DeepSeek

DeepSeek V4 Pro 0813

DeepSeekToken-based
Alias:deepseek-v4-pro-0813
Create API Key

Compare deepseek-v4-pro-0813 API pricing, supported endpoints, capabilities and access options on Modelsell.

textfunction_callingtoolsjson_modestructured_outputreasoningcontext:1048576
Starting price
Input / Output · 1M
Context
1M
Maximum input window
Max output
393.2K
Maximum tokens per response
Modalities
→

Pricing by Supplier

official
官方接口直连
Input$1.33/ 1M
Output$4/ 1M
Cache Read$0.044/ 1M
Volcengine
-8%
火山引擎官方接口
Input$1.33$1.2236/ 1M
Output$4$3.68/ 1M
Cache Read$0.044$0.04048/ 1M
火山引擎特价
-55%
火山引擎官方接口,高并发,活动特价
Input$1.33$0.5985/ 1M
Output$4$1.8/ 1M
Cache Read$0.044$0.0198/ 1M

Capabilities / Supported modalities

ReasoningFunction callingToolsJSON mode
Input
Output

Provider & data privacy

Provider
DeepSeekDocs
Tokenizer
DeepSeek tokenizer (BPE)
License
DeepSeek LicenseOpen weights
Data retention64 daysNot used for upstream training by default

Performance

Benchmarks

Scores on standardized evaluations. Higher percentages are better — and rank percentile shows

Metrics sourced fromArtificial Analysis 2026-09-30·DeepSeek V4 Pro 0813

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 0813

将复杂工程目标分步落地

DeepSeek V4 Pro 0813 是面向推理与智能体任务的正式版本,适合处理需要多次分析、操作和修正的软件工作。你可以让它阅读现有项目、理解需求与限制,安排实现顺序,再结合测试反馈持续改进,而不必把任务拆成互不关联的单次问答。

它使用文字输入和输出,可处理源码、日志、技术文档与业务规则。较大的上下文空间便于保留跨模块信息,适合检查复杂依赖、追踪故障路径和准备详细方案。图片、音频或视频中的内容,需要先转换为合适的文本资料再分析。

在编程任务中,明确验收行为比笼统要求“优化代码”更有帮助。例如,说明哪些请求应保持兼容、哪些失败必须能恢复、哪些文件允许改动。让它先检查当前实现,再给出最小方案,并用实际测试确认修改结果,可以使任务更接近可审阅的工程交付。

它支持思考与非思考模式,推理强度可选 low、high 和 max。工具调用可以连接文件检索、命令执行与业务查询,JSON 输出可以承载任务状态、审查意见和提取结果。调用端需要配置工具权限与执行环境;模型提出操作后,应依据真实返回结果决定是否继续。

使用中常问

适合长时间的开发任务吗? 可以分阶段推进,每阶段保存约束、已改动内容和验证结果,使后续步骤延续同一目标。

怎样避免过度修改? 明确必须保持的接口与行为,要求所有改动关联验收项,并单独列出可选重构建议。

Use cases and prompting

用验收行为约束工程实现

准备项目入口、相关代码与失败样本,再描述目标。

请给这个 webhook 消费服务增加幂等处理。
阅读现有事务和重试逻辑,先说明重复消息可能造成的状态变化。
实现最小方案,保证并发重复投递只执行一次业务更新,并验证失败后可以重试。
保留现有事件格式和查询接口;补充相应测试,最终报告改动与验证证据。

复杂任务可提高推理强度并预留输出预算。工具调用失败时保留错误信息,让模型重新判断;结束前审查差异、运行相关测试,并记录仍需人工确认的业务条件。

API access

API documentation

Code samples

RequestPOST/v1/chat/completions
Example request
Parameters
ParameterTypeDefault / rangeDescription
temperature
number
=10 ~ 2
Sampling temperature; lower is more deterministic
top_p
number
=10 ~ 1
Nucleus sampling probability mass
max_tokens
integer>= 1Maximum 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
integer0 ~ 20Number 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

Generation parameters
ParameterTypeDefault / rangeDescription
temperature
number
=10 ~ 2
Sampling temperature; lower is more deterministic
top_p
number
=10 ~ 1
Nucleus sampling probability mass
max_tokens
integer>= 1Maximum 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
integer0 ~ 20Number 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

SupplierRPMTPMRPD
officialUnlimitedUnlimitedUnlimited
VolcengineUnlimitedUnlimitedUnlimited
火山引擎特价UnlimitedUnlimitedUnlimited

No restriction

Frequently asked questions about deepseek-v4-pro-0813

What is deepseek-v4-pro-0813?

Compare deepseek-v4-pro-0813 API pricing, supported endpoints, capabilities and access options on Modelsell.

How do I call deepseek-v4-pro-0813?

Create an API key with access to deepseek-v4-pro-0813, 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-0813 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-0813?

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-0813?

The model catalog lists a maximum output of 393216 tokens. Your request settings may set a lower limit.

How should I evaluate deepseek-v4-pro-0813 for my project?

Start with the use cases and prompting guidance on this page, then evaluate the model with representative inputs from your project.