Codestral 25.08 pricing & specs
Mistral · released 2025-07-30 · ● verified 2026-10-11
input / 1M$0.30
output / 1M$0.90
context256K
max output8.2K
// price history ($/1M tokens)
// cheaper or similar alternatives
| model | in | out | ctx | vs Codestral 25.08 |
|---|---|---|---|---|
| Llama 3.2 1B Instruct | $0.02 | $0.02 | 131K | −95.6% |
| Gemma 4 E2B IT | $0.04 | $0.08 | 131.1K | −88.9% |
| Qwen3.7 Flash | $0.03 | $0.13 | 1M | −87.8% |
| Gemma 3 12B IT | $0.05 | $0.10 | 131.1K | −86.1% |
| Command R7B | $0.0375 | $0.15 | 128K | −85.4% |
// price by host
| host | in $/1M | out $/1M |
|---|---|---|
| Google Vertex AI | $0.30 | $0.90 |
// faq
How much does Codestral 25.08 cost?
Codestral 25.08 costs $0.30 per million input tokens and $0.90 per million output tokens. At 50M input and 10M output tokens per month that is about $24.00.
What is the context window of Codestral 25.08?
256K tokens, with up to 8.2K output tokens per request.
Does Codestral 25.08 support prompt caching?
Yes. Cached input tokens cost $0.03 per million.
What are cheaper alternatives to Codestral 25.08?
Llama 3.2 1B Instruct ($0.02 in / $0.02 out), Gemma 4 E2B IT ($0.04 in / $0.08 out), Qwen3.7 Flash ($0.03 in / $0.13 out) offer the same input types and capabilities for less.
// spec sheet
- input / 1M
- $0.30
- output / 1M
- $0.90
- cache read / 1M
- $0.03
- blended (3:1)
- $0.45
- context
- 256K
- max output
- 8.2K
- input types
- text
- reasoning
- no
- tool calling
- yes
- structured output
- yes
- open weights
- no
- knowledge cutoff
- n/a
- price source
- Mistral
// cost calculator
| model | in $/1M | out $/1M | = monthly |
|---|---|---|---|
| Llama 3.2 1B Instruct | $0.02 | $0.02 | $1.20 |
| Gemma 4 E2B IT | $0.04 | $0.08 | $2.80 |
| Qwen3.7 Flash | $0.03 | $0.13 | $2.80 |
| Codestral 25.08 | $0.30 | $0.90 | $24.00 |
Base-tier list prices. Long-context tiers, caching and batch discounts are not included.