Deepseek Prover V2 671B
deepseek/deepseek-prover-v2-671b
DeepSeek Launches Open-Source Model DeepSeek-Prover-V2-671B, Specializing in Mathematical Theorem Proving
The new model employs a Mixture of Experts (MoE) architecture and is trained using the Lean 4 framework for formal reasoning. With 671 billion parameters, it leverages reinforcement learning and large-scale synthetic data to significantly enhance automated theorem-proving capabilities.
功能
Serverless API
文档
deepseek/deepseek-prover-v2-671b is available via Novita's serverless API, where you pay per token. There are several ways to call the API, including OpenAI-compatible endpoints with exceptional reasoning performance.
可用的 Serverless
立即运行查询，仅按用量付费
输入$0.7 / M Tokens
输出$2.5 / M Tokens
使用以下代码示例与我们的 API 集成：
1from openai import OpenAI
2
3client = OpenAI(
4 api_key="<Your API Key>",
5 base_url="https://api.novita.ai/openai"
6)
7
8response = client.chat.completions.create(
9 model="deepseek/deepseek-prover-v2-671b",
10 messages=[
11 {"role": "system", "content": "You are a helpful assistant."},
12 {"role": "user", "content": "Hello, how are you?"}
13 ],
14 max_tokens=160000,
15 temperature=0.7
16)
17
18print(response.choices[0].message.content)信息
提供商
DeepSeek
量化
fp8
支持的功能
上下文长度
160000
最大输出
160000
Serverless
支持
输入能力
text
输出能力
text
构建生产级 AI 所需的一切。
200+ 个模型、按需 GPUs 和安全的智能体运行时——统一在一个 API 下。免费开始，随业务增长灵活扩展。