Moduck

Mistral: Codestral 25.08

Mistral code model for low-latency completion, fill-in-the-middle, and code generation

Model lab
Mistral
Model family
codestral
Modalitiestext → text
Context window128,000
Maximum output8,192
InputUSD 0.24 / 1M tokens
OutputUSD 0.72 / 1M tokens
Try nowView docs

Quickstart

Use your Moduck API Key, set the API base URL to https://api.moduck.ai/v1, and set the model parameter to moduck/mistral-ai/codestral-2508.

import os
import requests

base_url = "https://api.moduck.ai/v1"
api_key = os.environ["MODUCK_API_KEY"]
model_id = "moduck/mistral-ai/codestral-2508"

response = requests.post(
    f"{base_url}/chat/completions",
    headers={
        "Authorization": f"Bearer {api_key}",
        "Content-Type": "application/json",
    },
    json={
        "model": model_id,
        "messages": [{"role": "user", "content": "Hello!"}],
        "stream": False,
    },
    timeout=60,
)
response.raise_for_status()
print(response.json())

Use the familiar OpenAI-style chat request format to make model integration easier.

Codestral 25.08 API Pricing

TypePrice information
InputUSD 0.24 / 1M tokens
OutputUSD 0.72 / 1M tokens
Cached inputUSD 0.024 / 1M tokens

Performance

Performance trends

Throughput87.2 tok/sCurrent
Time to first token1.2 sCurrent
End-to-end latency7.2 sCurrent
Throughput
Current87.2 tok/s
Window average90.0 tok/s
Time to first token
Current1.2 s
Window average1.4 s
End-to-end latency
Current7.2 s
Window average7.5 s
Tail latency (P99)
Current15.3 s
Window average16.9 s
Prompt cache hit rate
Current26.4%
Window average23.3%
Error rate
Current0.0%
Window average0.1%

Availability

Uptime100%At least one provider responded
Availability100%Requests actually served
Error rate0%Share of failed requests
Served requests, hour by hour
24 hours agoNow

Codestral 25.08 Compare models

ModelInput priceOutput priceContext windowCapabilities
Codestral 25.08This pageUSD 0.24 / 1M tokensUSD 0.72 / 1M tokens128,000Text output · Tool calling
Codestral (latest)USD 0.24 / 1M tokensUSD 0.72 / 1M tokens256,000Text output · Tool calling
Codestral-22B-v0.1USD 0.24 / 1M tokens · Context ≤ 128000 tokens · Maximum output 4000 tokensUSD 0.72 / 1M tokens · Context ≤ 128000 tokens · Maximum output 4000 tokens32,768Text output
Devstral 2USD 0.32 / 1M tokensUSD 1.6 / 1M tokens262,144Text output · Tool calling
Devstral 2 (latest)USD 0.32 / 1M tokensUSD 1.6 / 1M tokens262,144Text output · Tool calling

Model specifications

Input
text
Output
text
Context window
128,000
Maximum output
8,192
Release date
2025-07-30
Attachments
No
Reasoning
No
Tool calling
Yes
Structured output
Yes
Temperature setting
Yes
Open weights
No

Frequently asked questions

What is Codestral 25.08 for?

Mistral code model for low-latency completion, fill-in-the-middle, and code generation

What inputs and outputs does Codestral 25.08 support?

Recorded inputs: text; outputs: text.

How is Codestral 25.08 priced?

The pricing table shows the current recorded Moduck price. For example: Input USD 0.24 / 1M tokens; Output USD 0.72 / 1M tokens. See the pricing table for all units, variants, and conditions.

What specifications are recorded for Codestral 25.08?

Current model records list Context window 128,000 tokens; Maximum output 8,192 tokens.

What model parameter does the Quickstart use?

The example uses moduck/mistral-ai/codestral-2508. This is a cataloged Moduck public or reserved ID; check your account’s available models before calling it.

Can I call this model through the Moduck API now?

This page has no verified Moduck API call for this model. A Quickstart example or reserved ID does not establish access; check the models available to your account.