0 Fork 0

mirror of https://github.com/langchain-ai/langchain.git synced 2026-10-05 17:35:28 +03:00

Files

T

History

langchain-oss-model-profiles[bot]andmdrxy 39701d6b8e chore(model-profiles): refresh model profile data (#39050 )

Automated refresh of model profile data for all in-monorepo partner
integrations via `langchain-profiles refresh`.

🤖 Generated by the [`refresh_model_profiles`
workflow](https://github.com/langchain-ai/langchain/blob/master/.github/workflows/refresh_model_profiles.yml).


## Summary of changes

**4 added · 2 removed · 31 changed** across 4 provider(s).

<details>
<summary>fireworks-ai</summary>

**✏️ 1 changed**
- `accounts/fireworks/models/minimax-m3`: added image input; added video
input

</details>

<details>
<summary>openai</summary>

**➖ 2 removed**
- `o3-deep-research`
- `o4-mini-deep-research`

**✏️ 17 changed**
- `gpt-3.5-turbo`: status unset → `deprecated`
- `gpt-4`: status unset → `deprecated`
- `gpt-4-turbo`: status unset → `deprecated`
- `gpt-4.1-nano`: status unset → `deprecated`
- `gpt-4o-2024-05-13`: status unset → `deprecated`
- `gpt-5-chat-latest`: removed attachments; audio input no → unset;
audio output no → unset; removed image input; image output no → unset;
last updated `2025-08-07` → unset; max output tokens 128,000 → unset;
display name `GPT-5 Chat (latest)` → unset; open weights no → unset;
removed reasoning; release date `2025-08-07` → unset; removed structured
output; removed temperature control; removed text input; removed text
output; tool calling no → unset; video input no → unset; video output no
→ unset
- `gpt-5-codex`: attachments no → unset; audio input no → unset; audio
output no → unset; removed image input; image output no → unset; last
updated `2025-09-15` → unset; max output tokens 128,000 → unset; display
name `GPT-5-Codex` → unset; open weights no → unset; removed reasoning;
release date `2025-09-15` → unset; removed structured output;
temperature control no → unset; removed text input; removed text output;
removed tool calling; video input no → unset; video output no → unset
- `gpt-5.1-chat-latest`: removed attachments; audio input no → unset;
audio output no → unset; removed image input; image output no → unset;
last updated `2025-11-13` → unset; max output tokens 16,384 → unset;
display name `GPT-5.1 Chat` → unset; open weights no → unset; removed
reasoning; release date `2025-11-13` → unset; removed structured output;
temperature control no → unset; removed text input; removed text output;
removed tool calling; video input no → unset; video output no → unset
- `gpt-5.1-codex`: removed attachments; audio input no → unset; audio
output no → unset; removed image input; image output no → unset; last
updated `2025-11-13` → unset; max output tokens 128,000 → unset; display
name `GPT-5.1 Codex` → unset; open weights no → unset; removed
reasoning; release date `2025-11-13` → unset; removed structured output;
temperature control no → unset; removed text input; removed text output;
removed tool calling; video input no → unset; video output no → unset
- `gpt-5.1-codex-max`: removed attachments; audio input no → unset;
audio output no → unset; removed image input; image output no → unset;
last updated `2025-11-13` → unset; max output tokens 128,000 → unset;
display name `GPT-5.1 Codex Max` → unset; open weights no → unset;
removed reasoning; release date `2025-11-13` → unset; removed structured
output; temperature control no → unset; removed text input; removed text
output; removed tool calling; video input no → unset; video output no →
unset
- `gpt-5.1-codex-mini`: removed attachments; audio input no → unset;
audio output no → unset; removed image input; image output no → unset;
last updated `2025-11-13` → unset; max output tokens 128,000 → unset;
display name `GPT-5.1 Codex mini` → unset; open weights no → unset;
removed reasoning; release date `2025-11-13` → unset; removed structured
output; temperature control no → unset; removed text input; removed text
output; removed tool calling; video input no → unset; video output no →
unset
- `gpt-5.2-codex`: removed attachments; audio input no → unset; audio
output no → unset; removed image input; image output no → unset; last
updated `2025-12-11` → unset; max input tokens 400,000 → unset; max
output tokens 128,000 → unset; display name `GPT-5.2 Codex` → unset;
open weights no → unset; removed reasoning; release date `2025-12-11` →
unset; removed structured output; temperature control no → unset;
removed text input; removed text output; removed tool calling; video
input no → unset; video output no → unset
- `gpt-image-1`: status unset → `deprecated`
- `o1`: status unset → `deprecated`
- `o1-pro`: status unset → `deprecated`
- `o3-mini`: status unset → `deprecated`
- `o4-mini`: status unset → `deprecated`

</details>

<details>
<summary>openrouter</summary>

**➕ 3 added**
- `anthropic/claude-opus-5` — 1,000,000 ctx, 128,000 out, text+image+pdf
in, reasoning, tools
- `anthropic/claude-opus-5-fast` — 1,000,000 ctx, 128,000 out,
text+image+pdf in, reasoning, tools
- `inclusionai/ling-3.0-flash:free` — 262,144 ctx, 32,768 out,
reasoning, tools

**✏️ 13 changed**
- `arcee-ai/trinity-large-thinking`: max output tokens 80,000 → 262,144
- `deepseek/deepseek-v4-flash`: max output tokens 65,536 → 393,216
- `google/gemini-3.1-flash-lite-image`: max output tokens 65,536 →
66,000; display name `Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)`
→ `Nano Banana 2 Lite`
- `google/gemma-4-26b-a4b-it`: max output tokens 16,384 → 262,144
- `google/lyria-3-clip-preview`: last updated `2026-03-30` →
`2026-03-25`; release date `2026-03-30` → `2026-03-25`
- `google/lyria-3-pro-preview`: last updated `2026-03-30` →
`2026-03-25`; release date `2026-03-30` → `2026-03-25`
- `meta-llama/llama-3.2-3b-instruct`: max output tokens 80,000 → 131,072
- `qwen/qwen3-14b`: max output tokens 16,384 → 8,192
- `qwen/qwen3-vl-30b-a3b-instruct`: max output tokens 32,768 → 16,384
- `qwen/qwen3.5-27b`: max output tokens 81,920 → 65,536
- `tencent/hy3`: max output tokens 262,144 → 128,000
- `thinkingmachines/inkling`: max input tokens 524,288 → 1,048,576
- `z-ai/glm-4.7-flash`: max output tokens 131,072 → 16,384

</details>

<details>
<summary>xai</summary>

**➕ 1 added**
- `grok-imagine-video-1.5` — 1,024 ctx, text+image+pdf in

</details>

Co-authored-by: mdrxy <61371264+mdrxy@users.noreply.github.com>

2026-07-26 21:24:00 -04:00

langchain_openai

chore(model-profiles): refresh model profile data (#39050 )

2026-07-26 21:24:00 -04:00

scripts

refactor(openai): mark Codex OAuth classes private (#38122 )

2026-06-12 22:19:40 -04:00

tests

feat(anthropic,fireworks,openai): support langsmith gateway through env var (#38742 )

2026-07-23 15:49:06 -04:00

.gitignore

openai: audio modality, remove sockets from unit tests (#27436 )

2024-10-18 08:02:09 -07:00

LICENSE

openai[minor]: implement langchain-openai package (#15503 )

2024-01-05 15:03:28 -08:00

Makefile

feat(core,partners): add package version tracking to tracing metadata (#35295 )

2026-06-11 02:23:19 -04:00

pyproject.toml

release(openai): 1.4.1 (#39045 )

2026-07-23 16:24:24 -04:00

README.md

docs: refresh README installation and resources (#38119 )

2026-06-12 17:38:22 -04:00

uv.lock

release(openai): 1.4.1 (#39045 )

2026-07-23 16:24:24 -04:00

README.md

langchain-openai

Looking for the JS/TS version? Check out LangChain.js.

Quick Install

uv add langchain-openai

🤔 What is this?

This package contains the LangChain integrations for OpenAI through their openai SDK.

📖 Documentation

For full documentation, see the API reference. For conceptual guides, tutorials, and examples on using these classes, see the LangChain Docs.

📕 Releases & Versioning

See our Releases and Versioning policies.

💁 Contributing

As an open-source project in a rapidly developing field, we are extremely open to contributions, whether it be in the form of a new feature, improved infrastructure, or better documentation.

For detailed information on how to contribute, see the Contributing Guide.

Resources

LangChain Academy — comprehensive, free courses on LangChain libraries and products, made by the LangChain team
Code of Conduct — community guidelines and standards