Which Mistral models does this reference list?

10 Mistral models: 8 text and 2 audio. Each has its own page with Mistral's list rate and the providers that serve it.

Which providers serve Mistral models?

Mistral and OpenRouter. You connect your own account with any of them; INFRO routes between the ones you connect.

What is the lowest Mistral input rate listed?

Ministral 3 3B, at $0.10 per 1M input tokens and $0.10 per 1M output tokens on Mistral's list (checked 2026-10-05).

Does INFRO add a markup to Mistral model usage?

No. Your Mistral or provider account bills usage directly; INFRO charges a software subscription and takes 0% of model spend.

Model vendor

Mistral models: API pricing and providers

10 Mistral models with Mistral's published list rates and the providers that serve each one. You call them through INFRO on a provider account you connect; that account bills you, and INFRO adds 0% to model spend.

Rates checked 2026-10-05.

Model	Modality	List rate	Providers
Mistral Large 3 mistral/mistral-large-3 Open-weight multimodal MoE flagship	Text	$0.50 per 1M input tokens and $1.50 per 1M output tokens	2
Mistral Medium 3.5 mistral/mistral-medium-3.5 Dense multimodal model for agentic and coding work	Text	$1.50 per 1M input tokens and $7.50 per 1M output tokens	2
Mistral Small 4 mistral/mistral-small-4 Hybrid instruct/reasoning/coding model	Text	$0.15 per 1M input tokens and $0.60 per 1M output tokens	2
Ministral 3 14B mistral/ministral-3-14b Small text+vision model	Text	$0.20 per 1M input tokens and $0.20 per 1M output tokens	2
Ministral 3 8B mistral/ministral-3-8b Small text+vision model	Text	$0.15 per 1M input tokens and $0.15 per 1M output tokens	2
Ministral 3 3B mistral/ministral-3-3b Tiny text+vision model	Text	$0.10 per 1M input tokens and $0.10 per 1M output tokens	2
Codestral mistral/codestral Low-latency code generation and FIM	Text	$0.30 per 1M input tokens and $0.90 per 1M output tokens	2
Voxtral Small mistral/voxtral-small Chat with audio input	Text	$0.10 per 1M input tokens and $0.40 per 1M output tokens	2
Voxtral Mini Transcribe 2 mistral/voxtral-mini-transcribe-2 Speech-to-text	Audio	$0.18 per audio hour	2
Voxtral TTS mistral/voxtral-tts Text-to-speech with voice cloning	Audio	$16 per 1M characters	1

Mistral models: questions

Which Mistral models does this reference list?: 10 Mistral models: 8 text and 2 audio. Each has its own page with Mistral's list rate and the providers that serve it.
Which providers serve Mistral models?: Mistral and OpenRouter. You connect your own account with any of them; INFRO routes between the ones you connect.
What is the lowest Mistral input rate listed?: Ministral 3 3B, at $0.10 per 1M input tokens and $0.10 per 1M output tokens on Mistral's list (checked 2026-10-05).
Does INFRO add a markup to Mistral model usage?: No. Your Mistral or provider account bills usage directly; INFRO charges a software subscription and takes 0% of model spend.

Mistral models

Mistral models: questions

Other model vendors