Fast Mistral production model for chat, extraction, and cost-sensitive agents
Mistral Small 4 is offered by 14 providers on this page. Its official list price is $0.15 per 1M input tokens and $0.60 per 1M output tokens. The lowest paid channel is EmpirioLabs AI at $0.15 / $0.60 per 1M, about 3.9× below the list price. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it.
Artificial Analysis rates it 11.3 on the Intelligence Index, with 26.6 for coding and 0.8 for agentic tasks. Against its lowest blended price of $0.263 per 1M, that is roughly 43 index points per dollar, which is the value ratio the leaderboards rank on. Median output speed is 177 tokens per second, with 0.68s to the first token. Running one task of the Artificial Analysis suite costs about $0.0150, which reflects how many tokens its reasoning consumes rather than the unit price alone.
The context window is 256,000 tokens at the reference host, but hosts report different limits, from 32,000 to 262,144, so the usable window depends on the provider you pick. It supports reasoning, tool use, and structured output. Accepted input modalities are Text and Image. The weights are open, so it can also be self-hosted or served through a gateway of your choice. Providers report the capability flags inconsistently, so verify a specific feature against the host you plan to use. Its training knowledge cuts off at 2025-06.
Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| EmpirioLabs AI mistral-small-4 | Gateway | $0.15 | $0.60 | $0.15 | — | 256,000 | 65,536 | |
| Kilo Gateway | Gateway | $0.15 | $0.60 | $0.015 | — | 262,144 ⚠ | 209,715 | |
| OpenRouter | Gateway | $0.15 | $0.60 | $0.015 | — | 262,144 ⚠ | 209,715 | |
| Pioneer mistralai/Mistral-Small-4-119B-2603 | Gateway | $0.15 | $0.60 | $0.015 | $0.15 | 32,000 ⚠ | 32,000 | |
| Eden AI | Gateway | $0.15 | $0.60 | $0.015 | — | 262,144 ⚠ | 256,000 | |
| Tempr Gateway | Gateway | $0.15 | $0.60 | — | — | 256,000 | 256,000 | |
| MistralOfficial | First-party | $0.15 | $0.60 | $0.015 | — | 256,000 | 256,000 | |
| DevPass (LLM Gateway) | Gateway | $0.15 | $0.60 | — | — | 262,144 ⚠ | 256,000 | |
| LLM Gateway | Gateway | $0.15 | $0.60 | — | — | 262,144 ⚠ | 256,000 | |
| Cortecs | Gateway | $0.16 | $0.63 | $0.016 | — | 262,144 ⚠ | 256,000 | |
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 3 of 14 providers.
4 / 14 providers expose no reasoning control (reasoning_options: []).
| Name | Conditions | Score | Metric | Source |
|---|---|---|---|---|
| Artificial Analysis Coding Index | — | 24.3 | index | Source ↗ |
| SciCode | — | 38 | percent correct | Source ↗ |
| Terminal-Bench Hard | — | 17.4 | success rate | Source ↗ |
The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.
Individual evaluations run by Artificial Analysis, on the same reasoning tier as the intelligence score above. Each benchmark has its own task set and harness, so rows are not comparable with one another. The Intelligence Index above draws on a different, newer set of evaluations.