tokenstat
tokenstat

Mistral: Codestral 2508

mistral/codestral-2508 · rates as of · Benchmarks · AI plans · Calculator

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

Cheapest input
$0.15
$/MTok · OpenRouter
Cheapest output
$0.45
$/MTok
Context
256K
tokens
Sources
3
11 listings

Price changes

Cheapest list input/output only. Rates move rarely, so this is an event log. Down means cheaper. Showing the 8 latest changes.

Input $/MTok over sampled dates
Output $/MTok
  • ↓ lowerOutput $0.9 → $0.45
  • ↓ lowerInput $0.3 → $0.15

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
OpenRoutercheapestmistralai/codestral-2508:batchOpenRouter$0.15$0.45$0.015256K
LiteLLMmistralai/codestral-2508:batchN/A$0.15$0.45$0.015N/A
models.devmistralai/codestral-2508Kilo Gateway$0.3$0.9$0.03256K
models.devmistralai/codestral-2508NanoGPT$0.3$0.9$0.15256K
OpenRoutermistralai/codestral-2508OpenRouter$0.3$0.9$0.03256K
models.devcodestral-2508DevPass (LLM Gateway)$0.3$0.9$0256K
models.devmistral/codestral-2508LLM Gateway$0.3$0.9$0256K
LiteLLMmistralai/codestral-2508N/A$0.3$0.9$0.03N/A
LiteLLMcodestral-2508N/A$0.3$0.9$0.03N/A
LiteLLMmistral/codestral-2508N/A$0.3$0.9$0.03N/A
models.devcodestral-2508Cortecs$0.368$1.10$0.037256K

Capabilities

  • Tool calling
  • Structured output
  • Attachments
  • Open weights
  • In: text
  • In: pdf
  • In: file
  • Out: text
Knowledge cutoff: 2025-03-31Released: 2025-08-01Family: 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.