DeepSeek
Latency—
Throughput—
Upload rate—
Context length1M tokens
Max output384K tokens
Input price$0.15per 1M tokens
Output price$0.6per 1M tokens
Cache read—per 1M tokens
Cache write—per 1M tokens
Console
Sign in
/deepseek/deepseek-v4.1-flash
DeepSeek: DeepSeek V4.1 Flash
DeepSeek V4.1 Flash is DeepSeek's high-efficiency multimodal reasoning model designed for fast inference, coding, agentic workflows, tool use, and visual understanding. It supports both thinking and non-thinking modes, native image understanding, a 1M-token context window, and up to 384K output tokens.
Modetext、image → text
Input price$0.15 per M tokens
Output price$0.6 per M tokens
Context length1M tokens
Listed at2026-09-10T00:00:00Z
Performance
Avg TPS—
Avg latency—
Avg success rate—
TPS—
TTFT—
Latency—
Success rate—
Success rate
Speed
Code Example
curl ${API_BASE_URL}/v1/messages \
-H "Authorization: Bearer <YOUR_API_KEY>" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek-v4.1-flash",
"messages": [
{
"role": "user",
"content": "Hello"
}
]
}'Replace <YOUR_API_KEY> with the API key generated on your token management page.
Authentication
All requests must include the Authorization: Bearer <TOKEN> header.
Endpoint Path
POST
Anthropic MessagesSupported Parameters
ParameterTypeDefaultDescription
integer-Maximum number of output tokens. DeepSeek V4.1 Flash supports up to 384K output tokens.
booleanfalseWhether to stream the response incrementally.
stringhighControls reasoning effort. Supported levels include low, high, and max.
Rate Limits
GroupRPMTPMRPD
RPM = requests per minute, TPM = tokens per minute, RPD = requests per day. Limits apply by token group.
Pricing
ProviderBilling typePrice summary
DeepSeek0%
Expression
Input price$0.15per 1M tokens
Completion price$0.6per 1M tokens
Cache read price$—per 1M tokens
Cache write price$—per 1M tokens
DeepSeek0%
Expression
Input price$0.15per 1M tokens
Completion price$0.6per 1M tokens
Cache read price$—per 1M tokens
Cache write price$—per 1M tokens