tokenstat
tokenstat

Codestral 25.01

azure/codestral-2501 · rates as of · Benchmarks · AI plans · Calculator

Mistral coding model for code completion, generation, and developer workflows

Cheapest input
$0.2
$/MTok · LiteLLM
Cheapest output
$0.6
$/MTok
Context
256K
tokens
Sources
2
6 listings

Sources

Same model, different sources. Our first-party rate is listed first, then router and aggregator rows stay separate so you can see the spread instead of a single blended number.

SourceProviderInputOutputCache readContext
LiteLLMcheapestcodestral-2501N/A$0.2$0.6$0.02N/A
LiteLLMcheapestvertex_ai/codestral-2501N/A$0.2$0.6$0.02N/A
models.devcodestral-2501Azure$0.3$0.9$0256K
models.devcodestral-2501Azure$0.3$0.9$0256K
LiteLLMCodestral-2501N/A$0.3$0.9$0.03N/A
LiteLLMazure_ai/Codestral-2501N/A$0.3$0.9$0.03N/A

Capabilities

  • Tool calling
  • In: text
  • Out: text
Knowledge cutoff: 2024-03Released: 2025-01-01Family: codestral

Run this model in a real workspace

Launch agents from the project they work in, use remote management to reach another machine, and see this model's sessions and token usage in your own history. Free to use, runs on your device.

CLI for macOS, Linux, and Windows

Data and list-price estimates may contain mistakes. Not investment advice.