DeepSeek API
DeepSeek's high-performance language models with OpenAI-compatible API
Data & Privacy
HQ:CN
Safety identifier:Not forwarded
API Training:Yes
Prompt Logging:Yes
Retention:Unknown
Available Models
DeepSeek V4.1 Flash
deepseek
deepseek-v4.1-flashStreaming
Vision
Tools
Reasoning
JSON Output
DeepSeek
Context: 1.1M
Time-based pricing
Input
$0.3
/M tokens
Cached
$0.006
/M tokens
Output
$1.2
/M tokens
Peak: Monday–Friday, 01:00–04:00 and 06:00–10:00 UTC.
Off-peak: Monday–Friday outside those hours, plus all day Saturday and Sunday UTC.
DeepSeek V4 Pro
deepseek
deepseek-v4-proStreaming
Tools
Reasoning
JSON Output
DeepSeek
Context: 1.1M
Time-based pricing
Input
$1.32
/M tokens
Cached
$0.044
/M tokens
Output
$3.96
/M tokens
Peak: Monday–Friday, 01:00–04:00 and 06:00–10:00 UTC.
Off-peak: Monday–Friday outside those hours, plus all day Saturday and Sunday UTC.
DeepSeek V3.1
deepseek
deepseek-v3.1Streaming
Vision
Tools
DeepSeek
Context: 128k
Input
$0.56
/M tokens
Cached
$0.07
/M tokens
Output
$1.68
/M tokens
DeepSeek R1 (0528)
deepseek
deepseek-r1-0528Streaming
DeepSeek
Context: 64k
Input
$0.55
/M tokens
Cached
—
/M tokens
Output
$2.19
/M tokens
Create an LLM Gateway API key and point any OpenAI-compatible SDK at https://api.llmgateway.io/v1. Set the model to deepseek-v4.1-flash. On pay-as-you-go keys, deepseek/deepseek-v4.1-flash pins every request to DeepSeek; DevPass coding plans do not support provider pinning. You do not need a separate DeepSeek account or SDK.