Codestral 25.08

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

mistral/codestral-2508

Organization: Mistral
Family: codestral
Providers: 9
Context: 128,000
Output limit: 8,192
Knowledge: —
Release: 2025-07-30
Updated: 2025-07-30
Weights: Closed
Input: text
Output: text
Capabilities: Tools, Structured, Temperature

Providers

Compare every cataloged offer for this model, including its provider, route, token limits, price, and capabilities.

10 offers · USD per million tokens

Provider	Model ID	Context	Output	Input / output · 1M	Reasoning	Tools	Structured	Details
AI/ML API	mistralai/codestral-2508	256,000	8,192	$0.41262 / $1.23786	No	Yes	Yes	View
Cortecs	codestral-2508	256,000	256,000	$0.368 / $1.103	No	Yes	Yes	View
Eden AI	mistral/codestral-2508	256,000	8,192	$0.30 / $0.90	No	Yes	Yes	View
Kilo Gateway	mistralai/codestral-2508	256,000	204,800	$0.30 / $0.90	No	Yes	Yes	View
LowRouter	auto/mistralai/codestral-2508	128,000	8,192	$0.3138 / $0.9413	No	Yes	Yes	View
Mistral	codestral-2508	256,000	8,192	$0.30 / $0.90	No	Yes	Yes	View
NanoGPT	mistralai/codestral-2508	256,000	32,768	$0.30 / $0.90	No	No	No	View
Mistralvia OpenRouter	mistralai/codestral-2508 unknown	256,000	204,800	$0.33 / $0.99	No	Yes	Yes	View
Mistralvia OpenRouter	mistralai/codestral-2508 unknown	256,000	204,800	$0.30 / $0.90	No	Yes	Yes	View
Vertex	codestral-2	128,000	8,192	$0.30 / $0.90	No	Yes	Yes	View

Prices and limits apply to each offer. A dash means the value is not provided. OpenRouter offers show the hosting provider and routing channel separately.

Pricing

Compare token rates and cache charges across available routes and hosting configurations.

USD per million tokens

Input from$0.30Per 1M input tokens

Output from$0.90Per 1M output tokens

Available offers10Across 9 providers

Lowest listed input and output prices across the offers above; they may belong to different providers. These are base rates, before conditional pricing, discounts or additional fees.

Endpoint price comparisonLatest observed snapshot · 2 lowest-priced configurations

InputOutput

Mistralmistral

$0.30$0.90

Mistralmistral/eu

$0.33$0.99

mistralai/codestral-2508Observed Oct 10, 2026, 11:31 AM UTC

Input: $0.30
Output: $0.90
Cache read: $0.03

Hosting prices through OpenRouter All endpoints and cache rates

Endpoint	Input / 1M	Output / 1M	Cache read / 1M	Cache write / 1M
Mistralmistral/eu	$0.33	$0.99	$0.033	—
Mistralmistral	$0.30	$0.90	$0.03	—

Each row is a hosting configuration. Open an offer in Providers for its full pricing conditions and additional fees. Endpoint observations may differ from the routing catalog's base price.

Performance

Review reported latency and output-throughput percentiles from the latest observed rolling window.

Latest 30-minute observation

Time to first token · milliseconds

Latency distributionRolling 30-minute snapshot · 1 endpoint

P50P75P90P99

Mistralmistral

206–6,145.2 ms

All latency percentiles 1 endpoints

Endpoint	P50	P75	P90	P99
Mistralmistral	206 ms	308 ms	729 ms	6,145.2 ms

Output throughput · tokens per second

Throughput distributionRolling 30-minute snapshot · 1 endpoint

P50P75P90P99

Mistralmistral

148.5–283.11 t/s

All throughput percentiles 1 endpoints

Endpoint	P50	P75	P90	P99
Mistralmistral	148.5 t/s	158.75 t/s	185.1 t/s	283.11 t/s

Percentiles describe the observed request distribution. These are snapshots of a rolling window, not a historical time series.

Uptime

Compare successful request rates across the latest 5-minute, 30-minute, and 24-hour observations.

Successful requests by window

Availability by endpointCurrent overlapping windows · 2 endpoints

Endpoint5 minutes30 minutes24 hours

Mistralmistral/euObserved Oct 10, 2026, 11:31 AM UTC

—

MistralmistralObserved Oct 10, 2026, 11:31 AM UTC

—

100%

Reported by OpenRouter at the time of collection; rate-limited requests are excluded. A dash means no measurement was reported. This is not a live availability check.

Benchmarks

Review attributed evaluation results on each source's original scale.

External evaluations

mistralai/codestral-2508Observed Oct 10, 2026, 11:31 AM UTC

Design Arena	Category	Elo	Win rate	Rank
models	codecategories	1,011	38.5%	115
models	dataviz	1,021	41.1%	107
models	gamedev	975	36.3%	118
models	uicomponent	1,020	46.7%	106
models	website	1,017	37.8%	120
models	3d	1,025	45.4%	102

Sources: Artificial Analysis and Design Arena, via OpenRouter. Scores retain their original scales and are not OpenAI Suite ratings.

Detailed evaluations

Evaluation	Configuration	Source	Results	Details
models · codecategories	Codestral 2 (2501)mistralai/codestral-2508	Design Arena	835 Elo	Details
models · dataviz	Codestral 2508mistralai/codestral-2508	Design Arena	1,019 Elo	Details
models · 3d	Codestral 2508mistralai/codestral-2508	Design Arena	1,020 Elo	Details
models · website	Codestral 2508mistralai/codestral-2508	Design Arena	1,014 Elo	Details
models · uicomponent	Codestral 2 (2501)mistralai/codestral-2508	Design Arena	853 Elo	Details
models · gamedev	Codestral 2508mistralai/codestral-2508	Design Arena	971 Elo	Details
models · uicomponent	Codestral 2508mistralai/codestral-2508	Design Arena	1,019 Elo	Details
models · website	Codestral 2 (2501)mistralai/codestral-2508	Design Arena	811 Elo	Details
models · dataviz	Codestral 2 (2501)mistralai/codestral-2508	Design Arena	778 Elo	Details
models · codecategories	Codestral 2508mistralai/codestral-2508	Design Arena	1,009 Elo	Details
models · gamedev	Codestral 2 (2501)mistralai/codestral-2508	Design Arena	815 Elo	Details

Sources: Artificial Analysis, Design Arena and OpenRouter. Evaluation configurations and scales differ; results are not interchangeable. Updated Oct 15, 2026.

Technical details & API

Explore specifications, supported parameters, reasoning controls, and API identifiers for each OpenRouter route.

Current route specifications

mistralai/codestral-2508Observed Oct 10, 2026, 11:31 AM UTC

Context: 256,000
Maximum output: 204,800
Tokenizer: Mistral
Input: text, file
Output: text
Moderation: No
Knowledge cutoff: 2025-03-31
Added to OpenRouter: 2025-08-01

Base URLhttps://openrouter.ai/api/v1

Model IDmistralai/codestral-2508

Version IDmistralai/codestral-2508

Supported parameters

frequency_penalty
max_tokens
prediction
presence_penalty
response_format
seed
stop
structured_outputs
temperature
tool_choice
tools
top_p

Default parameters

temperature: 0.3

Frequently asked questions

Answers based on the model metadata and serving offers currently in the catalog.

How much does Codestral 25.08 cost?

Listed rates start at $0.30 per million input tokens and $0.90 per million output tokens. Prices vary by provider and configuration; see Pricing for details.

Which providers offer Codestral 25.08?

There are 10 cataloged offers across 9 providers. Compare model IDs, prices and limits in Providers.

What is the context window?

The cataloged model context is 128,000 tokens. Each serving endpoint may apply a different limit.

Does it support tools and structured output?

Tool calling: Yes. Structured output: Yes. Support can vary by endpoint.

Catalog history · 1 recorded revision

Metadata observations since this model was first cataloged. These are not model release versions.

Oct 8, 2026 · 8eafd053ca91