Skip to content

deepseek-ai/DeepSeek-V4-Pro

deepinfra/deepseek-ai-deepseek-v4-pro

April 2026 preview of DeepSeek-V4-Pro, the large tier of the V4 family: a 1.6T-parameter MoE with 49B active, 1M-token context and hybrid compressed attention, aimed at reasoning, coding and long-running agents. Replaced by the GA release V4-Pro-0813.

API
curl "$AUDIOLAB_API_URL/v1/chat/completions" \
  -H "Authorization: Bearer $AUDIOLAB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "deepinfra/deepseek-ai-deepseek-v4-pro",
  "messages": [
    {
      "role": "user",
      "content": "Help me plan my next project."
    }
  ],
  "max_tokens": 256
}'
Input Price
$1.105 / 1M tokens
Output Price
$2.21 / 1M tokens
Context
1M tokens
Output Cap
16.4K tokens

Capabilities

Explore what deepseek-ai/DeepSeek-V4-Pro supports, then use the API section for a request tailored to this model.

Max tokens

Model Information

Provider
DeepInfra
Product
Language Models
Release Date
Apr 24, 2026
Data Policy
Not specified
Region
US
Input
Text
Output
Text
Provider Documentation

Playground

Try deepseek-ai/DeepSeek-V4-Pro by DeepInfra. Requests use the selected workspace’s credits and API pricing.

deepseek-ai/DeepSeek-V4-ProCredits —
deepseek-ai/DeepSeek-V4-Pro
⌘ / Ctrl + Enter to send

Providers

Compare available endpoints, pricing, and context limits for deepseek-ai/DeepSeek-V4-Pro.

ProviderContextOutput CapInput PriceOutput PriceEndpoint
DeepInfra1M tokens16.4K tokens$1.105 / 1M tokens$2.21 / 1M tokens
deepseek-ai/DeepSeek-V4-Pro

Prices are catalog rates. Your workspace’s estimate and endpoint pricing determine the final charge.

Input and Output Limits

Formats and limits AudioLab enforces on each request.

LimitValue
Max input tokens1048576
Max output tokens16384

Provider Notes

General LLM inference is an integration preview. Managed billing and deployment acceptance must be enabled before requests can be served.

Performance

Status

Current catalog availability. Your workspace’s access is checked separately before a request runs.

Getting Started

Use your workspace API key and the exact model identifier below. Set the API URL to the endpoint shown in your workspace and keep credentials on your server.

API
curl "$AUDIOLAB_API_URL/v1/chat/completions" \
  -H "Authorization: Bearer $AUDIOLAB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "deepinfra/deepseek-ai-deepseek-v4-pro",
  "messages": [
    {
      "role": "user",
      "content": "Help me plan my next project."
    }
  ],
  "max_tokens": 256
}'
Read the Endpoint Reference

Request Parameters

Available parameters depend on the provider and request format. The endpoint reference explains accepted values and required fields.

ParameterDetails
modeldeepinfra/deepseek-ai-deepseek-v4-pro — Required model identifier.
max_tokensView Accepted Values

Input and Output Limits

Formats and limits AudioLab enforces on each request.

LimitValue
Max input tokens1048576
Max output tokens16384

Similar Models

Explore more language models and compare their capabilities.

ModelContextInput PriceOutput Price
inclusionAI/Ling-3.0-flash-VLDeepInfra131.1K tokens$0.051 / 1M tokens$0.153 / 1M tokens
ibm-granite/granite-4.2-8bDeepInfra131.1K tokens$0.051 / 1M tokens$0.2125 / 1M tokens
DeepSeek V4 Pro 0813DeepInfra1M tokens$1.105 / 1M tokens$2.21 / 1M tokens
Muse Glimmer 30BDeepInfra131.1K tokens$0.255 / 1M tokens$1.02 / 1M tokens
inclusionAI/Ling-3.0-flashDeepInfra131.1K tokens$0.051 / 1M tokens$0.153 / 1M tokens
DeepSeek V4 Flash 0731DeepInfra1M tokens$0.051 / 1M tokens$0.153 / 1M tokens
View All Language Models