0 Fork 0

mirror of https://github.com/langchain-ai/langchain.git synced 2026-10-05 09:25:14 +03:00

Files

T

langchain-oss-model-profiles[bot]andmdrxy 89baaec5fe chore(model-profiles): refresh model profile data (#40217 )

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

**6 added · 2 removed · 9 changed** across 4 provider(s).

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

**➕ 1 added**
- `accounts/fireworks/models/qwen3p8-2p4t-a95b` — 262,144 ctx, 131,072
out, reasoning, tools

</details>

<details>
<summary>openai</summary>

**➕ 1 added**
- `gpt-6-astra` — 1,050,000 ctx, 128,000 out, text+image+pdf in,
reasoning, tools

</details>

<details>
<summary>openrouter</summary>

**➕ 4 added**
- `inclusionai/ling-3.0-flash-sante:free` — 262,144 ctx, 32,768 out,
reasoning, tools
- `openai/gpt-6-astra` — 1,050,000 ctx, 128,000 out, text+image+pdf in,
reasoning, tools
- `openai/gpt-6-astra-pro` — 1,050,000 ctx, 128,000 out, text+image+pdf
in, reasoning, tools
- `qwen/qwen3.8-max-0902` — 1,000,000 ctx, 131,072 out, text+image+video
in, reasoning, tools

**➖ 2 removed**
- `ibm-granite/granite-4.1-8b`
- `qwen/qwen3.8-max`

**✏️ 6 changed**
- `inclusionai/ling-3.0-flash`: display name `Ling-3.0-flash` → `Ling
3.0 Flash`
- `qwen/qwen3-235b-a22b-2507`: max output tokens 235,929 → 16,384
- `qwen/qwen3.5-35b-a3b`: max output tokens 235,929 → 16,384
- `qwen/qwen3.6-27b`: max output tokens 235,929 → 65,536
- `thedrummer/unslopnemo-12b`: max output tokens 26,214 → 819,200
- `~deepseek/deepseek-v4-flash-latest`: max output tokens 393,216 →
131,072

</details>

<details>
<summary>xai</summary>

**✏️ 3 changed**
- `grok-imagine-image`: max input tokens 8,000 → 16,000
- `grok-imagine-image-2.0`: max input tokens 8,000 → 64,000
- `grok-imagine-image-quality`: max input tokens 8,000 → 16,000

</details>

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

2026-09-06 15:33:28 -04:00

langchain_xai

chore(model-profiles): refresh model profile data (#40217 )

2026-09-06 15:33:28 -04:00

scripts

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

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

tests

fix(xai): recompute total_tokens after adding reasoning tokens to output (#39667 )

2026-08-18 13:19:28 -04:00

LICENSE

partners: add xAI chat integration (#28032 )

2024-11-12 15:11:29 -05:00

Makefile

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

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

pyproject.toml

release(xai): 1.3.0 (#38984 )

2026-07-21 12:11:24 -04:00

README.md

docs: refresh README installation and resources (#38119 )

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

uv.lock

chore: bump aiohttp from 3.14.1 to 3.14.3 in /libs/partners/xai (#39241 )

2026-08-04 17:10:44 -07:00

README.md

langchain-xai

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

Quick Install

uv add langchain-xai

🤔 What is this?

This package contains the LangChain integrations for xAI through their APIs.

📖 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