Codestral 2508 — Mistral AI | Modeldex

Codestral 2508

Active

Specialized code generation model.

Updated yesterdayStructured data from Modeldex catalog

AgenticLong context

Knowledge cutoff

Mar 31, 2025(1.1 years ago)

API release

Aug 1, 2025(9 months ago)

Not enough benchmark coverage yet for an Intelligence Index — needs at least 3 results across 2 categories.

History

Codestral 2508 became available via the Mistral AI API on 2025-08-01.

Training & availability

Training data has a knowledge cutoff of 2025-03-31 — information about events after that date is unlikely to appear in the model's responses. Mistral AI has not released the underlying model weights — access is via their hosted API only.

Capabilities

Context window: 256K tokens.
Max output: 256K tokens.
Input modalities: text.

Recommended for: agentic, long-context.

Limitations

The knowledge cutoff is 12 months old — this model will not know about recent events, releases, or API changes.
Text-only — cannot process images, audio, or video inputs.

Quick start

Minimal example using the OpenRouter API. Copy, paste, replace the key.

from openai import OpenAI

client = OpenAI(
    base_url="https://openrouter.ai/api/v1",
    api_key="sk-or-...",
)
resp = client.chat.completions.create(
    model="mistral/codestral-2508",
    messages=[{"role": "user", "content": "Explain quantum computing in one sentence."}],
)
print(resp.choices[0].message.content)

Cost calculator

Estimate your monthly bill. Presets are typical workload sizes.

Input tokens / month5.0M

@ $0.3/1M

Output tokens / month2.0M

@ $0.9/1M

Input cost

$1.5

5.0M × $0.3/1M

Output cost

$1.8

2.0M × $0.9/1M

Total / month

$3.3

$39.6 / year

Providers & performance

1 provider

Multi-provider inference routes for this model — sorted by throughput. Latency is time-to-first-token; throughput is output tokens per second. Data from OpenRouter, measured over the last 30 minutes.

Provider	Throughput	Latency (TTFT)	Input $ / 1M	Output $ / 1M	Context	Quant	Supports
Mistral	20tok/s	139ms	$0.3	$0.9	256K	—	tools · json

Integrations & tooling support

Tool calling: Supported
Structured outputs: Supported

Price vs quality

Budget pricing

Priced low — good for high-volume tasks. Quality tier pending more benchmark coverage.