mistralai Open weights

Devstral 2 2512 pricing & benchmarks

Released Dec 9, 2025 · served by 1 provider

Input / 1M tokens$0.400
Output / 1M tokens$2.00
Context window262K
Cached input$0.040
Intelligence index19.2
Coding index31.3
Agentic index10.6
1M in + 300K out$1.00

What Devstral 2 2512 is

Devstral 2 is a state-of-the-art open-source model by Mistral AI specializing in agentic coding. It is a 123B-parameter dense transformer model supporting a 256K context window. Devstral 2 supports exploring...

Providers and prices for Devstral 2 2512

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 $0.400 $2.00 262K 99.5%

Cheaper models in the same class

Models scoring within 4 points of Devstral 2 2512 on the Intelligence Index, but with a lower output price.

FAQ

How much does the Devstral 2 2512 API cost?

$0.400 per 1M input tokens and $2.00 per 1M output tokens. A typical workload of 1M input + 300K output tokens costs about $1.00.

Is Devstral 2 2512 free?

No. It is a paid model starting at $0.400 per 1M input tokens, though some providers offer trial credits.

Which provider is cheapest for Devstral 2 2512?

Mistral at $0.400 input / $2.00 output per 1M tokens.

Can I self-host Devstral 2 2512?

Yes — weights are published as mistralai/Devstral-2-123B-Instruct-2512 on Hugging Face, so you can run it on your own hardware.