Codestral API: Endpoint & Pricing
Codestral brings Mistral conversational intelligence to LLM.API so teams can ship assistants and agents without juggling multiple vendor SDKs.
What is Codestral?
Codestral is a Mistral chat model exposed on LLM.API under id `codestral-2508`. codestral-2508 provided by mistral. It is wired for API access through LLM.API with OpenAI-compatible patterns. Teams use it when they need reliable text generation with text inputs and text outputs over an OpenAI-compatible API.
Can you self-host Codestral?
No. We found no public weights for Codestral on Hugging Face, so there is nothing to download, quantize or serve on your own GPUs: no VRAM budget, no vLLM or GGUF build to plan for. The only way to run it is over an API.
Skip the deploy — use LLM.API as your endpoint
No GPUs, no quantization trade-offs. Same model, OpenAI-compatible, with custom volume discounts on request.
Providers
LLM.API routes Codestral to the providers below, with discounted effective rates versus list price.
List price by provider
InputOutputProvider list prices; the LLM.API discount applies on top.
| Provider | Pricing | Context | Capabilities |
|---|---|---|---|
| in $0.3; out $0.9 per 1M tokens | 256K tokens | tools, streaming, JSON, structured |
Prices and availability from the LLMAPI catalogue, updated nightly. Last updated 11 Oct 2026.
Try this model
Test Codestral right here — free to start.
Suggestions for your first prompt
Code snippet
Call Codestral through the OpenAI-compatible API — POST /v1/chat/completions.
Switching from OpenAI? Change 2 lines.
- base_url="https://api.openai.com/v1"
- api_key="YOUR_OPENAI_KEY"
+ base_url="https://api.llmapi.ai/v1"
+ api_key="YOUR_LLMAPI_KEY"Everything else stays the same — SDK, message format, tools, streaming. Set model to codestral-2508 and the call runs unchanged.
curl https://api.llmapi.ai/v1/chat/completions \
-H "Authorization: Bearer $LLMAPI_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "codestral-2508",
"messages": [
{"role": "user", "content": "Give me three crisp launch checklist items."}
]
}'from openai import OpenAI
client = OpenAI(
api_key="YOUR_LLMAPI_KEY",
base_url="https://api.llmapi.ai/v1",
)
resp = client.chat.completions.create(
model="codestral-2508",
messages=[
{"role": "system", "content": "You are a precise product assistant."},
{"role": "user", "content": "Give me three crisp launch checklist items."},
],
)
print(resp.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({
apiKey: process.env.LLMAPI_KEY,
baseURL: "https://api.llmapi.ai/v1",
});
const resp = await client.chat.completions.create({
model: "codestral-2508",
messages: [
{ role: "user", content: "Give me three crisp launch checklist items." },
],
});
console.log(resp.choices[0].message.content);stream = client.chat.completions.create(
model="codestral-2508",
messages=[{"role": "user", "content": "Write a haiku about latency."}],
stream=True,
)
for chunk in stream:
delta = chunk.choices[0].delta.content
if delta:
print(delta, end="", flush=True){
"model": "codestral-2508",
"messages": [
{"role": "system", "content": "You are a precise product assistant."},
{"role": "user", "content": "Give me three crisp launch checklist items."}
]
}ENDPOINTS
Supported endpoints & features
Base URL https://api.llmapi.ai/v1 · model ID codestral-2508 · OpenAI-compatible.
POST /v1/chat/completionsChat Completions — supported
| Feature | Status | How to set it |
|---|---|---|
| Function calling (tools) | Supported | tools, tool_choice |
| Parallel tool calls | Not supported | parallel_tool_calls |
| JSON mode | Supported | response_format: {"type": "json_object"} |
| Structured outputs | Supported | response_format: {"type": "json_schema", …} |
| Streaming | Supported | stream: true |
| Vision (image input) | Not supported | image_url content parts |
| Web search | Not supported | web_search |
ERRORS
Errors & fallback routing
| Code | What it means | What to do |
|---|---|---|
401 | Missing or invalid API key. | Send Authorization: Bearer YOUR_LLMAPI_KEY and check the key is active. |
429 | Rate limited, or the upstream provider is throttling the request. | Back off and retry with jitter; the gateway also retries the request on another provider where one is available. |
5xx | Upstream provider error or timeout. | Retry; fallback routing sends the retry to the next healthy provider for this model. |
When a provider fails or throttles, the request is routed to the next provider serving this model — the ones listed in the providers table above.
Codestral in production
What the model is good at.
Conversational UX
Maintains coherent multi-turn assistant behavior for product chat surfaces. Tuned to how teams typically call Codestral.
Code assistance
Helps write, explain, refactor, and debug application code across common languages. Tuned to how teams typically call Codestral.
Long-context synthesis
Summarizes and cross-references information across large prompts when context allows. Relevant for `codestral-2508` workloads on LLM.API.
Analytical writing
Produces clear analyses, comparisons, and decision memos from messy source material.
Instruction following
Follows detailed system and user instructions with strong adherence to format and tone.
What you get when you call Codestral through LLM.API.
Unified AI Routing
Reach Codestral and sibling models through one OpenAI-compatible endpoint.
One endpoint, every model.Cost Control
Compare provider price points and keep spend visible as you scale Codestral.
More performance, less spend.Reliability Layer
Practical: Retry and route across configured providers when a single upstream blips.
Never go dark on users.Observability
Trace prompts, tokens, and errors for Codestral alongside the rest of your stack.
See every token, everywhere.Drop-in SDKs
Keep using familiar OpenAI client patterns with base URL https://api.llmapi.ai/v1.
Think tasks, not models.Model Breadth
Swap Codestral for chat, media, or embedding alternatives without rewriting auth.
Scale from 1 to millions.
When to Use — When NOT to Use
Use it if...
- You need provider failover options exposed for this model id (Codestral)
- Your prompts benefit from the model's family strengths (reasoning, speed, or cost) (Codestral)
- You need a general-purpose text model for assistants, agents, or content workflows (Codestral)
- You want OpenAI-compatible chat completions through a single LLM.API key (Codestral)
Avoid if...
- Your use case depends on unpublished proprietary benchmarks not listed here
- You require on-prem only deployment with no cloud inference
- You need guaranteed real-time hard latency SLAs without benchmarking the provider
- You need pure embedding, OCR, or media generation instead of chat
COMMUNITY
What developers say about Mistral models
Summarised from publicly published developer and community reviews of this model family. Opinions are the sources’, not LLM.API’s, and may not be specific to Codestral.
- Long-form paid reviews rate Mistral Large around 4/5 and call it the best European-hosted option when data residency matters.
- For pure coding, community consensus is that it trails the top US and Chinese models, though it is considered fully usable as an assistant.
- Developers pick it mainly for EU hosting, predictable pricing, and open-weight siblings rather than leaderboard position.
SOURCES
Frequently Asked Questions
What modalities does Codestral support?
Codestral accepts text and produces text according to its architecture metadata on LLM.API.
Which providers serve Codestral?
LLM.API currently lists: mistral. Availability can vary by region and account.
What is the context length for Codestral?
Reported context for Codestral is 256K tokens. Always verify the active provider row if multiple providers are listed.
How is Codestral priced on LLM.API?
Listed pricing metadata shows: In $0.3 / 1M tokens · Out $0.9 / 1M tokens. LLM.API may offer discounted effective rates (illustrative ~30% callout vs list when available).. Confirm live rates in the LLM.API dashboard or docs before production budgeting.
Where is the canonical page for Codestral?
https://llmapi.ai/models/mistralai-codestral-2508/
Is Codestral a chat model?
Yes—Codestral is exposed as a chat/completions-style endpoint on LLM.API.
What is Codestral?
codestral-2508 provided by mistral. It is wired for API access through LLM.API with OpenAI-compatible patterns. On LLM.API it is addressed as `codestral-2508`.
How do I call Codestral via API?
Send OpenAI-compatible requests to https://api.llmapi.ai/v1 with model "codestral-2508" and your LLM.API key. See the code snippet on this page.
What are limitations of Codestral?
Like other API models, Codestral can be wrong, incomplete, or uneven on edge cases. Validate outputs for high-stakes use. Media/OCR/STT models additionally depend on input quality.
Can I use tools or structured outputs with Codestral?
Tool and/or structured-output flags appear on one or more providers for this model—confirm in the providers table.
When should I choose Codestral?
You need provider failover options exposed for this model id — especially when you specifically need Codestral.
COMPARE
Competitive Models
MiniMax M2.7
Input$0.3 / 1MOutput$1.2 / 1MList price per 1M tokens.
$0.3 in / $1.2 out per 1M tokens, 204,800 context — the closest current alternative to Codestral.
Kimi K2.5
Input$0.356 / 1MOutput$1.98 / 1MList price per 1M tokens.
$0.356 in / $1.98 out per 1M tokens, 262,144 context — the closest current alternative to Codestral.
Qwen3.8 27B
Input$0.425 / 1MOutput$2.55 / 1MList price per 1M tokens.
$0.425 in / $2.55 out per 1M tokens, 262,144 context — the closest current alternative to Codestral.
Get one key to every model
Swap your API key. Keep your code.