DeepSeek-V4.1-Flash-1017 (preview)

Munito AI serves DeepSeek-V4.1-Flash-1017 on the global host through an OpenAI- and Anthropic-compatible API.

This model is a preview. Munito AI can change or remove it without notice.

Use this model ID in the model field of a request:

deepseek-ai/deepseek-v4.1-flash-1017

APIsCopy Anchor Link

• Chat Completions: POST /chat/completions
• Responses: POST /responses
• Messages (Anthropic): POST /messages

PricesCopy Anchor Link

Prices are in USD for each million tokens, in the standard tier. The global host bills the global price. A regional host or a regional model ID bills the price of its region.

See Models and pricing for the priority and flex tiers, and for how a request is billed.

Rate limitsCopy Anchor Link

Base limits per organization.

See Rate limits for dynamic limits, headers and retries.

Request custom limits through Support in the console.

RegionsCopy Anchor Link

Call this model on the global host, api.munito.ai. The global host can process a request in any region.

See Regions for the base URLs and the rules for stored data.

ExampleCopy Anchor Link

export MUNITO_API_KEY="munitoai_..."
curl https://api.munito.ai/inference/v1/chat/completions \
  -H "Authorization: Bearer $MUNITO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-ai/deepseek-v4.1-flash-1017",
    "messages": [{"role": "user", "content": "Hello!"}],
    "max_tokens": 256
  }'

# pip install openai
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.munito.ai/inference/v1",
    api_key=os.environ["MUNITO_API_KEY"],
)
response = client.chat.completions.create(
    model="deepseek-ai/deepseek-v4.1-flash-1017",
    messages=[{"role": "user", "content": "Hello!"}],
    max_tokens=256,
)
print(response.choices[0].message.content)

The same model ID works with the Anthropic client. See Send your first request.