Short answer
TeamoRouter hasn't launched Mistral Large 4 yet. If you want an open-weight model for coding and agent work with a TeamoRouter key today, use one of these:
glm-5.3: Z.ai GLM-5.3 (model page)kimi-k3.1-pro: Moonshot AI Kimi K3.1 Pro (model page)deepseek-flash-1017: DeepSeek V4.1 Flash 1017 (model page)
All three have a 1M-token context window on TeamoRouter. GLM-5.3, Kimi K3 and DeepSeek V4.1 Flash 1017 are the open-weight models Mistral compares Large 4 against in its own announcement.
To follow its launch on TeamoRouter, or vote for it, see the Mistral Large 4 API page.
About Mistral Large 4 itself: Mistral released it in public preview on October 6, 2026 and published the open weights on October 29, 2026. It is a Mixture-of-Experts model with 1.05T total and 52B active parameters, takes text and images, and has a 1M-token context window. On Mistral's API the model ID is mistral-large-4 and the price is $0.70 per million input tokens, $0.07 cached input and $2.10 output.
New accounts start with a $0 balance — top up before your first request. Top up from $5. If a request returns 402 (400 on the OpenAI format) with "wallet balance is insufficient", your balance is empty — your base URL and key are fine. Top up and retry.
Specs at a glance
From Mistral's model page and announcement:
| Mistral Large 4 | |
|---|---|
| Model ID (Mistral API) | mistral-large-4 (version 26.10) |
| Released | Public preview October 6, 2026; open weights October 29, 2026 |
| Architecture | Mixture-of-Experts: 1.05T total parameters, 52B active, 1.6B vision encoder |
| Input / output | Text and images in, text out |
| Context window | 1M tokens |
| Reasoning modes | low (replaces "none"), medium, high (default) |
| Mistral API features | Chat Completions, Conversations and Agents, Batch, function calling, structured outputs |
| Weights | Hugging Face: mistralai/Mistral-Large-4-1T-A52B, for vLLM or SGLang |
| License | Mistral Ecosystem Open-Weight License |
Mistral recommends low for simple tasks, medium for everyday tasks and high for the hardest work that needs precise, thorough reasoning.
Price
| Per 1M tokens | Mistral API |
|---|---|
| Input | $0.70 |
| Cached input | $0.07 |
| Output | $2.10 |
These are the prices Mistral announced on October 29, 2026. OpenRouter lists the model as mistralai/mistral-large-4-0 with the same $0.70 / $2.10.
TeamoRouter bills per token with no subscription. Current prices for glm-5.3, kimi-k3.1-pro and deepseek-flash-1017 are on the pricing page.
What Mistral says it's good at
Mistral positions Large 4 for agentic coding and defensive cybersecurity. In the announcement it reports that the model leads open-weight models on Cognition's FrontierCode 2.0 (19.7%) and on Terminal-Bench, and matches the best open-weight models on the Artificial Analysis Coding Agent Index while using fewer tokens. These are Mistral's own figures.
The license is a modified MIT license: you can use, modify, fine-tune and commercialize the model, but a business that runs a Model-as-a-Service offering needs a separate commercial license from Mistral.
Use an open-weight alternative on TeamoRouter now
The TeamoRouter base URL is OpenAI-compatible, so the same request works for each model above. Change only model:
curl https://api.teamorouter.com/v1/chat/completions \
-H "Authorization: Bearer YOUR_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "glm-5.3",
"messages": [{"role": "user", "content": "Find the bug in this function and suggest a fix: ..."}]
}'
We sent this request with glm-5.3, kimi-k3.1-pro and deepseek-flash-1017 to the TeamoRouter gateway on November 2, 2026. In coding agents, set the model name in the tool's config: Claude Code with Kimi K3.1 Pro, DeepSeek V4.1 Flash API, Codex CLI guide, OpenCode guide.
Paying for usage
No subscription: you top up a balance from $5 and pay only for the tokens you use, by card or with USDT, USDC or ETH from any exchange app or wallet (how to pay with USDT). The same key also works for Claude, GPT and Gemini.
FAQ
Is Mistral Large 4 open source?
It is open weight. The weights are on Hugging Face under the Mistral Ecosystem Open-Weight License, which Mistral describes as a modified MIT license. It is free to use, modify, fine-tune and commercialize, except that Model-as-a-Service providers need a separate commercial license.
How much does Mistral Large 4 cost?
On Mistral's API, $0.70 per million input tokens, $0.07 per million cached input tokens and $2.10 per million output tokens.
Can I use Mistral Large 4 on TeamoRouter?
Not yet. glm-5.3, kimi-k3.1-pro and deepseek-flash-1017 are available now with the same key. The models that are live are listed on the models page.
Can I run it myself?
Yes. Mistral publishes the weights on Hugging Face and points to vLLM and SGLang for self-hosting. With 1.05T total parameters, it needs multi-GPU server hardware.