Codestral 2508 API pricing
Mistral charges $0.3 per million input tokens and $0.9 per million output tokens for Codestral 2508 (codestral-2508), and $0.03 per million cached input tokens. A typical request of 1,000 input and 500 output tokens costs $0.00075.
Codestral 2508 price per million tokens
| Token type | Standard |
|---|---|
| Input | $0.3 |
| Cached input | $0.03 |
| Output | $0.9 |
API model id: codestral-2508. Codestral 2508 supports a 128K-token context window, up to 128K output tokens and tool calling.
What Codestral 2508 costs per request
| Request | 1 request | 1,000 requests | 1M requests |
|---|---|---|---|
| Short chat message (300 in, 200 out) | $0.00027 | $0.27 | $270.00 |
| Typical request (1K in, 500 out) | $0.00075 | $0.75 | $750.00 |
| Long document summary (20K in, 1K out) | $0.0069 | $6.90 | $6,900.00 |
| Coding agent step (50K in, 2K out) | $0.0168 | $16.80 | $16,800.00 |
At standard rates. A token is about 4 characters of English text, so 1,000 tokens is roughly 750 words. Mistral counts tokens with its own tokenizer, so the same text can be a different number of tokens.
How Codestral 2508 compares
- For a typical request, Codestral 2508 is cheaper than 80% of the other models on apicost.app.
- GPT-5.6 Luna from OpenAI costs $0.2 input and $1.2 output per million tokens, so a typical request is $0.0008: about the same price as Codestral 2508.
- Claude Haiku 5.5 from Anthropic costs $0.1 input and $0.5 output per million tokens, so a typical request is $0.00035: 2.1× cheaper than Codestral 2508.
- Gemini 3.1 Flash Lite from Google Gemini costs $0.25 input and $1.5 output per million tokens, so a typical request is $0.001: 1.3× the price of Codestral 2508.
Codestral 2508 price history
Codestral 2508 has cost $0.3 per million input tokens and $0.9 per million output tokens since apicost.app started tracking prices on October 22, 2026.
Every LLM API price increase, cut, new and retired model, dated: LLM API price changes.
Models with a similar price
| Model | Provider | Input / 1M | Cached input / 1M | Output / 1M | Typical request |
|---|---|---|---|---|---|
| DeepSeek V3.2 | DeepSeek | $0.28 | $0.028 | $0.4 | $0.00048 |
| GPT-5.6 Luna | OpenAI | $0.2 | $0.02 | $1.2 | $0.0008 |
| DeepSeek V3 | DeepSeek | $0.27 | $0.07 | $1.1 | $0.00082 |
| GPT-5.4 nano | OpenAI | $0.2 | $0.02 | $1.25 | $0.000825 |
| DeepSeek V4 1 Flash 1017 | Mistral | $0.3 | $0.007 | $1.2 | $0.0009 |
| DeepSeek Flash | DeepSeek | $0.3 | $0.006 | $1.2 | $0.0009 |
| DeepSeek V4 Flash | DeepSeek | $0.3 | $0.006 | $1.2 | $0.0009 |
| Gemini 3.1 Flash Lite | Google Gemini | $0.25 | $0.025 | $1.5 | $0.001 |
Other Mistral models
- DeepSeek V4 1 Flash 1017 $0.3 / $1.2
- Labs Leanstral 1.5.1 $0 / $0
- Ministral 3 3B 2512 $0.1 / $0.1
- Ministral 3 8B 2512 $0.15 / $0.15
- Ministral 3 14B 2512 $0.2 / $0.2
- Ministral 3B 2512 $0.1 / $0.1
- Ministral 8B 2512 $0.15 / $0.15
- Ministral 14B 2512 $0.2 / $0.2
- Mistral Large 3 $0.5 / $1.5
- Mistral Large 4 $0.7 / $2.1
- Mistral Large 2512 $0.5 / $1.5
- Mistral Medium $1.5 / $7.5
- Mistral Small $0.1 / $0.3
- Mistral Tiny $0.25 / $0.25
- Open Mistral Nemo $0.3 / $0.3
Every Mistral model side by side, with batch, caching and long-context prices: Mistral API pricing. Ways to pay less: batch API, prompt caching, the cheapest models.
Questions and answers
How much does the Codestral 2508 API cost?
Mistral charges $0.3 per million input tokens and $0.9 per million output tokens for Codestral 2508 (codestral-2508), and $0.03 per million cached input tokens. A typical request of 1,000 input and 500 output tokens costs $0.00075.
Has the Codestral 2508 API price changed?
No. Codestral 2508 has cost $0.3 per million input tokens and $0.9 per million output tokens since apicost.app started tracking prices on October 22, 2026.
Is there a cheaper way to use Codestral 2508?
Prompt caching lowers the price of input that repeats across requests to $0.03 per million tokens.
What is the context window of Codestral 2508?
Codestral 2508 accepts up to 128,000 input tokens, roughly 96,000 words of English, and writes up to 128,000 output tokens per response. Filling the whole context window once costs $0.0384 in input tokens.
Is Codestral 2508 cheaper than GPT-5.6 Luna?
They cost about the same. GPT-5.6 Luna from OpenAI costs $0.2 input and $1.2 output per million tokens, so a typical request is $0.0008: about the same price as Codestral 2508.
Source: Mistral pricing, via the LiteLLM price list.