DeepSeek V4 Pro
deepseek-v4-proCompare deepseek-v4-pro API pricing, supported endpoints, capabilities and access options on Modelsell.
- Starting price
- Input / Output · 1M
- Context
- 1M
- Maximum input window
- Max output
- 384K
- Maximum tokens per response
- Modalities
- →
Pricing by Supplier
Capabilities / Supported modalities
Provider & data privacy
DeepSeek tokenizer (BPE)Performance
Benchmarks
Scores on standardized evaluations. Higher percentages are better — and rank percentile shows
Metrics sourced fromArtificial Analysis 2026-09-30·DeepSeek V4 Pro
This model is not included in the current benchmark snapshot.
Missing models or measurements are not zero scores.
Benchmark charts preserve the source model selection and reasoning settings. Missing models or measurements are not zero scores, and benchmark cost or speed is not this site’s service commitment.
About DeepSeek V4 Pro
面向需要深入分析的文本任务
DeepSeek V4 Pro 适合复杂推理、软件工程和长流程智能体工作。它可以阅读较大范围的代码与文档，比较多个方案中的约束，整理大量资料之间的关系，并为多步骤任务提出实施路径。适合研发团队、研究人员和需要综合长材料的业务分析场景。
把长上下文用于理解关系
处理大型代码库时，可以先让模型建立模块关系，再沿调用路径分析一个具体问题；处理研究资料时，可以要求它比较证据、指出冲突，而不是简单拼接摘要。长上下文提供了放入更多材料的空间，但任务目标、材料组织和出处标记仍然重要。
代码与数学问题应给出必要条件，并要求结果经过测试、计算或反例检查。复杂方案则应说明成本、依赖和失败条件，让结论可以被实际评估。模型生成的推理与建议是工作起点，验证步骤需要真正执行。
配合工具推进多步骤工作
通过应用提供的工具调用，V4 Pro可以参与检索、运行代码和自动化处理。每一轮工具结果应保留在上下文里，让后续行动依据实际状态更新。它以文本输入和文本输出为主，图像中的信息应先转成清楚的文字材料。固定模型、任务样本与请求设置进行评估，有助于比较不同工作流的实际效果。
Use cases and prompting
大型项目分析示例
“以下是缓存模块、数据库访问层与调用方代码。请找出缓存失效后可能读到旧数据的路径，按调用顺序列出依据。提出两个修复方案，比较一致性、性能和改动范围，并给出能暴露问题的并发验证方法。”
代码较多时，保留文件名和函数位置，并说明需要分析的具体行为。
长文档放得下，为什么仍会漏掉信息？
材料没有优先级、重复背景过多或问题过宽都会影响分析。先给出任务索引与关键约束，再要求结论对应具体材料。
怎样判断代码建议是否可用？
要求给出验证条件和失败案例，并实际运行检查。只看到一段合理的代码，不代表兼容性和边界问题已经解决。
API access
API documentation
Code samples
/v1/chat/completions| Parameter | Type | Default / range | Description |
|---|---|---|---|
temperature | number | = 10 ~ 2 | Sampling temperature; lower is more deterministic |
top_p | number | = 10 ~ 1 | Nucleus sampling probability mass |
max_tokens | integer | >= 1 | Maximum number of tokens in the response |
frequency_penalty | number | = 0-2 ~ 2 | Penalises repetition of frequent tokens |
presence_penalty | number | = 0-2 ~ 2 | Encourages introducing new topics |
stop | array | — | Up to 4 strings that stop generation |
seed | integer | — | Deterministic sampling seed (best-effort) |
n | integer | = 1>= 1 | Number of completions to generate |
stream | boolean | = false | Stream tokens via Server-Sent Events |
response_format | object | — | Force JSON object or schema-conforming output |
tools | array | — | Tool / function declarations the model may call |
tool_choice | string | autononerequired | Tool-choice policy or specific tool name |
logprobs | boolean | = false | Return per-token log probabilities |
top_logprobs | integer | 0 ~ 20 | Number of top log probabilities returned per token |
logit_bias | object | — | Per-token logit bias map |
user | string | — | End-user identifier for abuse monitoring |
Replace <YOUR_API_KEY> with the API key from your token settings.
Authentication
All requests must include Authorization: Bearer <TOKEN> header. Anthropic-formatted endpoints accept the x-api-key header instead.
Generate tokens from the Tokens page; you can scope them to specific models, groups, IPs, and rate-limits.
Supported parameters
| Parameter | Type | Default / range | Description |
|---|---|---|---|
temperature | number | = 10 ~ 2 | Sampling temperature; lower is more deterministic |
top_p | number | = 10 ~ 1 | Nucleus sampling probability mass |
max_tokens | integer | >= 1 | Maximum number of tokens in the response |
frequency_penalty | number | = 0-2 ~ 2 | Penalises repetition of frequent tokens |
presence_penalty | number | = 0-2 ~ 2 | Encourages introducing new topics |
stop | array | — | Up to 4 strings that stop generation |
seed | integer | — | Deterministic sampling seed (best-effort) |
n | integer | = 1>= 1 | Number of completions to generate |
stream | boolean | = false | Stream tokens via Server-Sent Events |
response_format | object | — | Force JSON object or schema-conforming output |
tools | array | — | Tool / function declarations the model may call |
tool_choice | string | autononerequired | Tool-choice policy or specific tool name |
logprobs | boolean | = false | Return per-token log probabilities |
top_logprobs | integer | 0 ~ 20 | Number of top log probabilities returned per token |
logit_bias | object | — | Per-token logit bias map |
user | string | — | End-user identifier for abuse monitoring |
Rate limits
| Supplier | RPM | TPM | RPD |
|---|---|---|---|
| Alibaba | Unlimited | Unlimited | Unlimited |
| Moonshot | Unlimited | Unlimited | Unlimited |
| official | Unlimited | Unlimited | Unlimited |
| Volcengine | Unlimited | Unlimited | Unlimited |
| 火山引擎特价 | Unlimited | Unlimited | Unlimited |
No restriction
Frequently asked questions about deepseek-v4-pro
What is deepseek-v4-pro?
Compare deepseek-v4-pro API pricing, supported endpoints, capabilities and access options on Modelsell.
How do I call deepseek-v4-pro?
Create an API key with access to deepseek-v4-pro, then use the exact model ID and a supported endpoint from the API access section. Request fields depend on the selected endpoint.
How is deepseek-v4-pro priced?
Pricing depends on the selected provider group and the model billing unit. The current input, output, request, or media prices are shown on this page before sign-up.
What is the context window of deepseek-v4-pro?
The model catalog lists a context window of 1048576 tokens. Check the selected endpoint for request limits.
What is the maximum output of deepseek-v4-pro?
The model catalog lists a maximum output of 384000 tokens. Your request settings may set a lower limit.
How should I evaluate deepseek-v4-pro for my project?
Start with the use cases and prompting guidance on this page, then evaluate the model with representative inputs from your project.