Mistral Large 4
by NanoGPT · family mistral-large · listed Oct 2026RTV
Mistral's 1T-parameter multimodal MoE for reasoning, coding, and agentic work
Current rates USD per 1M tokens
Input$0.68
Output$2.09
Cache read$0.07
Cache write—
Against the market
On the record
- Model id
mistralai/mistral-large-4- Context window
- 524K tokens
- Max output
- 262K tokens
- Input modalities
- text, image
- Output modalities
- text
- Reasoning
- yes
- Tool calls
- yes
- Open weights
- no
- Knowledge cutoff
- —
- Released
- 2026-10-06
- Last updated
- 2026-10-06
- Provider docs
- docs.nano-gpt.com
Back of the envelope
≈
Also listed at
- Vercel AI Gateway$0.68 in · $2.09 out
- OpenCode Zen$0.68 in · $2.09 out
- Requesty$0.68 in · $2.09 out
- Mistral$0.68 in · $2.09 out
- LLM Gateway$1.36 in · $4.18 out
- DevPass (LLM Gateway)$1.36 in · $4.18 out