Skip to main content
Core.Today
|
DeepSeekMediumUltra

DeepSeek V4 Pro

DeepSeek's strongest V4 model (checkpoint V4-Pro-0813). Advanced reasoning with thinking mode on by default, a 1M-token context window, and discounted cache reads - still far cheaper than comparable frontier models.

808/1,616credits
input / output ยท per 1M tokens
Strongest reasoning in the DeepSeek family
1M context window, up to 384K output tokens
Thinking mode on by default (switchable per request)
OpenAI-compatible API (chat completions)
Context cache hits billed at a steep discount

Run it right now

Test this model instantly in the Console Playground โ€” no code required

Sign in to try

Use with AI Assistant

Copy usage instructions for Claude, ChatGPT, or other AI

Model Specifications

Context Window
1.0M
tokens
Max Output
384K
tokens
Training Cutoff
2025-05
Compatible SDK
OpenAI

Capabilities

Vision
Function Calling
Streaming
JSON Mode
System Prompt

Token Pricing (per 1M tokens)

Token TypeCreditsUSD Equivalent
Input Tokens808$0.54
Output Tokens1,616$1.08
Cached Tokens6.7$0.00

* 1,500 credits โ‰ˆ $1 (actual charges may vary based on usage)

Quick Start

curl -X POST "https://api.core.today/llm/deepseek/v1/chat/completions" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer cdt_your_api_key" \
  -d '{
  "model": "deepseek-v4-pro",
  "messages": [
    {
      "role": "user",
      "content": "Prove that the sum of two even numbers is even."
    }
  ],
  "max_tokens": 2048
}'

Parameters

ParameterTypeRequiredDefaultDescription
modelstringYes-Model ID, e.g. "deepseek-v4-pro".
messagesarrayYes-Chat messages in OpenAI format (system/user/assistant roles).
temperaturenumberNo0.7Sampling temperature (0-2).
max_tokensintegerNo2048Maximum completion tokens.
streambooleanNofalseStream the response as server-sent events.

Examples

Chat completion

OpenAI-compatible chat completion request

curl -X POST "https://api.core.today/llm/deepseek/v1/chat/completions" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer cdt_your_api_key" \
  -d '{
  "model": "deepseek-v4-pro",
  "messages": [
    {
      "role": "user",
      "content": "Prove that the sum of two even numbers is even."
    }
  ],
  "max_tokens": 2048
}'

Tips & Best Practices

1Works with the OpenAI SDK - set base_url to https://ai.api.core.today/llm/deepseek/v1
2Thinking mode is on by default - disable it per request for latency-sensitive calls
3Cache hits are billed at a steep discount - reuse long system prompts and shared prefixes
4Anthropic-format endpoint is not supported through the gateway - use the OpenAI format

Use Cases

Complex reasoning, math, and code generation
Long-document analysis with the 1M context
Cost-efficient alternative to frontier reasoning models