BenchLeader

Pixtral Large 2502

Price#192 of 274
$3.00per 1M tokens
Dearer than most
3.2× the median
Speed#122 of 220
73tokens/s
Below the median
0.9× the median

Good value at this level: no ranked model within 2 Index points costs three quarters of the price or less.

No cheaper ranked model scores higher: it is on the price frontier.

As of 21 Nov 2026, Pixtral Large 2502 by Mistral AI is not yet ranked on the BenchLeader Index, which needs at least five independent results across two categories. API pricing: $2.00 per 1M input tokens and $6.00 per 1M output tokens ($3.00 blended at 3:1), list price on 21 Nov 2026. It streams about 73 tokens/s (OpenRouter). Released 8 Apr 2025.

Key facts (as of 21 Nov 2026)

  • Pixtral Large 2502 API pricing: $2.00 per 1M input tokens and $6.00 per 1M output tokens ($3.00 blended at 3:1) (list price, 21 Nov 2026).
  • Pixtral Large 2502 streams about 73 tokens/s (OpenRouter, 21 Nov 2026).
  • Pixtral Large 2502 was released on 8 Apr 2025 (Mistral AI).

In detail. Pixtral Large 2502 is a Mistral AI proprietary model, released 8 Apr 2025. It is not yet ranked: no independent benchmark results so far, only pricing and metadata. At $3.00 per million tokens blended it is pricier than most ranked models. Output speed of 73 tokens per second puts it slower than most, with a first token in 0.4 s.

Blended price
$3.00/M
$2.00 in · $6.00 out
via OpenRouter
Output speed
73 tok/s
OpenRouter traffic, 7-day median; not yet measured by Artificial Analysis
First answer
0.41 s
Context
128k
via OpenRouter
Accepts
Text · Images
via models.dev, OpenRouter
Cost per task
–
Tokens per task
–
Released
8 Apr 2025

Get an email when Pixtral Large 2502 gets its first benchmark results

And when Mistral AI ships a new model, plus the weekly review on Mondays.

Choose providers and emails

Versions

Mistral AI has shipped 2 models under this name. Each is ranked on its own results; a newer version often has fewer results so far, which holds its index nearer the average until more arrive.

ModelReleasedIndexRank
Pixtral Large 2502this page8 Apr 2025––
Pixtral Large18 Nov 2024––

No independent quality benchmark results yet — only pricing and metadata.

API pricing: where to run it

Every provider serving this model through OpenRouter, with throughput and first-token latency measured on live traffic over the last 30 minutes and each provider’s own price. Purple marks the best in each column.

ProviderSpeedFirst tokenInput $/MOutput $/MContextQuantisation
Amazon Bedrock70 tok/s0.43 s$2.00$6.00128k–

What a task costs

Estimates from list price, output speed and time to first answer for the best configuration. “With caching” assumes three-quarters of the input is served from the prompt cache. Reasoning tokens are not modelled.

WorkloadTokens in / outCostWith cachingTime
Chat reply400 / 300$0.0026–4.5 s
Summarize a 30-page report12,000 / 600$0.028–8.6 s
Code edit6,000 / 1,500$0.021–21.0 s
Agentic coding session60,000 / 4,000$0.144–55.2 s
Structured extraction2,000 / 200$0.0052–3.1 s

More from Mistral AI

New this month

See also

Questions people ask

Why does Pixtral Large 2502 have no BenchLeader Index score?
The index needs at least five independent results across at least two categories, and as of 21 Nov 2026 Pixtral Large 2502 does not have them yet. Launch-post scores are never used, so it is ranked once independent publishers have measured it.
How much does Pixtral Large 2502 cost per 1M tokens?
As of 21 Nov 2026, Pixtral Large 2502 costs $2.00 per 1M input tokens and $6.00 per 1M output tokens, $3.00 blended (three input tokens per output token).
When was Pixtral Large 2502 released?
Mistral AI released Pixtral Large 2502 on 8 Apr 2025.

Data as of 21 Nov 2026. Compare with another model.

Cite as: BenchLeader, “Pixtral Large 2502: benchmarks, pricing, speed and rank”, data as of 21 Nov 2026, https://www.benchleader.com/models/pixtral-large-2502.