Vendor
Mistral AI models
19 models in the reference catalogue, vendor list prices per million tokens. 0 are routable on this deployment today.
Models
19
0 routable here
Median list price
$0.40
3:1 input to output per 1M tokens
Every Mistral AI model
Newest first. Prices are the vendor's published rates per million tokens; click a model for the full specification.
| Model | Released | Context | Input / 1M | Output / 1M | Intelligence | Capabilities |
|---|---|---|---|---|---|---|
| Mistral Medium 3.5mistralai/mistral-medium-3-5 | Apr 30, 2026 | 262K | $1.50 | $7.50 | - | reasoning tools |
| Mistral Small 4mistralai/mistral-small-2603 | Mar 16, 2026 | 262K | $0.15 | $0.60 | - | reasoning tools open weights |
| Devstral 2 2512mistralai/devstral-2512 | Dec 9, 2025 | 262K | $0.40 | $2.00 | - | tools open weights |
| Ministral 3 14B 2512mistralai/ministral-14b-2512 | Dec 2, 2025 | 262K | $0.20 | $0.20 | - | tools open weights |
| Ministral 3 8B 2512mistralai/ministral-8b-2512 | Dec 2, 2025 | 262K | $0.15 | $0.15 | - | tools open weights |
| Ministral 3 3B 2512mistralai/ministral-3b-2512 | Dec 2, 2025 | 131K | $0.10 | $0.10 | - | tools open weights |
| Mistral Large 3 2512mistralai/mistral-large-2512 | Dec 1, 2025 | 262K | $0.50 | $1.50 | 11 | tools |
| Voxtral Small 24B 2507mistralai/voxtral-small-24b-2507 | Oct 30, 2025 | 33K | $0.10 | $0.30 | - | tools open weights |
| Mistral Medium 3.1mistralai/mistral-medium-3.1 | Aug 13, 2025 | 131K | $0.40 | $2.00 | - | tools |
| Codestral 2508mistralai/codestral-2508 | Aug 1, 2025 | 256K | $0.30 | $0.90 | - | tools |
| Mistral Small 3.2 24Bmistralai/mistral-small-3.2-24b-instruct | Jun 20, 2025 | 131K | $0.07 | $0.20 | - | tools open weights |
| Mistral Medium 3mistralai/mistral-medium-3 | May 7, 2025 | 131K | $0.40 | $2.00 | - | tools |
| Mistral Small 3.1 24Bmistralai/mistral-small-3.1-24b-instruct | Mar 17, 2025 | 128K | $0.35 | $0.56 | - | open weights |
| Sabamistralai/mistral-saba | Feb 17, 2025 | 33K | $0.20 | $0.60 | - | tools |
| Mistral Small 3mistralai/mistral-small-24b-instruct-2501 | Jan 30, 2025 | 33K | $0.05 | $0.08 | - | open weights |
| Mistral Large 2407mistralai/mistral-large-2407 | Nov 19, 2024 | 131K | $2.00 | $6.00 | - | tools |
| Mistral Nemomistralai/mistral-nemo | Jul 19, 2024 | 131K | $0.02 | $0.03 | - | tools open weights |
| Mixtral 8x22B Instructmistralai/mixtral-8x22b-instruct | Apr 17, 2024 | 66K | $2.00 | $6.00 | - | tools open weights |
| Mistral Largemistralai/mistral-large | Feb 26, 2024 | 128K | $2.00 | $6.00 | - | tools |
Frequently asked
- What is the cheapest Mistral AI model?
- Mistral Nemo at $0.02 per 1M input tokens and $0.03 per 1M output tokens (vendor list price).
- Which Mistral AI model has the largest context window?
- Mistral Medium 3.5 accepts 262K tokens of context.
- How do I route to Mistral AI models with OpenSmartRoute?
- Declare a target in targets.yaml with metadata.model set to the catalogue id (for example mistralai/mistral-medium-3-5); the router scores it against every other target on cost, quality, latency and your policies for each request.
Route Mistral AI with everything else
OpenSmartRoute picks the cheapest model that meets your quality bar per request, so a Mistral AI flagship handles hard prompts while small models take the rest. Price a workload or try a routing decision live.