DeepSeek V4.1 Flash
DeepSeek V4.1 Flash: very low-cost fast model with a 1M-token context.
Model ID: deepseek-v4.1-flash
Last 7 days · not enough recent requests for stats yet.
Playground
Credits for max_tokens are held first, then settled to the actual usage.
Start a conversation. Replies stream in and are billed by actual token usage.
Pricing by provider
Prices are per unit; requests without a provider are routed to the cheapest provider that supports your parameters.
| Provider | Option | Price (USD) | Credits |
|---|---|---|---|
| Vercel AI Gateway | All options | 15 / 1M input tokens | |
| All options | 59 / 1M output tokens | ||
| OpenRouter | All options | 2 / 1M input tokens | |
| All options | 98 / 1M output tokens |
API reference
Endpoints
Base URL: https://01router.com/api/v1
/chat/completionsChat completion (OpenAI-compatible, stream or not)Authentication
Send your API key as a Bearer token. Requests are billed to the key owner's credits.
Authorization: Bearer sk_xxxxxxxxxxxxxxxxRequest body
| Name | Type | Required | Description |
|---|---|---|---|
| model | string | Yes | "deepseek-v4.1-flash" |
| provider | string | No | Pin a provider; omit to auto-route to the cheapest. One of: vercel | openrouter |
| messages | array | Yes | OpenAI-format messages, each with role and content. |
| stream | boolean | No | true returns an SSE stream. |
| max_tokens | integer | No | Output token cap; credits are pre-held for it (default 4096). |
Example request
curl https://01router.com/api/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek-v4.1-flash",
"provider": "vercel",
"messages": [{ "role": "user", "content": "Hello!" }],
"stream": false
}'Response
Chat models (GPT, Claude, Gemini, Grok, DeepSeek…) use the OpenAI Chat Completions format, so the official OpenAI SDKs work with base URL https://01router.com/api/v1. Set "stream": true for server-sent events. Credits for the prompt plus max_tokens (4,096 when unset) are held first, then settled to the real token usage once the reply ends; the same request id appears in the X-Gateway-Request-Id header and the task log.
{
"id": "chatcmpl-…",
"object": "chat.completion",
"model": "deepseek-v4.1-flash",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "Hello! How can I help?"
},
"finish_reason": "stop"
}
],
"usage": {
"prompt_tokens": 9,
"completion_tokens": 8,
"total_tokens": 17
}
}Auth, routing, billing and error codes are covered in Gateway API reference