How much does deepseek-v4-flash-0731 cost per 1M tokens?

Input is priced at $0.22 per 1M tokens, output at $0.43 per 1M tokens. Billing is per token, no rounding to batch sizes.

How do I access deepseek-v4-flash-0731 via API?

Send requests to the UnoRouter /v1/chat/completions endpoint with model=deepseek-v4-flash-0731. Any OpenAI-compatible client library works. Authentication uses a standard Bearer token.

DeepSeek: deepseek-v4-flash-0731

Name: deepseek-v4-flash-0731
Brand: DeepSeek

deepseek-v4-flash-0731

1.0M context384K outReasoningToolsParallel toolsCacheStructured

Released Jul 31, 2026Updated Jul 31, 2026

DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows.

Tokenizer DeepSeekQuantization fp8

Pricing

Supported parameters

All providers = every upstream serving this model supports it. Some providers = depends on which upstream handles the request. Default = the value sent when you leave the parameter unset.

Parameter	Providers	Default
frequency_penalty	All providers	-
include_reasoning	All providers	-
logprobs	All providers	-
max_tokens	All providers	-
presence_penalty	All providers	-
reasoning	All providers	-
reasoning_effort	All providers	-
response_format	All providers	-
stop	All providers	-
temperature	All providers	-
tool_choice	All providers	-
tools	All providers	-
top_logprobs	All providers	-
top_p	All providers	-

DeepSeek: deepseek-v4-flash-0731

Pricing

Uptime

Performance

Usage & Ranking

Supported parameters

Frequently asked questions

Similar models