Ask

Codestral vs Mistral Medium 3

Detailed pricing comparison and cost analysis.

Updated August 2026

Cost Simulator

Codestral Cost
$0.48
Mistral Medium 3 Cost
$0.80
Codestral is 40% cheaper
FeatureCodestralMistral Medium 3
ProviderMistralMistral
Input Price (1M)$0.30$0.40
Output Price (1M)$0.90$2.00
Context Window256,000131,000

Verdict

Codestral costs $0.30 per 1M input tokens and $0.90 per 1M output tokens. Mistral Medium 3 costs $0.40 per 1M input tokens and $2.00 per 1M output tokens. Codestral is 25% cheaper on input tokens than Mistral Medium 3. For output tokens, Codestral is the more affordable option at $0.90/1M vs $2.00.

On context window, Codestral supports 256,000 tokens — meaning it can fit more conversation history, documents, or code in a single request. This matters for RAG pipelines, long document analysis, and agentic workflows where context builds up over many turns.

When to choose Codestral

  • ✓ You need the lowest input token cost ($ 0.30/1M)
  • ✓ Your workload is output-heavy — Codestral generates text cheaper
  • ✓ You need a larger context window (256,000 tokens)
  • ✓ You are already integrated with Mistral

When to choose Mistral Medium 3

  • ✓ You are already integrated with Mistral

Use the calculator above to simulate your specific workload and find the exact break-even point. For most applications, the cheapest model is the one that minimises your total monthly bill given your input-to-output token ratio.

Frequently Asked Questions

Is Codestral cheaper than Mistral Medium 3?

Codestral is cheaper on input tokens at $0.30/1M vs $0.40/1M for Mistral Medium 3 — a 25% saving.

What is the context window of Codestral vs Mistral Medium 3?

Codestral has a 256,000-token context window. Mistral Medium 3 has a 131,000-token context window. Codestral supports the larger context, suitable for longer documents and agentic workflows.

Which model is better: Codestral or Mistral Medium 3?

The best choice depends on your use case. For cost efficiency on input tokens, Codestral is the cheaper option. For maximum context length, Codestral supports 256,000 tokens. Use the comparison table above to find the right fit for your workload.