StatusOperational Live status
LLMAPI discountUp to −25%
Models on LLMAPI12
From$0 / 1M blended
RegionsEU, US
Best uptime (24h)100.00%
Verdict
Mistral builds high-efficiency open-weight and commercial models, strong on price-performance and popular for European data-residency requirements. Through LLMAPI you reach 10 Mistral models on the same OpenAI-compatible endpoint as every other provider, so switching between them is a one-string change.
Good fit for
- Text Generation
- Code Generation
- Vision / Image Understanding
- Cheapest per Token
- Best Price-to-Performance
- Coding Autocomplete
Consider another provider for
- No image generation models in this catalog
- No video generation models in this catalog
- No video understanding models in this catalog
- No speech-to-text models in this catalog
Key facts
Where a provider does not document something we say so rather than guess. Everything LLMAPI records about Mistral, in one table.
Overview | |
| Provider | Mistral |
| Website | mistral.ai |
| Best for | Price-performance and EU data-residency requirements |
| Models on LLMAPI | 12 |
| Popular models | Ministral 14B, Devstral 2, Ministral 8B, Mistral Large 3, Ministral 3B, Codestral |
Access & routing | |
| API compatibility | OpenAI-compatible — /v1/chat/completions |
| Model ID prefix | mistral/<model> |
| Regions | EU, US |
| Fallback | Configurable — on 429 or 5xx the router switches to any other model or provider on your list |
| Billing | One invoice across every provider, with per-key spend limits |
| Volume discount | Eligible |
Performance (median across listed models) | |
| Blended price / 1M | $0.18 |
| Uptime (24h) | 99.99% (median across listed models) |
Modality | |
| Tags | |
Price & performance | |
| Tags | |
Workflow | |
| Tags | |
Trust & safety | |
| Tags | |
Audience | |
| Tags | |
Privacy & data | |
| Inference location | EU or US, selected per endpoint |
| Data residency | EU residency on paid tiers |
| Default retention | 30 days for abuse monitoring, then deleted |
| Zero-data retention | On request Enterprise agreements only |
| Training on API data | No Paid tiers. Free-tier terms differ |
| Human review | Flagged abuse cases only |
Compliance & lifecycle | |
| Certifications | SOC 2 Type II · ISO 27001 · GDPR DPA |
| Deprecation notice | Minimum notice published before a model is retired |
| Operational status | Operational Live status |
Prices and context from the OpenRouter public catalogue; uptime and output speed from OpenRouter provider endpoints; quality scores from LiveBench. Refreshed nightly — last updated 2026-09-29. — means no figure is published for that model.
Best Mistral models
A quick view of how Mistral 's 10 models compare on intelligence, output speed and price — so you can pick the right one for your use case.
Most intelligent
#1Mistral Embed43
#2Mistral Large 340
#3Ministral 8B30
#4Mistral Medium 329
Intelligence index · 10 models
Fastest
#1Magistral Medium412 t/s
#2Mistral Medium 3374 t/s
#3Mistral Small 3.2324 t/s
#4Mistral Large 3322 t/s
Output tokens / second · 10 models
Lowest price
#1Mistral Medium 3$2.40
#2Pixtral Large$2.95
#3Mistral Small 3.2$3.09
#4Devstral$4.06
Blended price per 1M tokens · 10 models
Compared with other hosts
How Mistral sits against the rest of the catalog, using the same measurements shown on every provider page.
- Price. Median blended price of $7.27 per 1M tokens — 19% above the $6.13 median across all 50 providers in the catalog.
- Throughput. Median output speed of 276 tokens/s, 21% slower than the 348 tok/s catalog median.
- Catalog depth. 10 models listed, against a catalog average of 5 per provider.
- Integration. Identical to every other provider here — same endpoint, same SDK, same keys, so a switch costs one string change.
Median blended price per 1M tokens
lower is better| Mistral | $7.27 | |
| Inco | $7.33 | |
| Liquid AI | $7.61 | |
| Inception | $6.82 | |
| OpenAI | $7.75 | |
| Microsoft Azure | $7.75 |
Median output speed
higher is better| Mistral | 275 tok/s | |
| Inco | 697 tok/s | |
| Liquid AI | 233 tok/s | |
| Inception | 287 tok/s | |
| OpenAI | 348 tok/s | |
| Microsoft Azure | 202 tok/s |
Figures are medians across the models listed on each provider page and are refreshed with the catalog.
Models & pricing
Every Mistral model reachable with your LLMAPI key. Click a column heading to sort.
| Model | API model name | Uptime 24h | Price / 1M | Context |
|---|---|---|---|---|
| Ministral 14B | ministral-14b-2512 | 83.07% | $ 0.2 | 262 k |
| Devstral 2 | devstral-2512 | 99.99% | $ 0.8 | 262 k |
| Ministral 8B | ministral-8b-2512 | 99.95% | $ 0.15 | 262 k |
| Mistral Large 3 | mistral-large-2512 | 100.00% | $ 0.75 | 262 k |
| Ministral 3B | ministral-3b-2512 | 100.00% | $ 0.1 | 131 k |
| Codestral | codestral-2508 | 99.96% | $ 0.45 | 256 k |
| Devstral Small 1.1 | devstral-small-2507 | — | $ 0.15 | 131 k |
| Mistral Small 3.2 | mistral-small-2506 | — | $ 0.15 | 128 k |
| Pixtral Large Latest | pixtral-large-latest | — | $ 6 | 128 k |
| Mistral Large Latest | mistral-large-latest | 100.00% | $ 6 | 128 k |
| OCR-4-0 | mistral-ocr-4-0 | — | $ 0 | — |
| OCR 4.1 | mistral-ocr-4-1 | — | $ 0 | — |
Price is a blended per-1M-token figure; latency is time to first token and throughput is output tokens per second, measured on the LLMAPI edge.
Cost calculator
Pick a model, enter your traffic, and see the monthly bill at LLMAPI rates.
Estimates use the blended per-1M-token price shown in the table above. Word counts differ by language — Cyrillic and CJK text uses 2–3× more tokens per word.
Mistral via LLMAPI
Same models, same features, one key. Prefix the model ID with mistral/ and point your OpenAI client at our base URL.
# Python · OpenAI SDK from openai import OpenAI client = OpenAI( base_url="https://api.llmapi.ai/v1", api_key="LLMAPI_KEY", ) r = client.chat.completions.create( model="mistral/mistral-large-3", messages=[{"role": "user", "content": "Hello"}], )
| Pricing | Eligible for LLMAPI volume discounts; billed on one invoice with every other provider. |
| Features | Full pass-through — tool calling, JSON schema, streaming, vision and reasoning behave exactly as on Mistral’s own API. |
| Fallback | Configurable. On 429 or 5xx the router switches to any model or provider on your fallback list. |
| Regions | EU, US |
| Your data | LLMAPI stores request metadata only — model, token counts, latency and status. No prompt or completion content. |
Capabilities & use cases
Each tag below is its own catalog page listing every provider that shares it.
Developer resources
Where to go next.
Join thousands of developers building on one API key
Every provider in the catalog, one key, one invoice.
Questions
How do I call Mistral models through LLMAPI?
Point any OpenAI-compatible client at https://api.llmapi.ai/v1 and use the model ID mistral/mistral-large-3. No other change is needed.
Does Mistral cost more through LLMAPI?
No. This provider is eligible for LLMAPI volume discounts, so heavy usage lands below list price.
Which regions are used?
EU, US
What happens if the provider returns an error?
On 429 or 5xx responses the router falls back to any other model or provider on your configured list, so requests keep succeeding.
How many Mistral models are available?
10 at the moment, all listed in the models table above and updated as the provider ships new ones.
Related providers
Providers covering similar use cases.