Pricing note
+Prices shown in the documentation are B.AI standard reference prices for base billing purposes. B.AI may provide lower actual usage costs through top-up bonuses and account benefits. Specific prices, bonus Credits, and account benefits are subject to the platform display and final billing records.
+:::
diff --git a/docs/llmservice/models/gpt-5-4-mini.md b/docs/llmservice/models/gpt-5-4-mini.md
index 0054075b..7cc3c63e 100644
--- a/docs/llmservice/models/gpt-5-4-mini.md
+++ b/docs/llmservice/models/gpt-5-4-mini.md
@@ -34,3 +34,7 @@ GPT-5.4 Mini is OpenAI's high-performance compact model released on March 17, 20
 | Model | Input (Credits/Token) | Cache Write (Credits/Token) | Cache Read (Credits/Token) | Output (Credits/Token) | Web Search (Credits/Use) | Billing Notes |
 | :--- | --------------------: | --------------------------: | -------------------------: | ---------------------: | -----------------------: | :--- |
 | **GPT-5.4 Mini** | `0.75` | `0.75` | `0.075` | `4.50` | `10,000` | - |
+
+:::info Pricing note
+Prices shown in the documentation are B.AI standard reference prices for base billing purposes. B.AI may provide lower actual usage costs through top-up bonuses and account benefits. Specific prices, bonus Credits, and account benefits are subject to the platform display and final billing records.
+:::
diff --git a/docs/llmservice/models/gpt-5-4-nano.md b/docs/llmservice/models/gpt-5-4-nano.md
index ed79dfde..97315dfd 100644
--- a/docs/llmservice/models/gpt-5-4-nano.md
+++ b/docs/llmservice/models/gpt-5-4-nano.md
@@ -34,3 +34,7 @@ GPT-5.4 Nano is the smallest and most cost-effective variant in the GPT-5.4 fami
 | Model | Input (Credits/Token) | Cache Write (Credits/Token) | Cache Read (Credits/Token) | Output (Credits/Token) | Web Search (Credits/Use) | Billing Notes |
 | :--- | --------------------: | --------------------------: | -------------------------: | ---------------------: | -----------------------: | :--- |
 | **GPT-5.4 Nano** | `0.20` | `0.20` | `0.02` | `1.25` | `10,000` | - |
+
+:::info Pricing note
+Prices shown in the documentation are B.AI standard reference prices for base billing purposes. B.AI may provide lower actual usage costs through top-up bonuses and account benefits. Specific prices, bonus Credits, and account benefits are subject to the platform display and final billing records.
+:::
diff --git a/docs/llmservice/models/gpt-5-4-pro.md b/docs/llmservice/models/gpt-5-4-pro.md
index ff84e2fd..258f08ef 100644
--- a/docs/llmservice/models/gpt-5-4-pro.md
+++ b/docs/llmservice/models/gpt-5-4-pro.md
@@ -34,3 +34,7 @@ GPT-5.4 Pro is the highest-performance variant in the GPT-5.4 family, allocating
 | Model | Input (Credits/Token) | Cache Write (Credits/Token) | Cache Read (Credits/Token) | Output (Credits/Token) | Web Search (Credits/Use) | Billing Notes |
 | :--- | --------------------: | --------------------------: | -------------------------: | ---------------------: | -----------------------: | :--- |
 | **GPT-5.4 Pro** | `30.00` | `30.00` | `3.00` | `180.00` | `-` | - |
+
+:::info Pricing note
+Prices shown in the documentation are B.AI standard reference prices for base billing purposes. B.AI may provide lower actual usage costs through top-up bonuses and account benefits. Specific prices, bonus Credits, and account benefits are subject to the platform display and final billing records.
+:::
diff --git a/docs/llmservice/models/gpt-5-4.md b/docs/llmservice/models/gpt-5-4.md
index 67e72b74..327dbb64 100644
--- a/docs/llmservice/models/gpt-5-4.md
+++ b/docs/llmservice/models/gpt-5-4.md
@@ -34,3 +34,7 @@ GPT-5.4 is OpenAI's frontier model released on March 5, 2026, and the first main
 | Model | Input (Credits/Token) | Cache Write (Credits/Token) | Cache Read (Credits/Token) | Output (Credits/Token) | Web Search (Credits/Use) | Billing Notes |
 | :--- | --------------------: | --------------------------: | -------------------------: | ---------------------: | -----------------------: | :--- |
 | **GPT-5.4** | `2.50` | `2.50` | `0.25` | `15.00` | `10,000` | - |
+
+:::info Pricing note
+Prices shown in the documentation are B.AI standard reference prices for base billing purposes. B.AI may provide lower actual usage costs through top-up bonuses and account benefits. Specific prices, bonus Credits, and account benefits are subject to the platform display and final billing records.
+:::
diff --git a/docs/llmservice/models/gpt-5-5-instant.md b/docs/llmservice/models/gpt-5-5-instant.md
index 445ae994..7a1e439a 100644
--- a/docs/llmservice/models/gpt-5-5-instant.md
+++ b/docs/llmservice/models/gpt-5-5-instant.md
@@ -41,3 +41,7 @@ GPT-5.5 Instant is an OpenAI model released on May 5, 2026 as the successor to G
 | Model | Input (Credits/Token) | Cache Write (Credits/Token) | Cache Read (Credits/Token) | Output (Credits/Token) | Web Search (Credits/Use) | Billing Notes |
 | :--- | --------------------: | --------------------------: | -------------------------: | ---------------------: | -----------------------: | :--- |
 | **GPT-5.5 Instant** | `5.00` | `5.00` | `0.50` | `30.00` | `10,000` | Long-context (>272K input tokens): Input 2x, Output 1.5x |
+
+:::info Pricing note
+Prices shown in the documentation are B.AI standard reference prices for base billing purposes. B.AI may provide lower actual usage costs through top-up bonuses and account benefits. Specific prices, bonus Credits, and account benefits are subject to the platform display and final billing records.
+:::
diff --git a/docs/llmservice/models/gpt-5-5.md b/docs/llmservice/models/gpt-5-5.md
index 22be8c2a..d48f7e9e 100644
--- a/docs/llmservice/models/gpt-5-5.md
+++ b/docs/llmservice/models/gpt-5-5.md
@@ -39,3 +39,7 @@ GPT-5.5 is OpenAI's most capable model, released on April 23, 2026. Codenamed "S
 | Model | Input (Credits/Token) | Cache Write (Credits/Token) | Cache Read (Credits/Token) | Output (Credits/Token) | Web Search (Credits/Use) | Billing Notes |
 | :--- | --------------------: | --------------------------: | -------------------------: | ---------------------: | -----------------------: | :--- |
 | **GPT-5.5** | `5.00` | `5.00` | `0.50` | `30.00` | `10,000` | 2x input / 1.5x output beyond 272K tokens |
+
+:::info Pricing note
+Prices shown in the documentation are B.AI standard reference prices for base billing purposes. B.AI may provide lower actual usage costs through top-up bonuses and account benefits. Specific prices, bonus Credits, and account benefits are subject to the platform display and final billing records.
+:::
diff --git a/docs/llmservice/models/gpt-5-mini.md b/docs/llmservice/models/gpt-5-mini.md
index 44969305..dc689011 100644
--- a/docs/llmservice/models/gpt-5-mini.md
+++ b/docs/llmservice/models/gpt-5-mini.md
@@ -28,3 +28,7 @@ GPT-5-mini is an efficient and economical lightweight language model. It is opti
 | Model | Input (Credits/Token) | Cache Write (Credits/Token) | Cache Read (Credits/Token) | Output (Credits/Token) | Web Search (Credits/Use) | Billing Notes |
 | :--- | --------------------: | --------------------------: | -------------------------: | ---------------------: | -----------------------: | :--- |
 | **GPT-5 Mini** | `0.25` | `0.25` | `0.025` | `2.00` | `10,000` | - |
+
+:::info Pricing note
+Prices shown in the documentation are B.AI standard reference prices for base billing purposes. B.AI may provide lower actual usage costs through top-up bonuses and account benefits. Specific prices, bonus Credits, and account benefits are subject to the platform display and final billing records.
+:::
diff --git a/docs/llmservice/models/gpt-5-nano.md b/docs/llmservice/models/gpt-5-nano.md
index 21b4baaf..ef72e2b3 100644
--- a/docs/llmservice/models/gpt-5-nano.md
+++ b/docs/llmservice/models/gpt-5-nano.md
@@ -28,3 +28,7 @@ GPT-5-nano is an advanced language model that strikes an excellent balance betwe
 | Model | Input (Credits/Token) | Cache Write (Credits/Token) | Cache Read (Credits/Token) | Output (Credits/Token) | Web Search (Credits/Use) | Billing Notes |
 | :--- | --------------------: | --------------------------: | -------------------------: | ---------------------: | -----------------------: | :--- |
 | **GPT-5 Nano** | `0.05` | `0.05` | `0.005` | `0.40` | `-` | - |
+
+:::info Pricing note
+Prices shown in the documentation are B.AI standard reference prices for base billing purposes. B.AI may provide lower actual usage costs through top-up bonuses and account benefits. Specific prices, bonus Credits, and account benefits are subject to the platform display and final billing records.
+:::
diff --git a/docs/llmservice/models/kimi-k2.5.md b/docs/llmservice/models/kimi-k2.5.md
index 56fe32ea..42eeab1b 100644
--- a/docs/llmservice/models/kimi-k2.5.md
+++ b/docs/llmservice/models/kimi-k2.5.md
@@ -42,3 +42,7 @@ With its **256K ultra-long context window**, multimodal understanding, and advan
 | Model | Input (Credits/Token) | Cache Write (Credits/Token) | Cache Read (Credits/Token) | Output (Credits/Token) | Web Search (Credits/Use) | Billing Notes |
 | :--- | --------------------: | --------------------------: | -------------------------: | ---------------------: | -----------------------: | :--- |
 | **Kimi K2.5** | `0.59` | `0.59` | `0.177` | `3.00` | `-` | - |
+
+:::info Pricing note
+Prices shown in the documentation are B.AI standard reference prices for base billing purposes. B.AI may provide lower actual usage costs through top-up bonuses and account benefits. Specific prices, bonus Credits, and account benefits are subject to the platform display and final billing records.
+:::
diff --git a/docs/llmservice/models/kimi-k2.6.md b/docs/llmservice/models/kimi-k2.6.md
index 485b397e..9d73ecc0 100644
--- a/docs/llmservice/models/kimi-k2.6.md
+++ b/docs/llmservice/models/kimi-k2.6.md
@@ -44,3 +44,7 @@ Kimi K2.6 is Moonshot AI's open-weight multimodal model, released on April 20, 2
 | Model | Input (Credits/Token) | Cache Write (Credits/Token) | Cache Read (Credits/Token) | Output (Credits/Token) | Web Search (Credits/Use) | Billing Notes |
 | :--- | --------------------: | --------------------------: | -------------------------: | ---------------------: | -----------------------: | :--- |
 | **Kimi K2.6** | `0.95` | `0.95` | `0.16` | `4.00` | `-` | - |
+
+:::info Pricing note
+Prices shown in the documentation are B.AI standard reference prices for base billing purposes. B.AI may provide lower actual usage costs through top-up bonuses and account benefits. Specific prices, bonus Credits, and account benefits are subject to the platform display and final billing records.
+:::
diff --git a/docs/llmservice/models/minimax-m2.5.md b/docs/llmservice/models/minimax-m2.5.md
index 7ff4a9e3..10082038 100644
--- a/docs/llmservice/models/minimax-m2.5.md
+++ b/docs/llmservice/models/minimax-m2.5.md
@@ -1,44 +1,7 @@
-# MiniMax-M2.5
+# MiniMax M2.5
 
-## Core Overview
-**MiniMax-M2.5** is MiniMax's independently developed flagship multimodal general large model, designed for **high-throughput and low-latency** production environments. 
+:::caution Model retired
+MiniMax M2.5 is no longer available on B.AI and has been removed from the active model catalog. Please refer to the current model list and pricing table for supported models.
+:::
 
-It achieves industry-leading performance in coding and Agent capabilities, with the ability to natively understand, generate, and integrate multiple modalities including **text, audio, images, video, and music**. M2.5 aims to provide top-tier performance at extremely low costs, excelling particularly in complex task processing and professional office scenarios.
-
----
-
-## Key Features
-* **Industry-Leading Coding & Agent Capabilities:** Achieved best-in-industry performance on the **Multi-SWE-Bench** benchmark, demonstrating higher decision-making maturity and more efficient token utilization.
-* **Efficient Multimodal Processing:** Natively supports the integration of text, audio, images, video, and music, providing a truly rich multimodal interactive experience.
-* **Ultra-Long Context Processing:** Features a substantial context window of **197K tokens**, optimized through reinforcement learning for precise task decomposition.
-* **High Throughput, Low Latency:** Optimized for production with **100 TPS** and **50 TPS** versions. Pricing is significantly lower (1/10 to 1/20) than comparable models.
-* **Enhanced Office Scenarios:** Significant capability improvements in handling professional software tasks such as Word, PPT, and Excel financial modeling.
-
----
-
-## Best Use Cases
-1.  **Enterprise-Level Automated Workflows:** Ideal for automation requiring fast multimodal processing and complex Agent decision-making.
-2.  **Software Development & Code Assistance:** Industry-leading generation and debugging, especially in large, complex codebases.
-3.  **Multimodal Content Creation:** Innovative cross-modal generation (e.g., text-to-video or image-to-music integration).
-4.  **Advanced Office Document Processing:** High-efficiency information extraction and modeling for Word, Excel, and PPT.
-
----
-
-## Capabilities and Limitations
-
-| Capability | Detailed Description |
-| :--- | :--- |
-| **Reasoning Ability** | **Extremely Strong.** High decision-making maturity for multi-step Agent tasks. |
-| **Creative Ability** | **Extremely Strong.** Proficient in multimodal creation and office document automation. |
-| **Multimodal Ability** | **Native Multimodal.** Supports text, audio, images, video, and music. |
-| **Response Speed** | **Extremely Fast.** Offers 100 TPS and 50 TPS versions for high-throughput needs. |
-| **Context Window** | 197,000 Tokens |
-| **Max Output** | 131,000 Tokens |
-
----
-
-## Credits Usage
-
-| Model | Input (Credits/Token) | Cache Write (Credits/Token) | Cache Read (Credits/Token) | Output (Credits/Token) | Web Search (Credits/Use) | Billing Notes |
-| :--- | --------------------: | --------------------------: | -------------------------: | ---------------------: | -----------------------: | :--- |
-| **MiniMax M2.5** | `0.30` | `0.375` | `0.03` | `1.20` | `-` | - |
+For current model availability and pricing, see [Pricing and Usage](/llmservice/pricing-and-usage/).
diff --git a/docs/llmservice/models/minimax-m2.7.md b/docs/llmservice/models/minimax-m2.7.md
index 85a1827d..e1602ec3 100644
--- a/docs/llmservice/models/minimax-m2.7.md
+++ b/docs/llmservice/models/minimax-m2.7.md
@@ -41,3 +41,7 @@ MiniMax M2.7 is a reasoning-focused large language model developed by MiniMax (S
 | Model | Input (Credits/Token) | Cache Write (Credits/Token) | Cache Read (Credits/Token) | Output (Credits/Token) | Web Search (Credits/Use) | Billing Notes |
 | :--- | --------------------: | --------------------------: | -------------------------: | ---------------------: | -----------------------: | :--- |
 | **MiniMax M2.7** | `0.30` | `0.375` | `0.06` | `1.20` | `-` | - |
+
+:::info Pricing note
+Prices shown in the documentation are B.AI standard reference prices for base billing purposes. B.AI may provide lower actual usage costs through top-up bonuses and account benefits. Specific prices, bonus Credits, and account benefits are subject to the platform display and final billing records.
+:::
diff --git a/docs/llmservice/models/minimax-m3.md b/docs/llmservice/models/minimax-m3.md
index cff10ffe..2ea217fa 100644
--- a/docs/llmservice/models/minimax-m3.md
+++ b/docs/llmservice/models/minimax-m3.md
@@ -40,3 +40,7 @@ MiniMax M3 is MiniMax's next-generation large language model in the M series. It
 | Model | Input (Credits/Token) | Cache Write (Credits/Token) | Cache Read (Credits/Token) | Output (Credits/Token) | Web Search (Credits/Use) | Billing Notes |
 | :--- | --------------------: | --------------------------: | -------------------------: | ---------------------: | -----------------------: | :--- |
 | **MiniMax M3** | `0.30` | `0.30` | `0.06` | `1.20` | `-` | - |
+
+:::info Pricing note
+Prices shown in the documentation are B.AI standard reference prices for base billing purposes. B.AI may provide lower actual usage costs through top-up bonuses and account benefits. Specific prices, bonus Credits, and account benefits are subject to the platform display and final billing records.
+:::
diff --git a/docs/llmservice/pricing-and-usage.md b/docs/llmservice/pricing-and-usage.md
index 0f5c6b50..6bf0a175 100644
--- a/docs/llmservice/pricing-and-usage.md
+++ b/docs/llmservice/pricing-and-usage.md
@@ -16,7 +16,6 @@ The platform uses a unified Credits system to measure and settle usage across al
 | :---------------- | --------------------: | --------------------------: | -------------------------: | ---------------------: | -----------------------: |
 | MiniMax M3        |                  0.30 |                        0.30 |                       0.06 |                   1.20 |                        - |
 | MiniMax M2.7      |                  0.30 |                       0.375 |                       0.06 |                   1.20 |                        - |
-| MiniMax M2.5      |                  0.30 |                       0.375 |                       0.03 |                   1.20 |                        - |
 | Kimi K2.6         |                  0.95 |                        0.95 |                       0.16 |                   4.00 |                        - |
 | Kimi K2.5         |                  0.59 |                        0.59 |                      0.177 |                   3.00 |                        - |
 | GLM-5.1           |                  1.40 |                        1.40 |                       0.26 |                   4.40 |                        - |
@@ -33,6 +32,7 @@ The platform uses a unified Credits system to measure and settle usage across al
 | GPT-5 Mini        |                  0.25 |                        0.25 |                      0.025 |                   2.00 |                   10,000 |
 | GPT-5.4 Nano      |                  0.20 |                        0.20 |                       0.02 |                   1.25 |                   10,000 |
 | GPT-5 Nano        |                  0.05 |                        0.05 |                      0.005 |                   0.40 |                        - |
+| Claude Fable 5    |                 10.00 |                       12.50 |                       1.00 |                  50.00 |                   10,000 |
 | Claude Opus 4.8   |                  5.00 |                        6.25 |                       0.50 |                  25.00 |                   10,000 |
 | Claude Opus 4.7   |                  5.00 |                        6.25 |                       0.50 |                  25.00 |                   10,000 |
 | Claude Opus 4.6   |                  5.00 |                        6.25 |                       0.50 |                  25.00 |                   10,000 |
@@ -44,6 +44,10 @@ The platform uses a unified Credits system to measure and settle usage across al
 | Gemini 3.5 Flash  |                  1.50 |                        1.50 |                       0.15 |                   9.00 |                   14,000 |
 | Gemini 3 Flash    |                  0.50 |                        0.50 |                       0.05 |                   3.00 |                   14,000 |
 
+:::info Pricing note
+Prices shown in the documentation are B.AI standard reference prices for base billing purposes. B.AI may provide lower actual usage costs through top-up bonuses and account benefits. Specific prices, bonus Credits, and account benefits are subject to the platform display and final billing records.
+:::
+
 ### Cache Pricing Notes
 
 - **Cache Write:** The cost when tokens are first written into the prompt cache. Most providers charge no premium and use the same rate as standard input pricing. Claude models apply a 25% premium on cache writes.
@@ -114,15 +118,15 @@ You can use the **Usage** page in the left navigation to review detailed consump
 
 The platform uses a prepaid model, so you need to top up your account to obtain Credits. The platform offers a secure and convenient top-up experience across fiat payment channels and supported blockchain networks.
 
-Fiat payment is now supported. You can follow the on-screen instructions to complete a top-up using Alipay, WeChat Pay, UnionPay, credit cards, or other supported payment methods.
+The platform now supports both fiat and on-chain top-up flows end to end. You can follow the on-screen instructions to top up with Stripe-supported card payments, WeChat Pay, Alipay, UnionPay, and other available fiat payment methods, or use supported blockchain networks and tokens for on-chain payment.
 
 :::caution Security reminder
-Before topping up, make sure the address bar shows an official B.AI domain, such as `https://b.ai` or `https://chat.b.ai`. Do not continue from unfamiliar links, search ads, or pages with a different domain.
+Before topping up, make sure the address bar shows an official B.AI access URL, such as `https://chat.b.ai/chat`, `https://chat.ainft.com/chat`, or `https://chat.bankofai.io/chat`. Do not continue from unfamiliar links, search ads, or pages with a different domain.
 
 Complete fund-related operations only in a trusted network environment. Avoid topping up on public or shared Wi-Fi, and always review the payment details shown by your wallet before confirming.
 :::
 
-**Top-up process:** On the **Top up** page, the platform guides you through the selected payment method. You can use fiat payment methods such as Alipay, WeChat Pay, and UnionPay, or choose supported blockchain networks and tokens for on-chain payment. Follow the on-screen instructions to confirm the payment, and the system will automatically process the top-up after payment succeeds.
+**Top-up process:** On the **Top up** page, the platform guides you through the selected payment method. You can use fiat payment methods such as Stripe-supported card payments, WeChat Pay, Alipay, and UnionPay, or choose supported blockchain networks and tokens for on-chain payment. Follow the on-screen instructions to confirm the payment, and the system will automatically process the top-up after payment succeeds.
 
 **Supported payment methods:** The platform supports multiple fiat payment channels and mainstream tokens across supported blockchain networks. Available payment channels, networks, and token types may vary by region and availability, so please refer to the real-time options shown on the **Top up** page.
 
diff --git a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/claude-fable-5.md b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/claude-fable-5.md
new file mode 100644
index 00000000..c355efe5
--- /dev/null
+++ b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/claude-fable-5.md
@@ -0,0 +1,53 @@
+# Claude Fable 5
+
+## 概述
+
+Claude Fable 5 是 B.AI 上可用的 Anthropic 高能力模型，面向复杂推理、代码任务、长上下文分析和 Agent 工作流。它适合需要持续上下文、工具辅助执行和高质量结构化输出的复杂任务。具体能力、上下文长度、工具支持和可用状态可能会随 B.AI 模型目录和平台配置调整。
+
+## 核心特性
+
+* **高级推理能力**：适合复杂分析、技术任务和专业知识工作。
+* **软件工程工作流**：面向代码辅助、调试、重构、代码审查和多步骤实现规划。
+* **长上下文任务**：在平台配置支持时，可用于大型代码库、长文档和多轮工作会话的持续分析。
+* **Agent 与工具辅助工作流**：适合依赖工具调用、函数调用、代码执行、MCP 或兼容 Agent 环境的工作流。
+* **多模态理解**：在可用场景下，支持文本和图像输入，可用于文档、截图、图表和技术示意图理解。
+
+## 适用场景
+
+* **复杂软件工程**：大型功能开发、仓库级重构、迁移规划、Bug 排查和代码审查。
+* **长时间 Agent 工作流**：需要规划、工具调用、验证和持续上下文保持的多步骤任务。
+* **研究与知识工作**：技术文档、法律或金融材料以及结构化研究资料的分析与综合。
+* **视觉文档分析**：在工作流支持时，可处理截图、图表、PDF 和其他图像型材料。
+
+## 能力与限制
+
+| 能力维度 | 说明 |
+| :--- | :--- |
+| **推理能力** | 适合复杂专业任务和技术任务的高级推理 |
+| **编程能力** | 具备较强的编码、调试、重构和代码审查能力 |
+| **Agent 能力** | 适合长时间工具调用工作流和多步骤 Agent 任务 |
+| **计算机操作** | 可通过兼容工具和环境支持浏览器及桌面交互 |
+| **多模态能力** | 支持文本和图像输入；输出为文本 |
+| **上下文窗口** | 最高 1,000,000 tokens，具体以平台配置为准 |
+| **最大输出** | 最高 128,000 tokens，具体以平台配置为准 |
+| **工具调用** | 支持函数调用、代码执行、MCP、自适应思考和兼容 Agent 工作流 |
+| **多语言能力** | 在主要世界语言上具备较强的多语言表现 |
+
+### 已知限制
+
+* 具体能力可用性可能取决于 B.AI 集成、Anthropic 平台支持、套餐配置和功能上线状态。
+* 联网访问、代码执行、计算机操作和外部动作需要兼容工具或集成支持。
+* 支持图像输入，但该模型未标明原生音频或视频输入能力。
+* 公开评测、第三方对比、策略行为和实现细节可能随时间变化，因此本文档不将其作为固定承诺。
+
+## 积分消耗
+
+| 模型名称 | 输入 (Credits/Token) | Cache Write (Credits/Token) | Cache Read (Credits/Token) | 输出 (Credits/Token) | 网页搜索（Credits/次） | 计费说明 |
+| :--- | --------------------: | --------------------------: | -------------------------: | -------------------: | ---------------------: | :--- |
+| **Claude Fable 5** | `10.00` | `12.50` | `1.00` | `50.00` | `10,000` | - |
+
+:::info 价格说明
+文档价格为 B.AI 平台模型标准参考价，仅供基础计费说明使用。B.AI 可能会通过充值赠送及账户权益等方式，为用户提供更低的实际使用成本。具体价格、赠送积分及账户权益请以平台页面展示及最终账单为准。
+:::
+
+* **Prompt caching**：缓存写入按基础输入价格的 1.25x 计费（5 分钟 TTL），或按基础输入价格的 2x 计费（1 小时 TTL）。缓存读取按基础输入价格的 0.1x 计费。使用 Prompt caching 时，最低需要 1,024 tokens。
diff --git a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/claude-haiku-4-5.md b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/claude-haiku-4-5.md
index c7f6be4e..e3c80808 100644
--- a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/claude-haiku-4-5.md
+++ b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/claude-haiku-4-5.md
@@ -39,3 +39,7 @@ Claude Haiku 4.5 是 Anthropic 推出的轻量高速模型，已集成至 白B.A
 | 模型名称 | 输入 (Credits/Token) | Cache Write (Credits/Token) | Cache Read (Credits/Token) | 输出 (Credits/Token) | 网页搜索（Credits/次） | 计费说明 |
 | :--- | --------------------: | --------------------------: | -------------------------: | -------------------: | ---------------------: | :--- |
 | **Claude Haiku 4.5** | `1.00` | `1.25` | `0.10` | `5.00` | `10,000` | - |
+
+:::info 价格说明
+文档价格为 B.AI 平台模型标准参考价，仅供基础计费说明使用。B.AI 可能会通过充值赠送及账户权益等方式，为用户提供更低的实际使用成本。具体价格、赠送积分及账户权益请以平台页面展示及最终账单为准。
+:::
diff --git a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/claude-opus-4-5.md b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/claude-opus-4-5.md
index ee247183..6fcfcf12 100644
--- a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/claude-opus-4-5.md
+++ b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/claude-opus-4-5.md
@@ -39,3 +39,7 @@ Claude Opus 4.5 是 Anthropic 推出的旗舰级 AI 模型，已集成至 白B.A
 | 模型名称 | 输入 (Credits/Token) | Cache Write (Credits/Token) | Cache Read (Credits/Token) | 输出 (Credits/Token) | 网页搜索（Credits/次） | 计费说明 |
 | :--- | --------------------: | --------------------------: | -------------------------: | -------------------: | ---------------------: | :--- |
 | **Claude Opus 4.5** | `5.00` | `6.25` | `0.50` | `25.00` | `10,000` | - |
+
+:::info 价格说明
+文档价格为 B.AI 平台模型标准参考价，仅供基础计费说明使用。B.AI 可能会通过充值赠送及账户权益等方式，为用户提供更低的实际使用成本。具体价格、赠送积分及账户权益请以平台页面展示及最终账单为准。
+:::
diff --git a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/claude-opus-4-6.md b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/claude-opus-4-6.md
index 73d01d01..c3fac99c 100644
--- a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/claude-opus-4-6.md
+++ b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/claude-opus-4-6.md
@@ -41,3 +41,7 @@ Claude Opus 4.6 是 Anthropic 旗舰模型系列的最新版本。在 4.5 强大
 | 模型名称 | 输入 (Credits/Token) | Cache Write (Credits/Token) | Cache Read (Credits/Token) | 输出 (Credits/Token) | 网页搜索（Credits/次） | 计费说明 |
 | :--- | --------------------: | --------------------------: | -------------------------: | -------------------: | ---------------------: | :--- |
 | **Claude Opus 4.6** | `5.00` | `6.25` | `0.50` | `25.00` | `10,000` | - |
+
+:::info 价格说明
+文档价格为 B.AI 平台模型标准参考价，仅供基础计费说明使用。B.AI 可能会通过充值赠送及账户权益等方式，为用户提供更低的实际使用成本。具体价格、赠送积分及账户权益请以平台页面展示及最终账单为准。
+:::
diff --git a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/claude-opus-4-7.md b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/claude-opus-4-7.md
index 5b30267f..45ac8904 100644
--- a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/claude-opus-4-7.md
+++ b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/claude-opus-4-7.md
@@ -46,3 +46,7 @@ Claude Opus 4.7 于 2026 年 4 月 16 日发布，是 Anthropic 在 Claude 4 系
 | 模型名称 | 输入 (Credits/Token) | Cache Write (Credits/Token) | Cache Read (Credits/Token) | 输出 (Credits/Token) | 网页搜索（Credits/次） | 计费说明 |
 | :--- | --------------------: | --------------------------: | -------------------------: | -------------------: | ---------------------: | :--- |
 | **Claude Opus 4.7** | `5.00` | `6.25` | `0.50` | `25.00` | `10,000` | - |
+
+:::info 价格说明
+文档价格为 B.AI 平台模型标准参考价，仅供基础计费说明使用。B.AI 可能会通过充值赠送及账户权益等方式，为用户提供更低的实际使用成本。具体价格、赠送积分及账户权益请以平台页面展示及最终账单为准。
+:::
diff --git a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/claude-opus-4-8.md b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/claude-opus-4-8.md
index dd419243..66f2b3f4 100644
--- a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/claude-opus-4-8.md
+++ b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/claude-opus-4-8.md
@@ -46,4 +46,8 @@ Claude Opus 4.8 是 Anthropic Claude Opus 系列中的高能力模型，于 2026
 | :--- | --------------------: | --------------------------: | -------------------------: | -------------------: | ---------------------: | :--- |
 | **Claude Opus 4.8** | `5.00` | `6.25` | `0.50` | `25.00` | `10,000` | - |
 
+:::info 价格说明
+文档价格为 B.AI 平台模型标准参考价，仅供基础计费说明使用。B.AI 可能会通过充值赠送及账户权益等方式，为用户提供更低的实际使用成本。具体价格、赠送积分及账户权益请以平台页面展示及最终账单为准。
+:::
+
 * **Prompt caching**：缓存写入按基础输入价格的 1.25x 计费（5 分钟 TTL），或按基础输入价格的 2x 计费（1 小时 TTL）。缓存读取按基础输入价格的 0.1x 计费。使用 Prompt caching 时，最低需要 1,024 tokens。
diff --git a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/claude-sonnet-4-5.md b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/claude-sonnet-4-5.md
index c164aac3..143851b3 100644
--- a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/claude-sonnet-4-5.md
+++ b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/claude-sonnet-4-5.md
@@ -39,3 +39,7 @@ Claude Sonnet 4.5 是 Anthropic 推出的平衡型 AI 模型，已集成至 白B
 | 模型名称 | 输入 (Credits/Token) | Cache Write (Credits/Token) | Cache Read (Credits/Token) | 输出 (Credits/Token) | 网页搜索（Credits/次） | 计费说明 |
 | :--- | --------------------: | --------------------------: | -------------------------: | -------------------: | ---------------------: | :--- |
 | **Claude Sonnet 4.5** | `3.00` | `3.75` | `0.30` | `15.00` | `10,000` | - |
+
+:::info 价格说明
+文档价格为 B.AI 平台模型标准参考价，仅供基础计费说明使用。B.AI 可能会通过充值赠送及账户权益等方式，为用户提供更低的实际使用成本。具体价格、赠送积分及账户权益请以平台页面展示及最终账单为准。
+:::
diff --git a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/claude-sonnet-4-6.md b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/claude-sonnet-4-6.md
index b977e668..ce189e2e 100644
--- a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/claude-sonnet-4-6.md
+++ b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/claude-sonnet-4-6.md
@@ -41,3 +41,7 @@ Claude Sonnet 4.6 是 Anthropic Sonnet 系列的重要升级版本，在更低
 | 模型名称 | 输入 (Credits/Token) | Cache Write (Credits/Token) | Cache Read (Credits/Token) | 输出 (Credits/Token) | 网页搜索（Credits/次） | 计费说明 |
 | :--- | --------------------: | --------------------------: | -------------------------: | -------------------: | ---------------------: | :--- |
 | **Claude Sonnet 4.6** | `3.00` | `3.75` | `0.30` | `15.00` | `10,000` | - |
+
+:::info 价格说明
+文档价格为 B.AI 平台模型标准参考价，仅供基础计费说明使用。B.AI 可能会通过充值赠送及账户权益等方式，为用户提供更低的实际使用成本。具体价格、赠送积分及账户权益请以平台页面展示及最终账单为准。
+:::
diff --git a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/deepseek-v3.2.md b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/deepseek-v3.2.md
index c3122b5d..82d225a6 100644
--- a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/deepseek-v3.2.md
+++ b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/deepseek-v3.2.md
@@ -42,3 +42,7 @@
 | 模型名称 | 输入 (Credits/Token) | Cache Write (Credits/Token) | Cache Read (Credits/Token) | 输出 (Credits/Token) | 网页搜索（Credits/次） | 计费说明 |
 | :--- | --------------------: | --------------------------: | -------------------------: | -------------------: | ---------------------: | :--- |
 | **DeepSeek V3.2** | `0.29` | `0.29` | `0.145` | `0.44` | `-` | - |
+
+:::info 价格说明
+文档价格为 B.AI 平台模型标准参考价，仅供基础计费说明使用。B.AI 可能会通过充值赠送及账户权益等方式，为用户提供更低的实际使用成本。具体价格、赠送积分及账户权益请以平台页面展示及最终账单为准。
+:::
diff --git a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/deepseek-v4-flash.md b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/deepseek-v4-flash.md
index cf8553af..713e8643 100644
--- a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/deepseek-v4-flash.md
+++ b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/deepseek-v4-flash.md
@@ -41,3 +41,7 @@ DeepSeek-V4-Flash 是 DeepSeek 于 2026 年 4 月 24 日与 V4-Pro 同步发布
 | 模型名称 | 输入 (Credits/Token) | Cache Write (Credits/Token) | Cache Read (Credits/Token) | 输出 (Credits/Token) | 网页搜索（Credits/次） | 计费说明 |
 | :--- | --------------------: | --------------------------: | -------------------------: | -------------------: | ---------------------: | :--- |
 | **DeepSeek V4 Flash** | `0.28` | `0.28` | `0.0056` | `0.56` | `-` | - |
+
+:::info 价格说明
+文档价格为 B.AI 平台模型标准参考价，仅供基础计费说明使用。B.AI 可能会通过充值赠送及账户权益等方式，为用户提供更低的实际使用成本。具体价格、赠送积分及账户权益请以平台页面展示及最终账单为准。
+:::
diff --git a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/deepseek-v4-pro.md b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/deepseek-v4-pro.md
index 6488510b..10b3e3cc 100644
--- a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/deepseek-v4-pro.md
+++ b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/deepseek-v4-pro.md
@@ -41,3 +41,7 @@ DeepSeek-V4-Pro 是 DeepSeek 于 2026 年 4 月 24 日基于 MIT License 发布
 | 模型名称 | 输入 (Credits/Token) | Cache Write (Credits/Token) | Cache Read (Credits/Token) | 输出 (Credits/Token) | 网页搜索（Credits/次） | 计费说明 |
 | :--- | --------------------: | --------------------------: | -------------------------: | -------------------: | ---------------------: | :--- |
 | **DeepSeek V4 Pro** | `0.87` | `0.87` | `0.0087` | `1.74` | `-` | - |
+
+:::info 价格说明
+文档价格为 B.AI 平台模型标准参考价，仅供基础计费说明使用。B.AI 可能会通过充值赠送及账户权益等方式，为用户提供更低的实际使用成本。具体价格、赠送积分及账户权益请以平台页面展示及最终账单为准。
+:::
diff --git a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gemini-3-1-pro.md b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gemini-3-1-pro.md
index d3614ad8..e7be56bf 100644
--- a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gemini-3-1-pro.md
+++ b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gemini-3-1-pro.md
@@ -40,3 +40,7 @@ Gemini 3.1 Pro 是 Google 旗舰多模态模型的重要升级版本，在推理
 | 模型名称 | 输入 (Credits/Token) | Cache Write (Credits/Token) | Cache Read (Credits/Token) | 输出 (Credits/Token) | 网页搜索（Credits/次） | 计费说明 |
 | :--- | --------------------: | --------------------------: | -------------------------: | -------------------: | ---------------------: | :--- |
 | **Gemini 3.1 Pro** | `2.00` | `2.00` | `0.20` | `12.00` | `14,000` | - |
+
+:::info 价格说明
+文档价格为 B.AI 平台模型标准参考价，仅供基础计费说明使用。B.AI 可能会通过充值赠送及账户权益等方式，为用户提供更低的实际使用成本。具体价格、赠送积分及账户权益请以平台页面展示及最终账单为准。
+:::
diff --git a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gemini-3-5-flash.md b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gemini-3-5-flash.md
index 58ede3e6..14cfff4a 100644
--- a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gemini-3-5-flash.md
+++ b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gemini-3-5-flash.md
@@ -45,3 +45,7 @@ Gemini 3.5 Flash 是 Gemini 3 系列中的 Flash 层级模型。它面向低延
 | 模型名称 | 输入 (Credits/Token) | Cache Write (Credits/Token) | Cache Read (Credits/Token) | 输出 (Credits/Token) | 网页搜索（Credits/次） | 计费说明 |
 | :--- | --------------------: | --------------------------: | -------------------------: | -------------------: | ---------------------: | :--- |
 | **Gemini 3.5 Flash** | `1.50` | `1.50` | `0.15` | `9.00` | `14,000` | - |
+
+:::info 价格说明
+文档价格为 B.AI 平台模型标准参考价，仅供基础计费说明使用。B.AI 可能会通过充值赠送及账户权益等方式，为用户提供更低的实际使用成本。具体价格、赠送积分及账户权益请以平台页面展示及最终账单为准。
+:::
diff --git a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gemini-3-flash.md b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gemini-3-flash.md
index 83424625..9fb1312e 100644
--- a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gemini-3-flash.md
+++ b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gemini-3-flash.md
@@ -39,3 +39,7 @@ Gemini 3 Flash 是 Google Gemini 3 系列中速度最快、效率最高的模型
 | 模型名称 | 输入 (Credits/Token) | Cache Write (Credits/Token) | Cache Read (Credits/Token) | 输出 (Credits/Token) | 网页搜索（Credits/次） | 计费说明 |
 | :--- | --------------------: | --------------------------: | -------------------------: | -------------------: | ---------------------: | :--- |
 | **Gemini 3 Flash** | `0.50` | `0.50` | `0.05` | `3.00` | `14,000` | - |
+
+:::info 价格说明
+文档价格为 B.AI 平台模型标准参考价，仅供基础计费说明使用。B.AI 可能会通过充值赠送及账户权益等方式，为用户提供更低的实际使用成本。具体价格、赠送积分及账户权益请以平台页面展示及最终账单为准。
+:::
diff --git a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/glm-5-1.md b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/glm-5-1.md
index 41f7bf9a..b1edd1bf 100644
--- a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/glm-5-1.md
+++ b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/glm-5-1.md
@@ -42,3 +42,7 @@ GLM-5.1 是由 Z.ai 开发的开源旗舰 AI 模型。Z.ai 前身为智谱 AI，
 | 模型名称 | 输入 (Credits/Token) | Cache Write (Credits/Token) | Cache Read (Credits/Token) | 输出 (Credits/Token) | 网页搜索（Credits/次） | 计费说明 |
 | :--- | --------------------: | --------------------------: | -------------------------: | -------------------: | ---------------------: | :--- |
 | **GLM-5.1** | `1.40` | `1.40` | `0.26` | `4.40` | `-` | - |
+
+:::info 价格说明
+文档价格为 B.AI 平台模型标准参考价，仅供基础计费说明使用。B.AI 可能会通过充值赠送及账户权益等方式，为用户提供更低的实际使用成本。具体价格、赠送积分及账户权益请以平台页面展示及最终账单为准。
+:::
diff --git a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/glm-5.md b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/glm-5.md
index 35488bc7..4a5f51f8 100644
--- a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/glm-5.md
+++ b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/glm-5.md
@@ -44,3 +44,7 @@
 | 模型名称 | 输入 (Credits/Token) | Cache Write (Credits/Token) | Cache Read (Credits/Token) | 输出 (Credits/Token) | 网页搜索（Credits/次） | 计费说明 |
 | :--- | --------------------: | --------------------------: | -------------------------: | -------------------: | ---------------------: | :--- |
 | **GLM-5** | `1.00` | `1.00` | `0.20` | `3.20` | `-` | - |
+
+:::info 价格说明
+文档价格为 B.AI 平台模型标准参考价，仅供基础计费说明使用。B.AI 可能会通过充值赠送及账户权益等方式，为用户提供更低的实际使用成本。具体价格、赠送积分及账户权益请以平台页面展示及最终账单为准。
+:::
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 8de6b0e3..87aba76b 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
@@ -39,3 +39,7 @@ GPT-5.2 是 OpenAI 的一款大语言模型，重点优化了多模态处理速
 | 模型名称 | 输入 (Credits/Token) | Cache Write (Credits/Token) | Cache Read (Credits/Token) | 输出 (Credits/Token) | 网页搜索（Credits/次） | 计费说明 |
 | :--- | --------------------: | --------------------------: | -------------------------: | -------------------: | ---------------------: | :--- |
 | **GPT-5.2** | `1.75` | `1.75` | `0.175` | `14.00` | `10,000` | - |
+
+:::info 价格说明
+文档价格为 B.AI 平台模型标准参考价，仅供基础计费说明使用。B.AI 可能会通过充值赠送及账户权益等方式，为用户提供更低的实际使用成本。具体价格、赠送积分及账户权益请以平台页面展示及最终账单为准。
+:::
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
index f5439707..ba85176a 100644
--- 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
@@ -34,3 +34,7 @@ GPT-5.4 Mini 是 OpenAI 于 2026 年 3 月 17 日发布的一款高性能轻量
 | 模型名称 | 输入 (Credits/Token) | Cache Write (Credits/Token) | Cache Read (Credits/Token) | 输出 (Credits/Token) | 网页搜索（Credits/次） | 计费说明 |
 | :--- | --------------------: | --------------------------: | -------------------------: | -------------------: | ---------------------: | :--- |
 | **GPT-5.4 Mini** | `0.75` | `0.75` | `0.075` | `4.50` | `10,000` | - |
+
+:::info 价格说明
+文档价格为 B.AI 平台模型标准参考价，仅供基础计费说明使用。B.AI 可能会通过充值赠送及账户权益等方式，为用户提供更低的实际使用成本。具体价格、赠送积分及账户权益请以平台页面展示及最终账单为准。
+:::
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 acd3dd90..ab3f61da 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
@@ -41,3 +41,7 @@ GPT-5.4 Nano 是 GPT-5.4 系列中体量最小、成本最低的版本，于 202
 | 模型名称 | 输入 (Credits/Token) | Cache Write (Credits/Token) | Cache Read (Credits/Token) | 输出 (Credits/Token) | 网页搜索（Credits/次） | 计费说明 |
 | :--- | --------------------: | --------------------------: | -------------------------: | -------------------: | ---------------------: | :--- |
 | **GPT-5.4 Nano** | `0.20` | `0.20` | `0.02` | `1.25` | `10,000` | - |
+
+:::info 价格说明
+文档价格为 B.AI 平台模型标准参考价，仅供基础计费说明使用。B.AI 可能会通过充值赠送及账户权益等方式，为用户提供更低的实际使用成本。具体价格、赠送积分及账户权益请以平台页面展示及最终账单为准。
+:::
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
index 0da2e8f1..a7f8fc17 100644
--- 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
@@ -34,3 +34,7 @@ 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
 | 模型名称 | 输入 (Credits/Token) | Cache Write (Credits/Token) | Cache Read (Credits/Token) | 输出 (Credits/Token) | 网页搜索（Credits/次） | 计费说明 |
 | :--- | --------------------: | --------------------------: | -------------------------: | -------------------: | ---------------------: | :--- |
 | **GPT-5.4 Pro** | `30.00` | `30.00` | `3.00` | `180.00` | `-` | - |
+
+:::info 价格说明
+文档价格为 B.AI 平台模型标准参考价，仅供基础计费说明使用。B.AI 可能会通过充值赠送及账户权益等方式，为用户提供更低的实际使用成本。具体价格、赠送积分及账户权益请以平台页面展示及最终账单为准。
+:::
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
index 51d8b5c8..5b54560b 100644
--- 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
@@ -34,3 +34,7 @@ GPT-5.4 是 OpenAI 于 2026 年 3 月 5 日发布的前沿模型。它是首个
 | 模型名称 | 输入 (Credits/Token) | Cache Write (Credits/Token) | Cache Read (Credits/Token) | 输出 (Credits/Token) | 网页搜索（Credits/次） | 计费说明 |
 | :--- | --------------------: | --------------------------: | -------------------------: | -------------------: | ---------------------: | :--- |
 | **GPT-5.4** | `2.50` | `2.50` | `0.25` | `15.00` | `10,000` | - |
+
+:::info 价格说明
+文档价格为 B.AI 平台模型标准参考价，仅供基础计费说明使用。B.AI 可能会通过充值赠送及账户权益等方式，为用户提供更低的实际使用成本。具体价格、赠送积分及账户权益请以平台页面展示及最终账单为准。
+:::
diff --git a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gpt-5-5-instant.md b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gpt-5-5-instant.md
index 7d7e4622..3e4b978a 100644
--- a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gpt-5-5-instant.md
+++ b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gpt-5-5-instant.md
@@ -40,3 +40,7 @@ GPT-5.5 Instant 是 OpenAI 于 2026 年 5 月 5 日发布的模型，作为 GPT-
 | 模型名称 | 输入 (Credits/Token) | Cache Write (Credits/Token) | Cache Read (Credits/Token) | 输出 (Credits/Token) | 网页搜索（Credits/次） | 计费说明 |
 | :--- | --------------------: | --------------------------: | -------------------------: | -------------------: | ---------------------: | :--- |
 | **GPT-5.5 Instant** | `5.00` | `5.00` | `0.50` | `30.00` | `10,000` | 长上下文（输入超过 272K）时，输入按 2 倍、输出按 1.5 倍计费 |
+
+:::info 价格说明
+文档价格为 B.AI 平台模型标准参考价，仅供基础计费说明使用。B.AI 可能会通过充值赠送及账户权益等方式，为用户提供更低的实际使用成本。具体价格、赠送积分及账户权益请以平台页面展示及最终账单为准。
+:::
diff --git a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gpt-5-5.md b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gpt-5-5.md
index 2d2af9eb..ea145d04 100644
--- a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gpt-5-5.md
+++ b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/gpt-5-5.md
@@ -39,3 +39,7 @@ GPT-5.5 是 OpenAI 于 2026 年 4 月 23 日发布的最强模型，内部代号
 | 模型名称 | 输入 (Credits/Token) | Cache Write (Credits/Token) | Cache Read (Credits/Token) | 输出 (Credits/Token) | 网页搜索（Credits/次） | 计费说明 |
 | :--- | --------------------: | --------------------------: | -------------------------: | -------------------: | ---------------------: | :--- |
 | **GPT-5.5** | `5.00` | `5.00` | `0.50` | `30.00` | `10,000` | 超过 272K 输入按 2 倍、输出按 1.5 倍计费 |
+
+:::info 价格说明
+文档价格为 B.AI 平台模型标准参考价，仅供基础计费说明使用。B.AI 可能会通过充值赠送及账户权益等方式，为用户提供更低的实际使用成本。具体价格、赠送积分及账户权益请以平台页面展示及最终账单为准。
+:::
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 a7ec90b7..e059f381 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
@@ -39,3 +39,7 @@ GPT-5-mini 是一款高效、经济的轻量级语言模型，针对日常对话
 | 模型名称 | 输入 (Credits/Token) | Cache Write (Credits/Token) | Cache Read (Credits/Token) | 输出 (Credits/Token) | 网页搜索（Credits/次） | 计费说明 |
 | :--- | --------------------: | --------------------------: | -------------------------: | -------------------: | ---------------------: | :--- |
 | **GPT-5 Mini** | `0.25` | `0.25` | `0.025` | `2.00` | `10,000` | - |
+
+:::info 价格说明
+文档价格为 B.AI 平台模型标准参考价，仅供基础计费说明使用。B.AI 可能会通过充值赠送及账户权益等方式，为用户提供更低的实际使用成本。具体价格、赠送积分及账户权益请以平台页面展示及最终账单为准。
+:::
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 5e305d60..f75512ea 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
@@ -39,3 +39,7 @@ 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
 | 模型名称 | 输入 (Credits/Token) | Cache Write (Credits/Token) | Cache Read (Credits/Token) | 输出 (Credits/Token) | 网页搜索（Credits/次） | 计费说明 |
 | :--- | --------------------: | --------------------------: | -------------------------: | -------------------: | ---------------------: | :--- |
 | **GPT-5 Nano** | `0.05` | `0.05` | `0.005` | `0.40` | `-` | - |
+
+:::info 价格说明
+文档价格为 B.AI 平台模型标准参考价，仅供基础计费说明使用。B.AI 可能会通过充值赠送及账户权益等方式，为用户提供更低的实际使用成本。具体价格、赠送积分及账户权益请以平台页面展示及最终账单为准。
+:::
diff --git a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/kimi-k2.5.md b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/kimi-k2.5.md
index b8429e0d..ea449136 100644
--- a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/kimi-k2.5.md
+++ b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/kimi-k2.5.md
@@ -45,3 +45,7 @@
 | 模型名称 | 输入 (Credits/Token) | Cache Write (Credits/Token) | Cache Read (Credits/Token) | 输出 (Credits/Token) | 网页搜索（Credits/次） | 计费说明 |
 | :--- | --------------------: | --------------------------: | -------------------------: | -------------------: | ---------------------: | :--- |
 | **Kimi K2.5** | `0.59` | `0.59` | `0.177` | `3.00` | `-` | - |
+
+:::info 价格说明
+文档价格为 B.AI 平台模型标准参考价，仅供基础计费说明使用。B.AI 可能会通过充值赠送及账户权益等方式，为用户提供更低的实际使用成本。具体价格、赠送积分及账户权益请以平台页面展示及最终账单为准。
+:::
diff --git a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/kimi-k2.6.md b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/kimi-k2.6.md
index 477b7c56..b1f75aac 100644
--- a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/kimi-k2.6.md
+++ b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/kimi-k2.6.md
@@ -44,3 +44,7 @@ Kimi K2.6 是 Moonshot AI 于 2026 年 4 月 20 日发布的开放权重多模
 | 模型名称 | 输入 (Credits/Token) | Cache Write (Credits/Token) | Cache Read (Credits/Token) | 输出 (Credits/Token) | 网页搜索（Credits/次） | 计费说明 |
 | :--- | --------------------: | --------------------------: | -------------------------: | -------------------: | ---------------------: | :--- |
 | **Kimi K2.6** | `0.95` | `0.95` | `0.16` | `4.00` | `-` | - |
+
+:::info 价格说明
+文档价格为 B.AI 平台模型标准参考价，仅供基础计费说明使用。B.AI 可能会通过充值赠送及账户权益等方式，为用户提供更低的实际使用成本。具体价格、赠送积分及账户权益请以平台页面展示及最终账单为准。
+:::
diff --git a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/minimax-m2.5.md b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/minimax-m2.5.md
index b54c09c5..cdac74f5 100644
--- a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/minimax-m2.5.md
+++ b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/minimax-m2.5.md
@@ -1,47 +1,7 @@
-# MiniMax-M2.5
+# MiniMax M2.5
 
-## 概述
+:::caution 模型已下架
+MiniMax M2.5 已在 B.AI 下架，并已从当前可用模型目录中移除。请以当前模型列表和价格总表展示的可用模型为准。
+:::
 
-**MiniMax-M2.5** 是 MiniMax 自主研发的旗舰多模态通用大模型，专为 **高吞吐、低延迟** 的生产环境设计。
-
-该模型在编程与 Agent 能力方面表现领先，可原生理解和生成多种模态内容，包括 **文本、音频、图像、视频和音乐**。M2.5 在保持顶级性能的同时大幅降低成本，特别适用于复杂任务处理与专业办公场景。
-
----
-
-## 核心特性
-
-- **领先的编程与 Agent 能力：** 在 **Multi-SWE-Bench** 基准测试中表现领先，决策能力更成熟，Token 使用效率更高  
-- **高效多模态处理：** 原生支持文本、音频、图像、视频与音乐的融合处理  
-- **超长上下文能力：** 支持 **197K Token 上下文窗口**，通过强化学习优化复杂任务拆解  
-- **高吞吐低延迟：** 提供 **100 TPS** 与 **50 TPS** 两种版本，适合高并发生产环境  
-- **办公场景增强：** 在 Word、PPT、Excel 财务建模等专业办公任务中能力显著提升  
-
----
-
-## 适用场景
-
-1. **企业自动化工作流：** 适合需要多模态处理与 Agent 决策的自动化系统  
-2. **软件开发与代码辅助：** 在大型复杂代码库中提供高效生成与调试能力  
-3. **多模态内容创作：** 支持跨模态内容生成，例如文本生成视频或图像生成音乐  
-4. **办公文档处理：** 高效处理 Word、Excel、PPT 等文档的信息提取与分析  
-
----
-
-## 能力与限制
-
-| 能力 | 说明 |
-| :--- | :--- |
-| **推理能力** | 极强。适合多步骤 Agent 任务与复杂决策 |
-| **创造能力** | 极强。擅长多模态创作与办公自动化 |
-| **多模态能力** | 原生多模态。支持文本、音频、图像、视频和音乐 |
-| **响应速度** | 极快。提供 100 TPS 与 50 TPS 高吞吐版本 |
-| **上下文窗口** | 197,000 Token |
-| **最大输出** | 131,000 Token |
-
----
-
-## 积分消耗
-
-| 模型名称 | 输入 (Credits/Token) | Cache Write (Credits/Token) | Cache Read (Credits/Token) | 输出 (Credits/Token) | 网页搜索（Credits/次） | 计费说明 |
-| :--- | --------------------: | --------------------------: | -------------------------: | -------------------: | ---------------------: | :--- |
-| **MiniMax M2.5** | `0.30` | `0.375` | `0.03` | `1.20` | `-` | - |
+如需查看当前支持的模型和价格，请访问[价格与使用说明](/zh-Hans/llmservice/pricing-and-usage/)。
diff --git a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/minimax-m2.7.md b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/minimax-m2.7.md
index 5eeabb71..ec35be91 100644
--- a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/minimax-m2.7.md
+++ b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/minimax-m2.7.md
@@ -41,3 +41,7 @@ MiniMax M2.7 是由 MiniMax（上海）开发的推理型大语言模型，于 2
 | 模型名称 | 输入 (Credits/Token) | Cache Write (Credits/Token) | Cache Read (Credits/Token) | 输出 (Credits/Token) | 网页搜索（Credits/次） | 计费说明 |
 | :--- | --------------------: | --------------------------: | -------------------------: | -------------------: | ---------------------: | :--- |
 | **MiniMax M2.7** | `0.30` | `0.375` | `0.06` | `1.20` | `-` | - |
+
+:::info 价格说明
+文档价格为 B.AI 平台模型标准参考价，仅供基础计费说明使用。B.AI 可能会通过充值赠送及账户权益等方式，为用户提供更低的实际使用成本。具体价格、赠送积分及账户权益请以平台页面展示及最终账单为准。
+:::
diff --git a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/minimax-m3.md b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/minimax-m3.md
index 8047d09a..6ab8ab50 100644
--- a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/minimax-m3.md
+++ b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/llmservice/models/minimax-m3.md
@@ -40,3 +40,7 @@ MiniMax M3 是 MiniMax M 系列的新一代大语言模型。该模型引入 Min
 | 模型名称 | 输入 (Credits/Token) | Cache Write (Credits/Token) | Cache Read (Credits/Token) | 输出 (Credits/Token) | 网页搜索（Credits/次） | 计费说明 |
 | :--- | --------------------: | --------------------------: | -------------------------: | -------------------: | ---------------------: | :--- |
 | **MiniMax M3** | `0.30` | `0.30` | `0.06` | `1.20` | `-` | - |
+
+:::info 价格说明
+文档价格为 B.AI 平台模型标准参考价，仅供基础计费说明使用。B.AI 可能会通过充值赠送及账户权益等方式，为用户提供更低的实际使用成本。具体价格、赠送积分及账户权益请以平台页面展示及最终账单为准。
+:::
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 52d6a4ee..7d1e8801 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
@@ -16,7 +16,6 @@
 | :--- | --------------------: | ------------------------: | ------------------------: | --------------------: | ---------------------: |
 | MiniMax M3 | 0.30 | 0.30 | 0.06 | 1.20 | - |
 | MiniMax M2.7 | 0.30 | 0.375 | 0.06 | 1.20 | - |
-| MiniMax M2.5 | 0.30 | 0.375 | 0.03 | 1.20 | - |
 | Kimi K2.6 | 0.95 | 0.95 | 0.16 | 4.00 | - |
 | Kimi K2.5 | 0.59 | 0.59 | 0.177 | 3.00 | - |
 | GLM-5.1 | 1.40 | 1.40 | 0.26 | 4.40 | - |
@@ -33,6 +32,7 @@
 | GPT-5 Mini | 0.25 | 0.25 | 0.025 | 2.00 | 10,000 |
 | GPT-5.4 Nano | 0.20 | 0.20 | 0.02 | 1.25 | 10,000 |
 | GPT-5 Nano | 0.05 | 0.05 | 0.005 | 0.40 | - |
+| Claude Fable 5 | 10.00 | 12.50 | 1.00 | 50.00 | 10,000 |
 | Claude Opus 4.8 | 5.00 | 6.25 | 0.50 | 25.00 | 10,000 |
 | Claude Opus 4.7 | 5.00 | 6.25 | 0.50 | 25.00 | 10,000 |
 | Claude Opus 4.6 | 5.00 | 6.25 | 0.50 | 25.00 | 10,000 |
@@ -44,6 +44,10 @@
 | Gemini 3.5 Flash | 1.50 | 1.50 | 0.15 | 9.00 | 14,000 |
 | Gemini 3 Flash | 0.50 | 0.50 | 0.05 | 3.00 | 14,000 |
 
+:::info 价格说明
+文档价格为 B.AI 平台模型标准参考价，仅供基础计费说明使用。B.AI 可能会通过充值赠送及账户权益等方式，为用户提供更低的实际使用成本。具体价格、赠送积分及账户权益请以平台页面展示及最终账单为准。
+:::
+
 ### 缓存定价说明
 
 - **缓存写入（Cache Write）：** 当 token 首次写入 Prompt Cache 时产生的消耗。大多数提供方不会额外加价，通常与标准输入价格一致。Claude 模型的缓存写入会在标准输入价格基础上增加 25%。
@@ -114,15 +118,15 @@ Plan Pro 可以升级到 Plan Max。升级时，剩余的 Plan Pro 时长会按
 
 平台采用预付费模式，因此你需要先充值才能获得 Credits。平台支持多种法币支付渠道和区块链网络，提供安全且便捷的充值体验。
 
-现在已支持法币支付。你可以按照页面提示，使用支付宝、微信支付、银联、信用卡或其他支持的支付方式完成充值。
+平台已支持完整的法币与链上充值流程。你可以按照页面提示，使用通过 Stripe 支持的银行卡/信用卡支付、微信支付、支付宝、银联等法币支付方式完成充值；也可以选择支持的区块链网络和代币进行链上支付。
 
 :::caution 安全提醒
-充值前，请确认浏览器地址栏显示的是 B.AI 官方域名，例如 `https://b.ai` 或 `https://chat.b.ai`。不要通过陌生链接、搜索广告或非官方域名页面继续操作。
+充值前，请确认浏览器地址栏显示的是 B.AI 官方访问入口，例如 `https://chat.b.ai/chat`、`https://chat.ainft.com/chat` 或 `https://chat.bankofai.io/chat`。不要通过陌生链接、搜索广告或非官方域名页面继续操作。
 
 请只在安全、可信任的网络环境下进行资金相关操作。避免在公共或共享 Wi-Fi 下充值，并在钱包确认前仔细核对支付详情。
 :::
 
-**充值流程：** 在 **Top up** 页面中，平台会根据你选择的支付方式引导你完成充值。你可以使用支付宝、微信支付、银联等法币支付方式，也可以选择支持的区块链网络和代币进行链上支付。请按照页面提示完成确认，系统会在支付成功后自动处理到账。
+**充值流程：** 在 **Top up** 页面中，平台会根据你选择的支付方式引导你完成充值。你可以使用通过 Stripe 支持的银行卡/信用卡支付、微信支付、支付宝、银联等法币支付方式，也可以选择支持的区块链网络和代币进行链上支付。请按照页面提示完成确认，系统会在支付成功后自动处理到账。
 
 **支持的支付方式：** 平台支持多种法币支付方式以及多条区块链网络上的主流代币支付。具体可用的支付渠道、网络和代币类型，请以 **Top up** 页面实时展示为准。
 
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 fdc2a4b2..a55b6afd 100644
--- a/i18n/zh-Hans/docusaurus-plugin-content-docs/current/sidebars.js
+++ b/i18n/zh-Hans/docusaurus-plugin-content-docs/current/sidebars.js
@@ -229,6 +229,7 @@ const sidebars = {
             'llmservice/models/claude-opus-4-6',
             'llmservice/models/claude-opus-4-7',
             'llmservice/models/claude-opus-4-8',
+            'llmservice/models/claude-fable-5',
             'llmservice/models/claude-sonnet-4-5',
             'llmservice/models/claude-sonnet-4-6',
             'llmservice/models/deepseek-v3.2',
diff --git a/package.json b/package.json
index e6bcfc18..9542af1a 100644
--- a/package.json
+++ b/package.json
@@ -1,6 +1,6 @@
 {
   "name": "@x402-tron/docs",
-  "version": "1.2.24",
+  "version": "1.2.25",
   "description": "x402-tron documentation",
   "license": "MIT",
   "scripts": {
diff --git a/sidebars.js b/sidebars.js
index 8f6bd6d5..322d371b 100644
--- a/sidebars.js
+++ b/sidebars.js
@@ -226,6 +226,7 @@ const sidebars = {
             'llmservice/models/claude-opus-4-6',
             'llmservice/models/claude-opus-4-7',
             'llmservice/models/claude-opus-4-8',
+            'llmservice/models/claude-fable-5',
             'llmservice/models/claude-sonnet-4-5',
             'llmservice/models/claude-sonnet-4-6',
             'llmservice/models/deepseek-v3.2',
@@ -240,7 +241,6 @@ const sidebars = {
             'llmservice/models/kimi-k2.5',
             'llmservice/models/minimax-m3',
             'llmservice/models/minimax-m2.7',
-            'llmservice/models/minimax-m2.5',
           ],
         },
         { type: 'doc', id: 'llmservice/memory', label: 'Memory' },