DeepSeek V4 Pro API

Model details

Context window

1.1M tokens

Max output

393K tokens

Input

Text

Output

Text

Capabilities

Reasoning, Tool calling, Streaming, JSON output

Interfaces

OpenAI-style Chat Completions, Anthropic-style Messages, OpenAI-style Responses

Why teams pick it

• DeepSeek V4 Pro for OpenAI-style Chat Completions, Anthropic-style Messages, OpenAI-style Responses.

Call DeepSeek V4 Pro

DeepSeek V4 Pro answers on any of the APIs below — pick the one your code already speaks and just swap in your Inferray key.

curl https://api.inferray.com/v1/chat/completions \
  -H "Authorization: Bearer inferray_..." \
  -H "Content-Type: application/json" \
  -d '{
  "model": "deepseek-v4-pro",
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ]
}'

curl https://api.inferray.com/v1/messages \
  -H "Authorization: Bearer inferray_..." \
  -H "Content-Type: application/json" \
  -d '{
  "model": "deepseek-v4-pro",
  "max_tokens": 1024,
  "messages": [
    {
      "role": "user",
      "content": "Hello"
    }
  ]
}'

curl https://api.inferray.com/v1/responses \
  -H "Authorization: Bearer inferray_..." \
  -H "Content-Type: application/json" \
  -d '{
  "model": "deepseek-v4-pro",
  "input": "Hello"
}'

Use DeepSeek V4 Pro in your tools

Every coding agent below has a setup guide. Set the model to deepseek-v4-pro.

• Claude Code
• Codex
• opencode
• Cline
• Roo Code
• Aider
• Continue

More from DeepSeek

Alternatives to DeepSeek V4 Pro

• GLM-4.5GLM-4.5 for OpenAI-style Chat Completions, Anthropic-style Messages, OpenAI-style Responses.Z.ai
• MiniMax M3Multimodal long-context inference with sparse attention.MiniMax
• Nemotron 3 Ultra 550BNemotron 3 Ultra 550B for OpenAI-style Chat Completions, Anthropic-style Messages, OpenAI-style Responses.NVIDIA

Questions about this model

How much does the DeepSeek V4 Pro API cost?

DeepSeek V4 Pro costs $0.66 per 1M input tokens and $1.98 per 1M output tokens on Inferray, and cached input is $0.022 per 1M. That is the list price, with no gateway fee on top.

Is there a free tier for DeepSeek V4 Pro?

No. You add credit and pay DeepSeek V4 Pro's list rate for each request — seats, projects, and API keys are free, and pay-as-you-go credit never expires.

Am I charged for failed requests?

No. A request that fails without returning a result is not billed. If a response fails part-way, the tokens already processed before the failure are charged.

Is DeepSeek V4 Pro included in Token Plans?

No. DeepSeek V4 Pro is pay-as-you-go only; Token Plans cover the other text models in the catalog.

Can I use DeepSeek V4 Pro in Claude Code?

Yes. Set ANTHROPIC_BASE_URL to https://api.inferray.com, ANTHROPIC_AUTH_TOKEN to your Inferray key, and ANTHROPIC_MODEL to deepseek-v4-pro. The same key works in Codex, opencode, Cline, and other agents.

Does DeepSeek V4 Pro support tool calling and vision?

DeepSeek V4 Pro supports tool calling, reasoning, JSON output and streaming on Inferray. It does not take image input.

Is it the real DeepSeek V4 Pro?

Yes. A request for deepseek-v4-pro is answered by DeepSeek V4 Pro from DeepSeek, billed at its published list price. Inferray never substitutes a different or smaller model.