codestral-2508
Codestral 2508 is Mistral’s coding model released at the end of July 2025. It specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation.
Pricing: Input 60 credits / 1M tokens (≈ $0.30), Output 180 credits / 1M tokens (≈ $0.90).
Prices updated
How can I help you today?
This demo page does not include the full memory features of the client. For the complete experience, please use the client or the CLI.
More AI models from Mistral AI
Latest and popular AI models
Codestral 2508 API on ModelFold
Codestral 2508 is Mistral’s coding model released at the end of July 2025. It specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation. Try Codestral 2508 in the ModelFold Playground, then call it from your own code through an OpenAI-compatible chat completions API.
What Is the Codestral 2508 API
Codestral 2508 at a glance
Codestral 2508 is a chat model from Mistral AI. It accepts text and files (such as PDF) as input and returns text, with a context window of up to 256K tokens.
Use it without hosting anything
On ModelFold you call Codestral 2508 with a single API key — no model weights to download and no inference servers to run. The same key also works for the other chat, image, video and audio models on ModelFold.
Core Capabilities of Codestral 2508
Up to 256K tokens of context
Keep long conversations, large documents and sizeable code in a single request, so the model can reason over the full material instead of fragments.
Understands files (such as PDF)
Besides text, Codestral 2508 accepts files (such as PDF) as input, so a single request can combine instructions with visual or other media.
Function calling
Codestral 2508 supports tool (function) calling: describe your functions in the request and the model returns structured calls your code can run — the basis for agents and integrations.
Structured outputs
Ask for JSON that follows a schema (response_format), which makes extraction, classification and system integrations more reliable.
How to Use Codestral 2508 on ModelFold
- 1
Step 1: Try it in the Playground
Open the Playground at the top of this page, type a prompt and see how Codestral 2508 responds before writing any code.
- 2
Step 2: Create an API key
Sign in to ModelFold and create an API key in the console. Keep it secret and send it as a Bearer token.
- 3
Step 3: Send a request
Call POST https://modelfold.ai/v1/chat/completions with "model": "codestral-2508" and your messages. Existing OpenAI-compatible SDKs work by changing the base URL and key.
- ✓
Step 4: Ship and monitor
Integrate the response into your product and check token usage and spend for every call in the console logs.
What You Can Build with Codestral 2508
AI coding assistants
Generate, explain, debug and refactor code, review pull requests and work through multi-file changes in developer tools and IDE plugins.
Low-latency experiences
Power chat interfaces, autocomplete and interactive tools where users expect fast responses.
High-volume pipelines
Run classification, extraction, rewriting and batch jobs at scale where cost per request matters.
Tool-calling backends
Route requests, call functions and chain API calls as the worker model inside larger agent systems.
Frequently Asked Questions
What is Codestral 2508?⌄
Codestral 2508 is Mistral’s coding model released at the end of July 2025. It specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correction and test generation.
Which inputs does Codestral 2508 support?⌄
Codestral 2508 accepts text and files (such as PDF) and returns text. Through ModelFold you send text messages; documents attached in the Playground are converted to text.
How long is the context window of Codestral 2508?⌄
Up to 256K tokens, shared between your input and the model’s output.
Does Codestral 2508 support function calling?⌄
Yes. Codestral 2508 supports tools / function calling through the standard tools parameter of the chat completions API.
How is Codestral 2508 billed on ModelFold?⌄
Pay as you go by tokens: input and output tokens are charged at the per-million-token prices shown on this page. There is no monthly fee, and failed requests are not charged.
How do I call Codestral 2508 through the API?⌄
Send a POST request to https://modelfold.ai/v1/chat/completions with "model": "codestral-2508", using your ModelFold API key as the Bearer token.
| Input | 60 credits 1M tokens≈ $0.30 |
| Output | 180 credits 1M tokens≈ $0.90 |
Billed per token: input and output are priced separately, and thinking tokens count as output. The Playground charges exactly the same way.
Read API docs →AI Agents · Claude Code / Cursor / Trae →curl https://modelfold.ai/v1/chat/completions \
-H "Authorization: Bearer $MODELFOLD_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"codestral-2508","messages":[{"role":"user","content":"Hello"}]}'