tokenstat
tokenstat

Mistral: Devstral 2

mistralai/devstral-2-123b-instruct-2512 · rates as of · Benchmarks · Plans · Calculator

Mistral coding agent model for repository tasks and software engineering workflows

Cheapest input
$0.4
$/MTok · models.dev
Cheapest output
$1.40
$/MTok
Context
262K
tokens
Offers
5
2 sources

Offers

Same model, different listings. First-party, router, and aggregator rows stay separate so you can see the spread instead of a single blended number.

SourceProviderInputOutputCache readContext
models.devcheapestmistralai/devstral-2-123b-instruct-2512NanoGPT$0.4$1.40$0262K
LiteLLMmistralai/devstral-2-123b-instruct-2512$0.4$2$0.04
LiteLLMdevstral-2-123b-instruct-2512$0.4$2$0.04
LiteLLMscaleway/mistralai/devstral-2-123b-instruct-2512$0.4$2$0.04
models.devdevstral-2-123b-instruct-2512GreenPT$0.57$2.74$0200K

Capabilities

  • Tool calling
  • Open weights
  • In: text
  • Out: text
Knowledge cutoff: 2025-12Released: 2025-12-09Family: devstral

See what you actually spent

tokenstat prices your local sessions at list rates like these, with the cache split kept honest. Free, open source, runs on your machine.

$ curl -fsSL https://tokenstat.ai/install.sh | bash