deepseek/deepseek-prover-v2-671b

deepseek-ai/Deepseek-Prover-V2-671B

Context

32768

Input

text

Output

text

Tool calling

Not listed

About this model

DeepSeek-Prover-v2-671b is a 671B-parameter hybrid dense-MoE model specialized in mathematical theorem proving and formal reasoning, featuring 128 experts with 4-6 active per token. Optimized with FP8 quantization for efficient large-scale inference.

Compare Text Models

Input modalities

text

Accepted as model input

Providers

Available routing options for this model through OneInfer.

Novita

Available

Input tokens

$0.700 / 1M tokens

Output tokens

$2.500 / 1M tokens

Routing

OneInfer optimized

Pricing

Current OneInfer pricing for this model.

Usage	Price
Input tokens	$0.700 / 1M tokens
Output tokens	$2.500 / 1M tokens

Performance

Published evaluation results associated with this model.

Theorem Proving

MiniF2F-Isabelle56.3

Lean Proof51.7

TheoremBench71.2

IMO Problems45.8

Mathematical Reasoning

MATH62.5

GSM8K89.1

GPQA42.3

Formal Verification

CoqGym58.9

Isabelle Benchmark63.4

HolStep67.1

General Reasoning

MMLU-Math79.6

ARC-Challenge86.3

LogiQA81.7

API example

Refer Documentation

curl https://api.oneinfer.ai/v1/ula/chat/completions \
  -H "Authorization: Bearer $ONEINFER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-ai/Deepseek-Prover-V2-671B",
    "messages": [
      { "role": "user", "content": "Hello!" }
    ]
  }'