novita

deepseek/deepseek-v4-pro

Context

1M

Input

text

Output

text

Tool calling

Supported

About this model

DeepSeek-V4-Pro is a flagship Mixture-of-Experts (MoE) language model with 862B total parameters (49B activated) and a 1-million-token context window. It features a Hybrid Attention Architecture combining Compressed Sparse Attention and Heavily Compressed Attention for efficient long-context processing. With multiple distinct reasoning modes (such as Think Max for maximum reasoning effort), it is built for advanced mathematical reasoning, software engineering, tool use scenarios, and complex long-horizon agentic workflows.

Capabilities

text

Available through the unified API

Quick start

View API docs
curl https://api.oneinfer.ai/v1/chat/completions \
  -H "Authorization: Bearer $ONEINFER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "b348948916bf49c58cb451cec8f119f4",
    "messages": [
      { "role": "user", "content": "Hello!" }
    ]
  }'

Providers

Available routing options for this model through OneInfer.

novita

b348948916bf49c58cb451cec8f119f4

Available

Input

$1.600 / 1M

Output

$3.200 / 1M

Routing

OneInfer optimized

Pricing

Current OneInfer pricing for this model.

UsagePrice
Input tokens$1.600 / 1M
Output tokens$3.200 / 1M

Performance

Published evaluation results associated with this model.

Reasoning

MATH 50094.5
GPQA Diamond77.2
AIME 202482.5

Coding

SWE-bench Verified68.4
LiveCodeBench81.3

Agentic

WebArena72
OSWorld48.5

API example

curl https://api.oneinfer.ai/v1/chat/completions \
  -H "Authorization: Bearer $ONEINFER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "b348948916bf49c58cb451cec8f119f4",
    "messages": [
      { "role": "user", "content": "Hello!" }
    ]
  }'