providers/Mistral
Mistral · Paris, France

Mistral models on AIgateway — pricing, context, capabilities

Mistral ships 8 models on AIgateway spanning audio-stt, audio-tts, moderation, text. Call any of them via the OpenAI-compatible endpoint at api.aigateway.sh/v1 with one key. Pass-through inference pricing plus a 5% platform fee at credit top-up. No per-call markups, no seat fees, no minimum.

Get your key →See pricingVisit Mistral →
models · 8modalities · audio-stt, audio-tts, moderation, textlocation · Paris, France
audio-stt

Mistral audio-stt models

2 audio-stt models from Mistral.

Voxtral Mini Transcribe Realtime
mistral/voxtral-mini-transcribe-realtime-26-02
Voxtral Mini Transcribe Realtime (Feb 2026) — streaming ASR.
$0.0080 / min
Voxtral Mini Transcribe
mistral/voxtral-mini-transcribe-26-02
Voxtral Mini Transcribe (Feb 2026) — Mistral ASR.
$0.0060 / min
audio-tts

Mistral audio-tts models

1 audio-tts model from Mistral.

Voxtral TTS
mistral/voxtral-tts-26-03
Voxtral TTS (Mar 2026) — Mistral multilingual speech synthesis.
$12.0000 / 1k chars
moderation

Mistral moderation models

1 moderation model from Mistral.

Mistral Moderation 2
mistral/mistral-moderation-26-03
Mistral's policy-aware moderator. Returns per-category scores.
$0.00010 / req
text

Mistral text models

4 text models from Mistral.

Mistral Small 4
mistral/mistral-small-4-0-26-03
Mistral Small 4 (Mar 2026) — compact frontier-class text model.
$0.200 in · $0.600 out / 1M131,072 ctx
Mistral-Small-3.1-24b-Instruct
mistralai/mistral-small-3.1-24b-instruct
Building upon Mistral Small 3 (2501), Mistral Small 3.1 (2503) adds state-of-the-art vision understanding and enhances long context capabilities up to 128k tokens without compromising text performance. With 24 billion parameters, this model achieves top-tier capabilities in both text and vision tasks.
$0.350 in · $0.550 out / 1M128,000 ctx
Mistral-7b-Instruct-V0.2-Lora
mistral/mistral-7b-instruct-v0.2-lora
The Mistral-7B-Instruct-v0.2 Large Language Model (LLM) is an instruct fine-tuned version of the Mistral-7B-v0.2.
$0.050 in · $0.100 out / 1M15,000 ctx
Mistral-7b-Instruct-V0.1
mistral/mistral-7b-instruct-v0.1
Instruct fine-tuned version of the Mistral-7b generative text model with 7 billion parameters
$0.110 in · $0.190 out / 1M2,824 ctx
About Mistral

Who they are, what they focus on

Mistral AI is a French lab building efficient open-weight and commercial models. Mistral Small 3.1 is a strong vision-capable mid-tier; Voxtral handles speech; Mistral Moderation covers 9-category content safety.

Headquartered in Paris, France. Homepage: mistral.ai.

FAQ

Common questions about Mistral on AIgateway

Which Mistral models does AIgateway support?
AIgateway routes 8 Mistral models including Voxtral TTS. Full catalog with pricing and context windows is in the sections above.
How do I call a Mistral model from my code?
Point the OpenAI SDK at https://api.aigateway.sh/v1 with your AIgateway key and set model to the Mistral slug (e.g. "mistral/voxtral-tts-26-03"). Request and response shapes are identical to OpenAI.
How much do Mistral models cost on AIgateway?
Pass-through Mistral pricing plus a 5% platform fee applied at credit top-up, not per call. No seat fees, no minimum beyond the $5 top-up floor.
Can I bring my own Mistral API key (BYOK)?
Yes. Attach your Mistral key in the AIgateway dashboard. Calls to Mistral models flip to pass-through and AIgateway waives the 5% platform fee on those calls.
Where is Mistral based?
Mistral is headquartered in Paris, France.
Is there a free tier?
AIgateway's free tier is 100 requests/day on Kimi K2.6 — any account can test without a card. Paid Mistral models require a $5 minimum credit top-up.
Other providers

Browse other labs

Anthropic →OpenAI →Google →xAI →Moonshot →DeepSeek →Meta →Alibaba →Deepgram →Black Forest Labs →BAAI →All providers →