deepseek-v4-pro
DeepSeek·Token-based
DeepSeek 的 deepseek-v4-pro 模型，支持文本输入和文本输出。支持推理、工具调用、结构化输出。
textfunction_callingtoolsjson_modestructured_outputreasoningcontext:1048576
- Starting price
- Input / Output · 1M
- Context
- 1M
- Maximum input window
- Max output
- 393.2K
- Maximum tokens per response
- Modalities
- →
- Released
- Apr 2026
Pricing by Supplier
official
官方接口直连
Input$1.33/ 1M
Output$4/ 1M
Cache Read$0.044/ 1M
Cache Write (5m)$2.175/ 1M
Cache Write (1h)$3.48/ 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
Cache Write (5m)$2.175$2.001/ 1M
Cache Write (1h)$3.48$3.2016/ 1M
Alibaba
阿里巴巴百炼官方
Input$1.33/ 1M
Output$4/ 1M
Cache Read$0.044/ 1M
Cache Write (5m)$2.175/ 1M
Cache Write (1h)$3.48/ 1M
Moonshot
Kimi 官方渠道
Input$1.33/ 1M
Output$4/ 1M
Cache Read$0.044/ 1M
Cache Write (5m)$2.175/ 1M
Cache Write (1h)$3.48/ 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
Cache Write (5m)$2.175$0.97875/ 1M
Cache Write (1h)$3.48$1.566/ 1M
Capabilities / Supported modalities
Function callingToolsJSON modeStructured outputReasoning
Input
Output
Provider & data privacy
Provider
DeepSeekDocs
Tokenizer
DeepSeek tokenizer (BPE)License
DeepSeek LicenseOpen weights
Data retention31 daysNot used for upstream training by default
Performance
API access
Code samples
RequestPOST
/v1/chat/completionsExample request
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 |
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
| 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 | 650 | 260K | 13K |
| Moonshot | 570 | 229K | 11K |
| official | 800 | 319K | 16K |
| Volcengine | 610 | 245K | 12K |
| 火山引擎特价 | 340 | 135K | 6.7K |
RPM = requests per minute, TPM = tokens per minute, RPD = requests per day. Limits apply per token group.
API access questions
Everything you need to decide before creating an account.