mistralai Vision Reasoning

Mistral Medium 3.5 pricing & benchmarks

Released Apr 30, 2026 · served by 1 provider · ranked #55 by intelligence in our index

Input / 1M tokens$1.50
Output / 1M tokens$7.50
Context window262K
Cached input
Intelligence index29.9
Coding index46.9
Agentic index19.0
1M in + 300K out$3.75

What Mistral Medium 3.5 is

Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex...

Providers and prices for Mistral Medium 3.5

The same model costs different amounts depending on who serves it. Prices are per 1M tokens, cheapest first. Uptime and throughput are OpenRouter's rolling measurements, not vendor claims.

ProviderInputOutputContext QuantUptime 24hThroughput
Mistralcheapest $1.50 $7.50 262K 100.0%

Cheaper models in the same class

Models scoring within 4 points of Mistral Medium 3.5 on the Intelligence Index, but with a lower output price.

FAQ

How much does the Mistral Medium 3.5 API cost?

$1.50 per 1M input tokens and $7.50 per 1M output tokens. A typical workload of 1M input + 300K output tokens costs about $3.75.

Is Mistral Medium 3.5 free?

No. It is a paid model starting at $1.50 per 1M input tokens, though some providers offer trial credits.

Which provider is cheapest for Mistral Medium 3.5?

Mistral at $1.50 input / $7.50 output per 1M tokens.

Can I self-host Mistral Medium 3.5?

No. Mistral Medium 3.5 is closed-weight and only available through hosted APIs.