/

/

Codestral 2508

Codestral 2508

Codestral 2508 is a Mistral AI model available in SteelEngine. It supports a 128k token context window. Pricing starts at $0.3/1M input tokens and $0.9/1M output tokens. Key capabilities include Temperature 0-1, Tool choice, Structured outputs.

Coding model for writing, reviewing, and refactoring code in agent workflows. Handles 128k tokens of context. Pinned snapshot 2508 for reproducible behavior.

INPUT / 1M

$0.3

CACHED INPUT / 1M

$0.03

OUTPUT / 1M

$0.9

CONTEXT WINDOW

128k

MAX OUTPUT

Not published

PRICING

What Codestral 2508 costs to run.

List prices in USD per 1M tokens. Cached input applies when a request reuses a prompt the provider has already cached.

01 / INPUT

$0.3

per 1M input tokens

02 / CACHED INPUT

$0.03

per 1M cached input tokens

03 / OUTPUT

$0.9

per 1M output tokens

LONG CONTEXT

SUPPORTED CAPABILITIES

What Codestral 2508 supports.

Capabilities show up as model settings on SteelEngine workflow blocks and agents, so teams can tune each step without changing providers.

CAPABILITIES

Temperature 0-1, Tool choice, Structured outputs

CONTEXT WINDOW

128k

MAX OUTPUT TOKENS

Not published

MODEL ID

codestral-2508

PROVIDER

Mistral AI

BUILD WITH STEELENGINE

Put Codestral 2508 to work.

Use this model in deterministic workflow steps or production agents, with approvals, guardrails, and a full audit trail around every call.