DeepSeek V4.1 Flash
POST
/openai/v1/responses
WARNING
TIP
deepseek-v4-1-flash now serves the DeepSeek-V4.1-Flash-1017 release (October 17, 2026). The model name, endpoint and request format are unchanged, so existing integrations keep working without any changes. The new release improves coding and reasoning performance while producing shorter outputs and completing tasks faster.DeepSeek V4.1 Flash API is an OpenAI Responses–compatible endpoint that accepts a plain string or a structured input array, thinks deeply by default, and supports function calling, image understanding, and structured JSON output.
Thinking
reasoning.effort and thinking.type do the same job, so you only need one of them.CAUTION
max_output_tokens, temperature and top_p are not supported on this model and have no effect.Tools & input
Error handling
{"code": ..., "msg": "..."} (for example 401 invalid API key, 402 insufficient credits, 429 rate limited; the HTTP status may still be 200) or as {"error": {"type": "...", "message": "..."}}.Request
Body Params application/jsonRequired
Responses
Request Request Example
Shell
JavaScript
Java
Swift
curl --location 'https://api.kie.ai/openai/v1/responses' \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '{
"model": "deepseek-v4-1-flash",
"stream": false,
"input": [
{
"role": "user",
"content": [
{
"type": "input_text",
"text": "What is in this image?"
},
{
"type": "input_image",
"image_url": "https://example.com/demo.png"
}
]
}
]
}'Response Response Example
200 - Success
{
"id": "resp_xxx",
"object": "response",
"created_at": 1790128600,
"model": "deepseek-v4-1-flash",
"status": "completed",
"output": [
{
"type": "reasoning",
"id": "rs_xxx",
"status": "completed",
"summary": [
{
"type": "summary_text",
"text": "The user is asking what is in the image. It shows a cat sitting on a windowsill."
}
]
},
{
"type": "message",
"id": "msg_xxx",
"role": "assistant",
"status": "completed",
"content": [
{
"type": "output_text",
"text": "The image shows a cat sitting on a windowsill.",
"annotations": []
}
]
}
],
"usage": {
"input_tokens": 38,
"input_tokens_details": {
"cached_tokens": 0
},
"output_tokens": 36,
"output_tokens_details": {
"reasoning_tokens": 35
},
"total_tokens": 74
},
"credits_consumed": 0.01
}