Codestral 2508
Mistral AI · released Aug 1, 2025
- Type
- Closed
- Input
- $0.30
- Output
- $0.90
- Cached
- $0.030
List price · per 1M tokens · Mistral AI at 256K context · source ↗
Our take
Written Sep 1, 2026Codestral 2508 is Mistral AI's proprietary coding model built for long-context code work, with a 256,000-token request limit and three hosted offers at closely matched price points. It launched in August 2025 but carries no measured quality scores in our data.
Pick this for repository-wide code review or analysis where the 256,000-token window matters more than proven benchmark scores. Choose Mistral's own 40-tokens-per-second endpoint if throughput is worth a modest price premium over the slower tier. Skip it if you need verified coding quality data, want to self-host, or are comparing against models with measured HumanEval or SWE-bench scores.
The case for it
- 256,000-token request limit — unusually long for code tasks.
- Three hosted offers with closely matched pricing, giving a straightforward speed-vs-cost choice.
The case against it
- No benchmark scores in our data: no coding Elo, HumanEval, or SWE-bench to justify its positioning.
- Parameter count undisclosed, so efficiency claims are unverifiable.
- Proprietary weights — not available for local deployment.
How good is it?
We hold no score for this model.
So there is no figure here for everyday use, coding, agent work or writing. That is a gap in our data, not a low score.
Where to rent it
Prices checked 4 hours ago — each listing carries its own date.
Mistral AI, through OpenRouter
The lab is also the cheapest we hold. The strip above and this offer are the same one, so nothing on this page undercuts Mistral AI on 256K of context.
- per 1M tokens
- $0.30 in / $0.90 out
- Context served
- 256K
- Throughput
- ~39 tok/s
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouterOpenRouter's own listing | $0.30 / $0.90checked 4 hours ago | 256K | not measured | Unknown | Unknown | Unknown |
| Mistral AIThrough OpenRouter | $0.30 / $0.90checked 4 hours ago | 256K205K max reply | 39 tok/s | No | Yes30 days | Unknown |
| Mistral AIeuThrough OpenRouter | $0.33 / $0.99checked 4 hours ago | 256K205K max reply | 20 tok/s | No | Yes30 days | Confirmed |
OpenRouterAcross the 3 listings we hold: 2 say they do not train on prompts, 0 say they do and 1 does not say. 1 appears in the zero-retention registry we check; the rest are unknown to us.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouterOpenRouter's own listing | ✓ | ✓ | ✓ |
| Mistral AIThrough OpenRouter | ✓ | ✓ | ✓ |
| Mistral AIeuThrough OpenRouter | ✓ | ✓ | ✓ |
Tool calling: 3 of 3 listings say yes. JSON output: 3 of 3 listings say yes. Strict schema: 3 of 3 listings say yes.
When we formed this view
Recent changes
What moved
first indexed by our pipelineEach date is the day we first saw the change, or the day the maker announced it.
What we do not know about this model yet
- No independent board has scored it, so we hold no quality figures at all.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 1 of 3 listings does not say whether it trains on prompts.
- We hold no batch or off-peak rate for any of its listings.
Licence and identifiers
What the licence allowsWe hold no licence record for this model. Inside are the identifiers you need to pull it — its Hugging Face repo where we have one, our slug and a machine-readable card.
Licence
We hold no licence record for this model, and no record of published weights either — so we can neither summarise its terms nor point you at the weights.
Identifiers
- Takes in, gives back
- Text and documents in, text out
- Catalogue slug
- mistralai-codestral-2508