Side by side pricing and context for Codestral and GPT-4.1 Mini. Rates are curated catalog values with last verified dates on each model page.
Codestral
Code-focused Mistral model for completion and repo assistance. Estimate with real code prompts: token density differs from prose.
Input $1.00 / Output $3.00 per 1M
Context 256K · Approx
GPT-4.1 Mini
Cheaper GPT-4.1 variant for the same long-context shape. Use for RAG and assistants where Mini quality is enough and you want Exact OpenAI token counts.
Input $0.400 / Output $1.60 per 1M
Context 1M · Exact (o200k_base)
Quick take
- GPT-4.1 Mini is cheaper on input in this catalog snapshot.
- GPT-4.1 Mini is cheaper on output in this catalog snapshot.
- Both last verified on their model pages (2026-08-02 / 2026-08-02).
Rate table
| Metric | Codestral | GPT-4.1 Mini |
|---|---|---|
| Input / 1M | $1.00 | $0.400 |
| Output / 1M | $3.00 | $1.60 |
| Cached input / 1M | n/a | $0.100 |
| Context | 256K | 1M |
| Tokenizer | Approx | Exact (o200k_base) |