Mistral's 1T-parameter multimodal MoE for reasoning, coding, and agentic workQuality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| Standard Compute mistralai/mistral-large-4-0 | Gateway | $0.68 | $2.09 | $0.07 | — | 1,048,576 | 50,000 | |
| Ollama Cloud | Cloud | $0.68 | $2.09 | $0.07 | — | 1,048,576 | 262,144 | |
| Requesty mistral-large-4@eu | Gateway | $0.68 | $2.09 | $0.07 | — | 524,288 ⚠ | 262,144 | |
| Requesty | Gateway | $0.68 | $2.09 | $0.07 | — | 524,288 ⚠ | 262,144 | |
| OpenCode | Gateway | $0.68 | $2.09 | $0.07 | — | 524,288 ⚠ | 262,144 | |
| NanoGPT | Gateway | $0.68 | $2.09 | $0.07 | — | 524,288 ⚠ | 262,144 | |
| MistralOfficial mistral-large-4-0-8 | First-party | $0.70 | $2.10 | $0.07 | — | 1,048,576 | 262,144 | beta |
| MistralOfficial mistral-large-latest | First-party | $0.70 | $2.10 | $0.07 | — | 1,048,576 | 262,144 | beta |
| MistralOfficial | First-party | $0.70 | $2.10 | $0.07 | — | 1,048,576 | 262,144 | beta |
| Vercel AI Gateway | Cloud | $0.70 | $2.10 | $0.07 | — | 1,048,576 | 262,144 |
Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.
Interleaved thinking (reasoning between tool calls) is declared by 2 of 19 providers.
1 / 19 providers expose no reasoning control (reasoning_options: []).
Individual evaluations run by Artificial Analysis, on the same reasoning tier as the intelligence score above. Each benchmark has its own task set and scale (percent correct, points or an index), so rows are not comparable with one another.