Mistral Large 3 675B Instruct — Available Providers
Last refreshed 2026-05-16. Next refresh: weekly.
Compare pricing and deployment options across 4 providers.
Monthly cost ranking
Ranked for 1M input and 0.2M output tokens per month. Cache and batch discounts are applied only when the provider row has sourced prices.
Traffic profile
US default
Cost bars
Cheapest
AWS Bedrock
$0.80 at the selected traffic profile.
Batch jobs
Mistral AI Studio
$0.25 / $0.75 batch pricing is sourced for queued workloads.
Cache-heavy
Mistral AI Studio
Cache read is sourced at $0.050/1M.
Recipe-ready
AWS Bedrock
Install, auth, and call snippets are available from curated provider snippet data.
Provider matrix
Region, SLA, and compliance rows are hidden until curated source fields exist.| Provider | Profile cost | Input / Output | Batch | Cache | Deploy | Recipe | Links |
|---|---|---|---|---|---|---|---|
| AWS Bedrock hyperscaler | $0.80 | $0.50 / $1.50 | - | - | Serverless | Snippets | |
| Mistral AI Studio lab | $0.80 | $0.50 / $1.50 | $0.25 / $0.75 | read $0.050 | Serverless | Docs only | |
| Microsoft Foundry hyperscaler | Not enough pricing | - / - | - | - | Serverless | Docs only | |
| NVIDIA NIM inference | Not enough pricing | - / - | - | - | Serverless | Docs only |
Mistral Large 3 675B Instruct operational data note: this page ranks sourced token, cache, and batch fields only. Region, SLA, compliance, and latency claims are intentionally omitted until a curated matrix is added.