Pixtral Large (25.02)
As of Nov 22, 2026, the cheapest Pixtral Large (25.02) API price is $1.993 per 1M input tokens (Cortecs) and $5.978 per 1M output tokens (Cortecs). Pixtral Large (25.02) is offered by 6 providers in the pixtral-large family, reasoning enabled.
API pricing by provider
Metered per-token prices. Cheapest input and output are highlighted; † marks a context-tier surcharge. How prices are ranked. Seeing a wide range? Why the same LLM costs different amounts.
| Cortecspixtral-large-2502 | Cheapest$1.993 | Cheapest$5.978 | — | — | 128k |
| Amazon Bedrockeu.mistral.pixtral-large-2502-v1:0 | $2 | $6 | — | — | 128k |
| Amazon Bedrockmistral.pixtral-large-2502-v1:0 | $2 | $6 | — | — | 128k |
| Amazon Bedrockus.mistral.pixtral-large-2502-v1:0 | $2 | $6 | — | — | 128k |
| Eden AIamazon/mistral.pixtral-large-2502-v1:0 | $2 | $6 | — | — | 128k |
| DevPass (LLM Gateway)pixtral-large-2502 | $2 | $6 | — | — | 131k |
| LLM Gatewayaws-bedrock/pixtral-large-2502 | $2 | $6 | — | — | 131k |
| OpenRoutermistralai/pixtral-large-2502 | $2 | $6 | — | — | 128k |
Pixtral Large (25.02) pricing FAQ
What is the cheapest Pixtral Large (25.02) API?
As of Nov 22, 2026, Cortecs has the lowest Pixtral Large (25.02) output price at $5.978 per 1M tokens, and Cortecs has the lowest input price at $1.993 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.
How many providers offer Pixtral Large (25.02)?
6 providers list Pixtral Large (25.02) on Sovyron; 8 of them sell it at a metered per-token price.
Is Pixtral Large (25.02) free?
No provider in the Sovyron catalog lists a free tier for Pixtral Large (25.02).
What is the context window of Pixtral Large (25.02)?
Pixtral Large (25.02) supports a 131k-token context window and up to 131k output tokens.
Token cost calculator
What a month costs at one provider's published rates. Enter the tokens you expect to send and receive; cached tokens use the cached-input price where the provider lists one, and count as ordinary input where it does not. See how much prompt caching saves and why output tokens cost more than input tokens.
Estimated
—