anoman

Mistral

Codestral 2508

modelcodestral-2508-global
BudgetStableStreamingToolsBatchLong contextGlobal

Context

256K

Input / 1M tokens

Rp 5.544

Output / 1M tokens

Rp 16.632

Cached input / 1M tokens

Rp 1.303

Cache write / 1M tokens

โ€” (bills at input price)

About this model

Codestral 2508

Codestral 2508 is a model by Mistral, available through the Anoman AI OpenAI-compatible API with a 256K-token context window. It costs Rp 5.544 per 1M input tokens and Rp 16.632 per 1M output tokens. Usable on: Free (from credit or balance), Pro, Enterprise.

Key facts

Maker
Mistral
Context window
256K tokens
Max output
205K tokens
Lane
Guarded: the provider has confirmed it does not train on your data
Modality
Text
Input price
Rp 5.544 per 1M tokens
Output price
Rp 16.632 per 1M tokens
Processing region(s)
global
Precision
Never routed to providers that report below FP8; some providers do not report precision
Usable on
Free (from credit or balance), Pro, Enterprise
Price comparison
Priced below 151 of 188 pro-band guarded models on Anoman (blended price: 1 part input to 3 parts output).

More models by Mistral

Code example

Chat completion with Codestral 2508

from openai import OpenAI

client = OpenAI(
    base_url="https://api.anoman.io/v1",
    api_key="anm-sk-..."
)

response = client.chat.completions.create(
    model="codestral-2508-global",
    messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)

Alternatives

Similar models in our catalog

Same maker first, then the closest price to Codestral 2508 in the Anoman catalog.

Use Codestral 2508 through Anoman.