MistralText / ChatCodestral 2508 API: Mistral AI's chat / LLM model, one key away
Codestral 2508 via the ApexApi gateway
Mistral's code model, tuned for completion, refactoring and review rather than open-ended chat. 256K of context for repository-scale work. Call it through ApexApi's unified, OpenAI-compatible API with one `ak-` key, alongside every other model in the catalog. It supports a 256,000-token context window, tool / function calling, and streaming responses. Pricing is $0.36 input and $1.08 output per 1M tokens, billed pay-per-use from your credit balance with no subscription.
Codestral 2508 is served through ApexApi's unified, OpenAI-compatible API. One key, one format, with smart routing and automatic failover. Provider: Mistral AI.
Why Codestral 2508
256,000-token context
Reason over long documents, codebases, and multi-turn history in a single request.
Tool & function calling
Structured outputs and tool orchestration for agentic and automation workloads.
OpenAI-compatible
Drop-in with any OpenAI SDK. Change the base URL and key, keep your code.
Specifications
- Modality
- chat
- Context window
- 256K tokens
- Max output
- —
- Streaming
- Yes
- Tool / function calling
- Yes
- Vision input
- —
Codestral 2508: measured reliability
From real calls ApexApi made to Codestral 2508 during health sweeps over the last 30 days. Our own measurements, not vendor claims.
- Success rate
- 100%
- Avg latency
- 3.7s
- Calls measured
- 1
- Last checked
- Aug 30
See how Codestral 2508 compares against every model we serve on the model rankings.
Codestral 2508 pricing
- A million tokens in and a million out costs $1.44 here, all-in.
- That makes it the 21st cheapest of the 81 chat models we serve, ranked on output price.
- It runs 8.3× cheaper than Mistral Medium 3.5, the pricier option from the same maker.
Getting started with Codestral 2508
OpenAI-compatible. Point your client at ApexApi, swap your key, and call it. No new SDK to learn.
from openai import OpenAI
client = OpenAI(
base_url="https://api.apexapi.dev/v1",
api_key="<YOUR_APEXAPI_KEY>",
)
response = client.chat.completions.create(
model="mistralai/codestral-2508",
messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)Codestral 2508 use cases
What teams build with Codestral 2508 on ApexApi.
Agents & automation
Tool-using agents that orchestrate multi-step workflows and call APIs.
Coding assistants
Code generation, refactoring, reviews, and multi-file reasoning.
RAG & knowledge apps
Summarization and long-document Q&A grounded in your own data.
Codestral 2508 vs other models
How it compares, and on ApexApi you can switch between any of them with a single string change, same key, same endpoint.
Codestral 2508 vs Claude Opus 4.7
Compare Codestral 2508 against this model on price, capabilities, and latency. A/B them with a single key on ApexApi.
Learn more about Claude Opus 4.7 API →Codestral 2508 vs GPT-5.5
Compare Codestral 2508 against this model on price, capabilities, and latency. A/B them with a single key on ApexApi.
Learn more about GPT-5.5 API →Codestral 2508 vs Gemini 3.1 Pro Preview
Compare Codestral 2508 against this model on price, capabilities, and latency. A/B them with a single key on ApexApi.
Learn more about Gemini 3.1 Pro Preview API →Codestral 2508 API: FAQ
How do I call Codestral 2508 through ApexApi?
Create an ApexApi key, point your client at https://api.apexapi.dev/v1, and POST to /v1/chat/completions with the model set to `mistralai/codestral-2508`. The API is OpenAI-compatible, so an existing OpenAI SDK works once you change the base URL and key.
How much does Codestral 2508 cost on ApexApi?
$0.36 per million input tokens and $1.08 per million output tokens, all-in with no separate platform fee. You buy credits and pay per call, with no subscription or minimum.
What is the context window for Codestral 2508?
256,000 tokens.
Does Codestral 2508 support tool calling and image input?
Codestral 2508 supports tool / function calling and streaming responses, and it does not support image (vision) input.
What should I use instead of Codestral 2508?
From the same maker, Ministral 3 14B 2512 costs less for lighter work and Mistral Large 3 2512 is the step up when this one falls short. Switching is one string: both run on the same endpoint and the same key, so there is nothing to re-integrate.
Ready to build with Codestral 2508?
One API key. Every major AI model. Pay only for what you use.
Get your API key, free to start