Codestral 2508 (batch)
by Mistral · mistralai/codestral-2508:batch · #95 cheapest of 422 paid models
Prices updated Sep 19, 2026, 6:22 PM UTC · refreshed hourly
Mistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation. [Blog Post](https://mistral.ai/news/codestral-25-08)
Compare vs:Claude Sonnet 5Claude Opus 4.6Claude Haiku 4.5GPT-5.6 Sol
Pricing
Input
$0.15
per 1M tokens
Output
$0.45
per 1M tokens
Blended (3:1)
$0.225
3 input : 1 output
Cache read
$0.015
per 1M cached tokens
Cache write
—
per 1M tokens
Cache & batch economics
Effective prices for Codestral 2508 (batch) with prompt caching.
| Cache hit rate | Effective blended $/1M | Example request* | vs no cache |
|---|---|---|---|
| 0% | $0.225 | $0.0158 | — |
| 50% | $0.174 | $0.009 | −43% |
| 90% | $0.134 | $0.0036 | −77% |
*Example: 100K sticky context + 2K new input + 1K output. Batch discount is an approximate 50% off list rates (available for OpenAI / Anthropic / Google — not flagged for this creator). Confirm on the vendor’s pricing page.
What a request costs
| Workload | Input tokens | Output tokens | Cost / request | Cost / 1K requests |
|---|---|---|---|---|
| Short chat message | 500 | 300 | $0.00021 | $0.21 |
| Document summary | 8,000 | 1,000 | $0.00165 | $1.65 |
| Codebase question (RAG) | 30,000 | 2,000 | $0.0054 | $5.40 |
| Long-context analysis | 150,000 | 5,000 | $0.0247 | $24.75 |
Performance
Intelligence Index
—
AA composite quality
Coding Index
—
Math Index
—
Agentic Index
—
Output speed
—
median
Time to first token
—
median
Time to first answer
—
after reasoning tokens
Design Arena Elo
| Category | Elo |
|---|---|
| Website | 1,025 |
| UI components | 1,032 |
| Data viz | 1,032 |
| 3D | 1,049 |
| Game dev | 991 |
| Code categories | 1,022 |
Specs
Context window
256K
tokens
Max output
205K
tokens
Input modalities
text, file
Tokenizer
Mistral