OpenAI compatible API · Attested · Public status

Mistral

Explore Mistral models on TrustedRouter with current routes, token pricing, policy sources, privacy posture, regional availability, and API support.

Verify gateway

Onebase URL to migrate

100sof models and routes

0prompt or output logs. Always.

Mistralmistral

No provider claim

All providers

These privacy labels describe Mistral, the upstream model provider. Confidential requires all three: verified provider compute, end-to-end encryption and explicit zero data retention. Account and billing metadata are outside the content-retention claim.

Provider	Mistral
API operator country	FR Legal home of the API operator, not an inference-location guarantee.
Headquarters	Not verified
Routing status	Active
Provider website	https://mistral.ai/
Models	11 public models
Credits routes	11
Zero data retention	no
Verified confidential inference	Not verified
Policy note	TrustedRouter's managed Mistral account has model-training use disabled, so new input and output sent through TR-funded routes is opted out of model training. This is not zero data retention: Mistral's published policy says ordinary API input and output may be retained for 30 rolling days unless ZDR is separately activated. Customer BYOK accounts keep their own Mistral privacy settings. Policy source

Inference locations

Provider API declarations are also available on each model's endpoint API. Direct chat and Responses replies separate advertised availability from serving location in usage.inference_location; the actual serving region remains unknown when not reported.

Where the upstream GPUs execute the model, not the provider's headquarters, API ingress, or data storage. ZDR and confidential inference do not by themselves restrict geography.

Declared countries or regions: Not verified
No inference-location declaration has been verified for this provider.
Can locations change?: Not verified. Do not assume that the serving location is fixed.
Provider region pinning: Not verified.
Pinning through TrustedRouter: No verified provider-specific location pin documented here.
Infrastructure declaration: Inference location not verified; no country-specific residency commitment.
Evidence: Not yet reviewed.

Provider selection alone is not a region pin. TrustedRouter's US provider filter selects company jurisdiction, not GPU location. A regional gateway hostname does not pin a downstream GPU. For a binding residency requirement, confirm the model, region, failover scope and enforced controls before sending sensitive data.

Measured performance

28 samples

Continuously sampled across Mistral's routed models: p50 TTFT, effective throughput, and success rate. Effective throughput uses provider-reported output tokens over complete request time. Unsupported route and probe-configuration rows are separated from provider downtime. No prompt or output content stored.

p50 TTFT	1059 ms
Effective throughput	64 tok/s n=2
Uptime	100.00%

Model	p50 TTFT	Effective throughput	Uptime	Config excluded	Availability samples
mistralai/ministral-8b-2512	704 ms	—	100.00%	—	2
mistralai/mistral-nemo	933 ms	64 tok/s n=2	100.00%	—	3
mistralai/codestral-2508	941 ms	—	100.00%	—	2
mistralai/mistral-large	1027 ms	—	100.00%	—	4
mistralai/ministral-3b-2512	1059 ms	—	100.00%	—	8
mistralai/ministral-14b-2512	1196 ms	—	100.00%	—	1
mistralai/mistral-small-2603	1692 ms	—	100.00%	—	3
mistralai/mistral-medium-3-5	1826 ms	—	100.00%	—	5

Mistral performance history · Full provider & model leaderboard.

Provider models

Models served by Mistral.

Each row links to pricing, provider, benchmark, and API pages for the model.

Model	AI IQ	Context	Input	Cached input	Output
`mistralai/codestral-2508` Mistral: Codestral 2508	—	256,000	$0.3165/1M	$0.03165/1M	$0.9495/1M
`mistralai/ministral-14b-2512` Mistral: Ministral 3 14B 2512	—	262,144	$0.211/1M	$0.0211/1M	$0.211/1M
`mistralai/ministral-3b-2512` Mistral: Ministral 3 3B 2512	—	131,072	$0.1055/1M	$0.01055/1M	$0.1055/1M
`mistralai/ministral-8b-2512` Mistral: Ministral 3 8B 2512	—	262,144	$0.15825/1M	$0.015825/1M	$0.15825/1M
`mistralai/mistral-large` Mistral Large	—	128,000	$0.5275/1M	$0.05275/1M	$1.5825/1M
`mistralai/mistral-large-4` Mistral: Mistral Large 4	IQ 117#49	1,048,576	$0.7174/1M	$0.07385/1M	$2.20495/1M
`mistralai/mistral-medium-3-5` Mistral: Mistral Medium 3.5	—	262,144	$1.5825/1M	$0.15825/1M	$7.9125/1M
`mistralai/mistral-nemo` Mistral: Mistral Nemo	—	131,072	$0.025848/1M	Not published	$0.103179/1M
`mistralai/mistral-small-2603` Mistral: Mistral Small 4	—	262,144	$0.15825/1M	$0.015825/1M	$0.633/1M
`mistralai/voxtral-mini-2602` Voxtral Mini Transcribe 2	—	7 MiB, 10 minutes	$0.003165/audio minute	Not applicable	Included
`mistralai/voxtral-mini-tts-2603` Mistral: Voxtral Mini TTS	—	10000 characters	$16.88/M characters	Not applicable	Included

Questions

Does Mistral have zero data retention?

TrustedRouter does not currently mark Mistral as provider-level zero data retention. Use trustedrouter/zdr or provider.min_privacy=zdr to select a different eligible route, and review the linked policy source for changes.

Is Mistral end-to-end encrypted?

TrustedRouter does not currently mark Mistral as end-to-end encrypted at the provider boundary. The TrustedRouter gateway is still attested, but the selected provider normally receives the request in order to run the model. Use trustedrouter/e2e for the stronger route requirement.

Which Mistral models are available through TrustedRouter?

This page currently lists 11 public Mistral models, with live pricing, route count, context length, measured performance when available, and links to each model's provider and benchmark pages.