openai
Codestral 2508 vs GPT-5.6 Luna
73.6 overall · $0.450 / 1M
// mistralai
Codestral 2508
mistralai/codestral-2508
tool callingfile inputprompt caching
Codestral 2508 costs $0.300 per 1M input tokens and $0.900 per 1M output tokens with a 256K-token context window.
A tool-calling model from mistralai, released Aug 1, 2025. LiveBench hasn't published a run for it, so this page carries measured price and specs only — no benchmark numbers.
- Input / 1M
- $0.300
- Output / 1M
- $0.900
- Context
- 256K
- LiveBench overall
- Not evaluated
Specs and pricing
| Input price USD per 1M prompt tokens | $0.300 |
|---|---|
| Output price USD per 1M completion tokens, reasoning included | $0.900 |
| Blended price 3:1 input:output — #129 cheapest of 343 listed models | $0.450 |
| Cached input read Blank means not priced separately — not free | $0.030 |
| Cache write | — |
| Context window | 256,000 tokens |
| Max output | 204,800 tokens |
| Input modalities | text, file |
| Tool calling | Yes |
| Extended reasoning | No |
| Knowledge cutoff | 2025-03-31 |
| Listed | Aug 1, 2025 |
Also listed as mistralai/codestral-2508:batch ($0.225 blended)— the same model at a different price or rate limit.
What Codestral 2508 costs to run
Monthly list cost across five workload shapes, using the published cached-input rate where there is one. A floor, not a quote — batch discounts and cache writes aren't included.
| Workload | Per month |
|---|---|
| Support chatbot 1.2K in / 400 out × 200K requests | $124.56/mo |
| RAG assistant 8K in / 600 out × 100K requests | $186.00/mo |
| Coding agent 40K in / 4K out × 20K requests | $160.80/mo |
| Document extraction 20K in / 1.5K out × 50K requests | $354.00/mo |
| Bulk classification 500 in / 20 out × 5M requests | $705.00/mo |
Compare Codestral 2508 with
Benchmarked models at a similar price.
openai
Codestral 2508 vs GPT-5.4 Nano
69.6 overall · $0.463 / 1M
minimax
Codestral 2508 vs MiniMax M3
67.3 overall · $0.525 / 1M
deepseek
Codestral 2508 vs DeepSeek V4 Flash Vision Exp
76.8 overall · $0.330 / 1M
qwen
Codestral 2508 vs Qwen3.6 Plus
68.9 overall · $0.731 / 1M
Codestral 2508 vs Gemini 3.5 Flash Lite
63.9 overall · $0.850 / 1M
Codestral 2508 FAQ
How much does Codestral 2508 cost?
Codestral 2508 lists at $0.300 per 1M input tokens and $0.900 per 1M output tokens, with cached input reads at $0.030 per 1M. A RAG assistant handling 100K requests a month (8K tokens in, 600 out) comes to about $186.00 at list price.
What is the context window of Codestral 2508?
Codestral 2508 accepts up to 256,000 tokens of context and can return up to 204,800 output tokens per response.
Does Codestral 2508 support tool calling?
Yes — Codestral 2508 supports tool (function) calling. It accepts text, file input.
How does Codestral 2508 score on benchmarks?
LiveBench has not published a run for Codestral 2508 yet. Until it does, compare it on price and specs, or run your own evaluation on your own tasks.
What is the API model ID for Codestral 2508?
On OpenRouter the model ID is "mistralai/codestral-2508". It was listed on Aug 1, 2025.
More from mistralai
How these numbers are produced
- Price and specs — provider list data from OpenRouter, refreshed every 15 minutes. “Blended” is a 3:1 input:output mix.
- Scores and ranks — LiveBench release 2026-06-25. Ranks count only models that have a published run; a blank means “not evaluated”, never “bad”.
- Cost per point — the measured dollars LiveBench spent on the run, divided by the score it earned.
Published benchmarks rank models on someone else's tasks. Before committing, see LLM & agent evaluation for building an eval on your own.