Balanced Mistral model for enterprise assistants, multilingual work, and tools
Mistral Medium 3.5 is offered by 14 providers on this page. Public prices are shown for 12 of them. Its official list price is $1.50 per 1M input tokens and $7.50 per 1M output tokens. The lowest paid channel is NanoGPT at $1.50 / $7.50 per 1M, about 1.4× below the list price. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it. It also has 1 free ($0) channel; free tiers usually carry rate limits, and subscription-covered access bills $0 per token only after the subscription fee.
Artificial Analysis rates it 14.2 on the Intelligence Index, with 46.9 for coding and 7 for agentic tasks. Against its lowest blended price of $3.00 per 1M, that is roughly 5 index points per dollar, which is the value ratio the leaderboards rank on. Median output speed is 166 tokens per second, with 2.19s to the first token. Running one task of the Artificial Analysis suite costs about $0.5020, which reflects how many tokens its reasoning consumes rather than the unit price alone.
The context window is 262,144 tokens at the reference host, but hosts report different limits, from 256,000 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, Image, and PDF. 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.
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 |
|---|---|---|---|---|---|---|---|---|
| Nvidia mistralai/mistral-medium-3.5-128b | Cloud | Free | — | — | 262,144 | 32,768 | deprecated | |
| NanoGPT mistralai/mistral-medium-3.5 | Gateway | $1.50 | $7.50 | $0.75 | — | 256,000 ⚠ | 32,768 | |
| OpenRouter mistralai/mistral-medium-3-5 | Gateway | $1.50 | $7.50 | — | — | 262,144 | 209,715 | |
| Pioneer mistral-medium-3.5 | Gateway | $1.50 | $7.50 | $1.50 | $1.50 | 256,000 ⚠ | 131,072 | |
| Eden AI | Gateway | $1.50 | $7.50 | $0.15 | — | 262,144 | 262,144 | |
| Tempr Gateway | Gateway | $1.50 | $7.50 | — | — | 262,144 | 262,144 | |
| MistralOfficial | First-party | $1.50 | $7.50 | $0.15 | — | 262,144 | 262,144 | |
| DevPass (LLM Gateway) mistral-medium-3-5 | Gateway | $1.50 | $7.50 | — | — | 262,144 | 262,144 | |
| Kilo Gateway mistralai/mistral-medium-3-5 | Gateway | $1.50 | $7.50 | — | — | 262,144 | 209,715 | |
| evroc mistralai/Mistral-Medium-3.5-128B | Cloud | $1.73 | $6.90 | — | — | 262,144 | 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 1 of 14 providers.
1 / 14 providers expose no reasoning control (reasoning_options: []).
1 more channels offer $0 (Nvidia); free tiers usually have rate limits and no SLA, excluded from ranking.
| Name | Conditions | Score | Metric | Source |
|---|---|---|---|---|
| SWE-Bench Verified | — | 77.6 | resolved | Source ↗ |
| τ³-Telecom | variant: public preview | 91.4 | accuracy | 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.