Start free trial

Mistral: Codestral 2508 (batch)

mistralai/codestral-2508-batch
CompareAPITry this model

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](https://mistral.ai/news/codestral-25-08)

Modalities
In / out per 1M$0.15 / $0.45
Context250K
ReleasedAug 1, 2025

Providers

2 providers serve this model upstream.

Providers serving this model
ProviderInput /MOutput /MCache read /MLatency P50Throughput P50Uptime
Mistral$0.30$0.90$0.030.40s81 tps100%
Mistraleu$0.33$0.99$0.03——100%

Market-wide measurements, refreshed every 15 minutes. They describe who serves Codestral 2508 (batch) in general, not how ProjectCOZY routes your requests.

Pricing

List rates per 1M tokens — what Codestral 2508 (batch) costs pay-as-you-go elsewhere, not what you pay here.

Input
$0.15
per 1M tokens
Output
$0.45
per 1M tokens
Cache read
$0.01
per 1M cached tokens
Included in every pass
Codestral 2508 (batch) is included in every ProjectCOZY pass at no extra cost — one flat rate, no per-token metering. The rates above are there for comparison.

Performance

Time to first token and output speed across every provider, over the last 3 days.

0.0s1.0s2.0s3.0s4.0s
Oct 16, 1 AMOct 16, 9 AMOct 16, 6 PMOct 17, 5 AMOct 17, 1 PMOct 17, 9 PMOct 18, 8 AMOct 18, 4 PMOct 19, 1 AMOct 19, 9 AM
Mistral
0 tok/s50 tok/s100 tok/s150 tok/s200 tok/s
Oct 16, 1 AMOct 16, 9 AMOct 16, 6 PMOct 17, 5 AMOct 17, 1 PMOct 17, 9 PMOct 18, 8 AMOct 18, 4 PMOct 19, 1 AMOct 19, 9 AM
Mistral

Uptime

100% of requests were served successfully over the last 3 days, across all providers.

Last 3 daysAvailability 99.94%
Oct 16, 9:00 AMNow
Availability over the last 24 hoursAvailability 99.94%
100% 97% 93% 90%
Oct 18, 9:20 AMNow

Apps

Tools that most often run Codestral 2508 (batch), by tokens this week.

Kilo CodeCli Agent · 42.3% of tokens396.1MOpenClawPersonal Agent · 21.2% of tokens198.9MpiCli Agent · 16.3% of tokens153.1MHermes AgentPersonal Agent · 11.2% of tokens104.5MMegaLens.ai9% of tokens84.1M

Activity

3.6B tokens processed market-wide in the last month.

0500.0M1.0B1.5B2.0B
Sep 19Sep 24Sep 29Oct 4Oct 9Oct 14Oct 19
Tokens

FAQ

Which model id do I use for Codestral 2508 (batch)?
mistralai/codestral-2508:batch. Send it as the model field from any OpenAI-compatible client, against http://192.168.1.55/v1.
How much context does Codestral 2508 (batch) hold?
256,000 tokens per request, of which up to 204,800 can be the response.
What can it accept and return?
Input: text, file. Output: text.
What does Codestral 2508 (batch) cost on a pass?
Nothing beyond the pass itself. Pay-as-you-go elsewhere it lists at $0.15 per 1M input tokens and $0.45 per 1M output tokens.
How current is its knowledge?
Training data runs to Mar 2025. Anything later has to come from your prompt or a tool call.
Who built Codestral 2508 (batch)?
Mistral, in the Codestral family.

Explore

Other models your pass can call.

Aion 3.5aion-labs/aion-3.5256KAionAion 3.5 Miniaion-labs/aion-3.5-mini256KAionAion-2.0aion-labs/aion-2.0128KAionAion-3.0aion-labs/aion-3.0128KAionAion-3.0-Miniaion-labs/aion-3.0-mini128KAionAion-RP 1.0 (8B)aion-labs/aion-rp-llama-3.1-8b32KAion