Model family
Mistral on FlexAI.Every variant. One key
Mistral is Mistral's open model line on FlexAI. One variant runs serverless on the OpenAI-compatible API, with 13 more available as dedicated endpoints, spanning chat, multimodal, transcription, audio, code. One API key serves every variant.
Variants
Every served variant in the family, with live serverless pricing.
Serverless · pay per token
| Model | Context | Price | Status |
|---|---|---|---|
| Mistral Nemo | 32K | $0.018 / $0.03 per M | Serving |
Dedicated endpoints · reserved GPUs
| Model | Context | Price | Status |
|---|---|---|---|
| Mistral Medium 3.5 | 256K | Dedicated | Dedicated |
| Devstral 2 123B Instruct | 256K | Dedicated | Dedicated |
| Mistral Small 4 119B | 256K | Dedicated | Dedicated |
| Voxtral Small 24B | 128K | Dedicated | Dedicated |
| Mistral Small 3.2 24B Instruct | 128K | Dedicated | Dedicated |
| Devstral Small 2 24B Instruct | 384K | Dedicated | Dedicated |
| Mistral Small 3.1 24B | 128K | Dedicated | Dedicated |
| Ministral 3 14B Instruct | 256K | Dedicated | Dedicated |
| Ministral 3 8B Instruct | 256K | Dedicated | Dedicated |
| Mistral 7B Instruct v0.2 | 128K | Dedicated | Dedicated |
| Voxtral Mini 4B Realtime | 128K | Dedicated | Dedicated |
| Voxtral 4B TTS | — | Dedicated | Dedicated |
| Ministral 3 3B Instruct | 256K | Dedicated | Dedicated |
Which variant for what
Pick by the role you're filling. Same key for all of them.
Mistral Nemo runs execute steps in workflow automation
Call the flagship
OpenAI-compatible. Swap the model id for any variant above.
curl https://tokens.flex.ai/v1/chat/completions \
-H "Authorization: Bearer $FLEXAI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "Mistral-Nemo-Instruct-2407-FP8",
"messages": [{"role": "user", "content": "Hello from FlexAI"}]
}'Where it runs
Use cases that put Mistral to work in a pipeline.
Run Mistral on one API key
Every Mistral variant, serverless and dedicated, behind one OpenAI-compatible key.
$10/month in free credits for your first 3 months