Muke Labs

DeepSeek V4 Pro

Vendor: DeepSeek

Text

Latest DeepSeek Pro model for advanced reasoning and coding

Typical latency
2-5s
Reference inputs
None
toolId
deepseek-v4-pro

Input modes

chat

Parameters

ParameterTypeDefaultValuesNotes
temperatureslider0.70–2Creativity level: 0=focused, 2=creative
max_tokensselectnormalnormal | extendedNormal fits most edits; Extended allows longer, more complex edit instructions.

Pricing

Pricing will be published shortly — contact us for early access rates

Prices last updated: —

API example

POST /v1/generations — deepseek-v4-pro
curl -X POST https://api.mukelabs.com/v1/generations \
  -H "Authorization: Bearer $MUKE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "toolId": "deepseek-v4-pro",
    "inputMode": "chat",
    "prompt": "your prompt here",
    "params": { "max_tokens": "normal" },
    "references": [],
    "idempotencyKey": "a-unique-key-per-task",
    "subjectId": "your-user-id"
  }'

FAQ

How do I call DeepSeek V4 Pro on Muke Labs?
Submit POST /v1/generations with toolId "deepseek-v4-pro" and one of its input modes (chat), then poll GET /v1/generations/{jobId} for the result.
What does DeepSeek V4 Pro cost?
Public pricing for this model is being finalized — contact us for early access rates. All tasks are billed from your prepaid USD balance and failed tasks refund automatically.
What happens if a task fails?
The job returns status "failed" with a typed error code, and its charge is returned to your balance automatically.
Where do I get an API key?
Create one in the developer portal (https://portal.muke.name), then send it as a Bearer token on every request.

Related models

Text

DeepSeek V3.1 Terminus

DeepSeek

Older DeepSeek V3.1 route kept for generation comparison

chat
Text

DeepSeek V3.2

DeepSeek

Previous DeepSeek generation for economical chat and coding

chat
Text

DeepSeek V4 Flash

DeepSeek

Frontier-class reasoning for high-frequency tasks

chat
Text

DeepSeek V4.1 Flash

DeepSeek

DeepSeek V4.1 Flash

chat