Mistral Large 4 Gateway
Mistral Large 4 on Vercel AI Gateway now uses updated weights with lower pricing for input, cached input, and output tokens, and the existing model ID string mistral/mistral-large-4 serves the new version without changes.
The Deploy Log | Models | Free, no signup
7 rows in The Deploy Log from 5 companies name Mistral Large 4: Vercel, Mistral, Hugging Face, Netlify and OpenRouter. They are listed from to , each by its publisher's date or, where the record carries none, its edition's date. Newest first, each linking the publisher's own page.
| Company | First row dated | Days after the first |
|---|---|---|
| OpenRouter | First | |
| Vercel | First | |
| Netlify | 7 | |
| Hugging Face | 23 | |
| Mistral | 23 |
Mistral Large 4 on Vercel AI Gateway now uses updated weights with lower pricing for input, cached input, and output tokens, and the existing model ID string mistral/mistral-large-4 serves the new version without changes.
Mistral released the weights of Mistral Large 4, a 1-trillion-parameter multimodal model, after three weeks of additional reinforcement learning. It leads open-weight coding on FrontierCode 2.0 with 19.7% and Terminal-Bench 4.0 with 41%, and scores 51% on the Artificial Analysis Cyber Index.
Mistral Large 4, a 1T-parameter MoE model with 49B active parameters and 1M context, is on Hugging Face.
TRL v1.17.0 adds LoRA fine-tuning support for Mistral Large 4 on a single 8×B300 node.
Mistral Large 4 is available in Netlify Agent Runners with a 524K-token context window.
Mistral Large 4 is available on AI Gateway via one API key, with AI SDK, OpenAI-compatible, Responses, and Anthropic Messages APIs.
Mistral Large 4 is available on OpenRouter with a 512K context window and 256K output tokens.
One line every time AI actually ships, around the clock, free on Threads and Bluesky. Every one is in The Deploy Log with its source.