Code-specialized model tuned for agentic editing.
PassingRight routes requests to the best providers that are able to handle your prompt size and parameters.
Code-specialized model tuned for agentic editing. You can access it through PassingRight's OpenAI-compatible API with automatic provider routing, fallback, and cost analytics.
Pricing for Codestral 3 on PassingRight starts at $0.90 per million input tokens and $3.00 per million output tokens, depending on the provider. The pricing table above always reflects the current per-provider rates.
Codestral 3 supports a context window of up to 256,000 tokens on its largest provider deployment.
Codestral 3 is served by Mistral AI through PassingRight. Requests are automatically routed to the best available provider, with fallback when a provider has issues.
Codestral 3 supports tool (function) calling and soft JSON output, but NOT strict JSON output schema (its upstream provider does not enforce it).
Codestral 3 was released on September 23, 2026.
Mistral Medium 4
Up to 5% off128,000 context$0.38 in / $1.90 out per 1M
Devstral 2
Up to 5% off262,144 context$0.38 in / $1.90 out per 1M
Mistral Large Latest
Up to 5% off128,000 context$3.80 in / $11.40 out per 1M
Mistral Large 3
Up to 5% off262,144 context$0.47 in / $1.42 out per 1M
Ministral 8B
Up to 5% off262,144 context$0.14 in / $0.14 out per 1M
Ministral 3B
Up to 5% off131,072 context$0.09 in / $0.09 out per 1M