Available now
DeepSeek
deepseek-v4-flash
DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...
TextReasoningToolsOpen Weights1MCache
Input$0.20/ 1M
Output$0.40/ 1M
Endpointsopenai, anthropic
Capabilities
ReasoningToolsCacheStructured
Modalities
Input
text
Output
text
Quick stats
Context window1M
Max output131.1K
TokenizerDeepSeek
Quantizationfp4
Hugging Facedeepseek-ai/DeepSeek-V4-Flash
Performance
Loading performance data...
Supported parameters
| Parameter | Always | Default |
|---|---|---|
| frequency_penalty | — | (do not send) |
| include_reasoning | — | |
| logit_bias | — | — |
| logprobs | — | — |
| max_tokens | — | |
| min_p | — | — |
| presence_penalty | — | (do not send) |
| reasoning | — | |
| repetition_penalty | — | (do not send) |
| response_format | — | — |
| seed | — | — |
| stop | — | — |
| structured_outputs | — | — |
| temperature | (do not send) | |
| tool_choice | — | — |
| tools | — | — |
| top_k | — | (do not send) |
| top_logprobs | — | — |
| top_p | (do not send) |
§ 01
Pricing
| Input price | $0.20 · 1M tokens |
| Output price | $0.40 · 1M tokens |
| Compatible endpoints | openai, anthropic |
| Vendor | DeepSeek |
§ 02
Call deepseek-v4-flash from your code
Point any OpenAI-compatible SDK at UnoRouter and request the model by name. Replace YOUR_API_KEY with a real key from your dashboard.
bash
curl https://api.unorouter.ai/v1/chat/completions \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek-v4-flash",
"messages": [{"role": "user", "content": "Hello!"}]
}'§ 03
Frequently asked questions
How much does deepseek-v4-flash cost per 1M tokens?
Input is priced at $0.20 per 1M tokens, output at $0.40 per 1M tokens. Billing is per token, no rounding to batch sizes.
How do I access deepseek-v4-flash via API?
Send requests to the UnoRouter /v1/chat/completions endpoint with model=deepseek-v4-flash. Any OpenAI-compatible client library works. Authentication uses a standard Bearer token.
§ 04
Similar models
Try deepseek-v4-flash now
Create an API key and start making requests in under a minute.