Mistral · 2025-08-01
Codestral 2508 pricing
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.
Prices from OpenRouter’s models API, updated October 29, 2026
What Codestral 2508 costs a month
| Workload | Standard |
|---|---|
| Support chatbot: 1,000 chats a day, 1,500 tokens in, 400 out | $24.30 |
| Daily summaries: 10,000 a day, 3,000 tokens in, 300 out | $351 |
| Coding agent: 400 calls a day, 60,000 tokens in (80% cached), 2,000 out | $82.08 |
30 days. Cached input billed at the cache-read price. Use your own numbers.
Cheaper models with a similar context window
| Model | Provider | Input /1M | Output /1M | Cache read /1M | Context | Chatbot, per month* |
|---|---|---|---|---|---|---|
| Ling 3.0 Flash | inclusionai | $0.021 | $0.063 | $0.0042 | 262K | $1.70 |
| GLM 5.3 Flash | Z.ai | $0.046 | $0.074 | $0.03 | 1.05M | $2.95 |
| Qwen3.7 Flash | Alibaba Qwen | $0.03 | $0.13 | $0.006 | 1M | $2.91 |
| Mercury 2.5 | inception | $0.04 | $0.15 | $0.004 | 260K | $3.60 |
| Laguna XS 2.1 free variant | poolside | $0.06 | $0.12 | $0.03 | 262K | $4.14 |
* Support chatbot: 1,000 chats a day, 1,500 tokens in, 400 out, 30 days, no caching. Prices in US dollars per 1M tokens.
Cheaper isn’t automatically as good. Glow’s GlowBench scores models on your kind of task before suggesting a swap.
Other Mistral models
| Model | Input /1M | Output /1M | Cache read /1M | Context | Chatbot, per month* |
|---|---|---|---|---|---|
| Mistral Large 4 | $1.36 | $4.18 | $0.14 | 1.05M | $111 |
| Mistral Medium 3.5 | $1.50 | $7.50 | – | 262K | $158 |
| Mistral Small 4 | $0.15 | $0.60 | $0.015 | 262K | $13.95 |
| Devstral 2 2512 | $0.40 | $2 | $0.04 | 262K | $42.00 |
| Ministral 3 14B 2512 | $0.20 | $0.20 | $0.02 | 262K | $11.40 |
| Ministral 3 3B 2512 | $0.10 | $0.10 | $0.01 | 131K | $5.70 |
* Support chatbot: 1,000 chats a day, 1,500 tokens in, 400 out, 30 days, no caching. Prices in US dollars per 1M tokens.
Related
Codestral 2508: questions
How much does Codestral 2508 cost?
$0.30 per 1M input tokens and $0.90 per 1M output tokens, with cached input at $0.03. A 1,000-token prompt with a 500-token answer costs about $0.0008.
What is Codestral 2508’s context window?
256,000 tokens, with up to 204,800 output tokens per response.
Is there a cheaper alternative to Codestral 2508?
Ling 3.0 Flash costs $0.021 in and $0.063 out per 1M tokens with a similar context window. Whether it matches Codestral 2508’s quality depends on the task: test it on your own prompts (Glow’s GlowBench does this per task).
Know what each model really costs you.
Connect OpenRouter and Glow shows spend by model, key and product, and flags the swap that saves the most at the same quality.
- Read-only keys
- Never shown again
- 2FA + Face ID
- 7-day trial