Skip to content

feat: Add Infinity provider #693

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
Marviel wants to merge 1 commit into
base: dev
Choose a base branch
from
Open

feat: Add Infinity provider #693

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 3 additions & 0 deletions providers/infinity/logo.svg
View file
Open in desktop
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
23 changes: 23 additions & 0 deletions providers/infinity/models/QuantTrio/DeepSeek-V3.2-AWQ.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,23 @@
# DeepSeek-V3.2-AWQ - High-performance MoE model
name = "DeepSeek-V3.2-AWQ"
description = "A next-generation open language model that balances strong reasoning, efficient long-context processing and everyday agent tasks with high performance and practical inference efficiency"
family = "deepseek"
release_date = "2025-10-01"
last_updated = "2026-01-15"
attachment = false
reasoning = true
temperature = true
tool_call = true
open_weights = true

[cost]
input = 0.28
output = 0.42

[limit]
context = 32_768
output = 16_384

[modalities]
input = ["text"]
output = ["text"]
28 changes: 28 additions & 0 deletions providers/infinity/models/QuantTrio/GLM-4.7-AWQ.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,28 @@
# GLM-4.7-AWQ - 358B parameter reasoning model
name = "GLM-4.7-AWQ"
description = "GLM 4.7 with AWQ quantization (358B params)"
family = "glm"
release_date = "2025-12-22"
last_updated = "2026-01-15"
knowledge = "2025-04"
attachment = false
reasoning = true
temperature = true
tool_call = true
open_weights = true

[interleaved]
field = "reasoning_content"

[cost]
input = 0.40
output = 1.50
cache_read = 0.20

[limit]
context = 65_536
output = 16_384

[modalities]
input = ["text"]
output = ["text"]
26 changes: 26 additions & 0 deletions providers/infinity/models/nvidia/Kimi-K2-Thinking-NVFP4.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,26 @@
# Kimi-K2-Thinking-NVFP4 - Moonshot's reasoning model in NVFP4 format
name = "Kimi-K2-Thinking-NVFP4"
description = "Built for long documents and deep analysis, Kimi K2 excels at reading, summarization, and multi-step reasoning across massive contexts."
family = "kimi-thinking"
release_date = "2025-11-06"
last_updated = "2026-01-15"
attachment = false
reasoning = true
temperature = true
tool_call = true
open_weights = true

[interleaved]
field = "reasoning_content"

[cost]
input = 0.40
output = 1.75

[limit]
context = 32_768
output = 32_768

[modalities]
input = ["text"]
output = ["text"]
23 changes: 23 additions & 0 deletions providers/infinity/models/openai/gpt-oss-120b.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,23 @@
# GPT-OSS-120B - OpenAI's open-source reasoning model
name = "GPT-OSS-120B"
description = "A large-scale open model designed for high-quality general intelligence. Ideal for advanced reasoning, rich text generation, and enterprise-grade applications."
family = "gpt-oss"
release_date = "2025-08-05"
last_updated = "2026-01-15"
attachment = false
reasoning = true
temperature = true
tool_call = true
open_weights = true

[cost]
input = 0.04
output = 0.19

[limit]
context = 32_768
output = 16_384

[modalities]
input = ["text"]
output = ["text"]
6 changes: 6 additions & 0 deletions providers/infinity/provider.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,6 @@
name = "Infinity"
env = ["INFINITY_API_KEY"]
npm = "@ai-sdk/openai-compatible"
api = "https://api.infinity.inc/v1"
doc = "https://infinity.inc/docs"

Loading