DeepSeek V4 Flash 0731
Live·DeepSeekmodel·Served by DeepInfra
Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding
Providers
Every request goes to the cheapest healthy route and fails over to the next.
Loading the routes…
Latency and throughput appear after the first hourly test request to each provider, or once this model has traffic here. Every request goes to the cheapest healthy route and fails over to the next.
Pricing
What a call costs through Rapid Router, at the route requests go to.
What it supports
- Tool calling (function calling)
- JSON mode and structured output
- Image input (vision)
- Audio input
- Extended reasoning
- Streaming responses
- OpenAI SDK, Anthropic SDK and any OpenAI-compatible client
Price in rupees
What DeepSeek V4 Flash 0731 costs through Rapid Router, converted at today's billing rate (₹98.25 per $). Top up with UPI or a card; a GST invoice follows every recharge.
| Rupees | US dollars | |
|---|---|---|
| 1M input tokens | ₹5.89 | $0.060 |
| 1M output tokens | ₹17.68 | $0.180 |
| 1K input tokens | ₹0.006 | $0.00006 |
| 1K output tokens | ₹0.018 | $0.00018 |
| A typical exchange: 1,300 tokens in, 400 out | ₹0.015 | $0.00015 |
Make a request
The same request you send to OpenAI today, pointed at https://rapidrouter.ai/api/v1.
curl https://rapidrouter.ai/api/v1/chat/completions \
-H "Authorization: Bearer $RAPIDROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek/deepseek-v4-flash-0731",
"messages": [{ "role": "user", "content": "Hello" }]
}'Frequently asked
What does DeepSeek V4 Flash 0731 cost in rupees?
Through Rapid Router, DeepSeek V4 Flash 0731 (deepseek/deepseek-v4-flash-0731) costs ₹5.89 per million input tokens and ₹17.68 per million output tokens, billed in Indian rupees from a prepaid balance. In dollars these are the provider's list prices, exactly what your balance is debited; the rupee figures are converted at our billing rate, the market rate plus a 4% currency margin. Our platform fee is charged once, when you buy credits.
How do I call DeepSeek V4 Flash 0731 through an OpenAI-compatible API?
Point any OpenAI-compatible client at https://rapidrouter.ai/api/v1 with a Rapid Router API key and set the model to deepseek/deepseek-v4-flash-0731. The chat completions endpoint is https://rapidrouter.ai/api/v1/chat/completions.
What is the context window of DeepSeek V4 Flash 0731?
DeepSeek V4 Flash 0731 has a context window of 1,048,576 tokens on Rapid Router, and returns up to 384,000 output tokens per reply.
What can DeepSeek V4 Flash 0731 do?
On Rapid Router, DeepSeek V4 Flash 0731 supports tool calling, JSON mode, extended reasoning.
Can I pay for DeepSeek V4 Flash 0731 in rupees with UPI?
Yes. Rapid Router bills in Indian rupees: top up with UPI or a card, get a GST invoice on every recharge, and DeepSeek V4 Flash 0731 is debited from that balance at the provider's list price per million tokens.
More DeepSeek models
Compare and rank
What a month of your own usage costs on it: cost calculator · every head-to-head: comparisons