Back to models
retired

DeepSeek: DeepSeek V4 Pro 0423

deepseek/deepseek-v4-pro

Prices

Input

$1.32 per 1M tokens

unverified · disputed
Input (cache write)

$0.00 per 1M tokens

low
Input (cached read)

$0.044 per 1M tokens

unverified · disputed
Output

$3.96 per 1M tokens

unverified · disputed

Also available on

The same model, sold by someone else. The price above is the maker's own.

48 sales channels for this model.
ChannelWhatPrice
Microsoft AzureInput$1.74 per 1M tokens
Output$3.48 per 1M tokens
Microsoft Azure · azure-aiInput$1.74 per 1M tokens
Input (cached read)$0.145 per 1M tokens
Output$3.48 per 1M tokens
DatabricksInput$1.32 per 1M tokens
Input (cache write)$1.32 per 1M tokens
Input (cached read)$0.132 per 1M tokens
Output$3.96 per 1M tokens
Cloudflare Workers AIInput$1.32 per 1M tokens
Input (cached read)$0.044 per 1M tokens
Output$3.96 per 1M tokens
Fireworks AI · fireworks-aiInput$1.32 per 1M tokens
Input (cached read, priority)$0.60 per 1M tokens
Input (cached read)$0.044 per 1M tokens
Input (priority)$1.20 per 1M tokens
Output$3.96 per 1M tokens
Output (priority)$1.20 per 1M tokens
Alibaba Model StudioInput$2.40 per 1M tokens
Input (cached read)$0.20 per 1M tokens
Output$4.80 per 1M tokens
Alibaba Model Studio · alibaba-cnInput$0.435 per 1M tokens
Input (cached read)$0.003625 per 1M tokens
Output$0.87 per 1M tokens
OpenRouter · deepseekInput$0.2088 per 1M tokens
Input (cached read)$0.0174 per 1M tokens
Output$0.4176 per 1M tokens
OpenRouterInput$0.2088 per 1M tokens
Input (cached read)$0.0174 per 1M tokens
Output$0.4176 per 1M tokens
Token plan · alibaba-token-planInput$0.00 per 1M tokens
Input (cache write)$0.00 per 1M tokens
Input (cached read)$0.00 per 1M tokens
Output$0.00 per 1M tokens
Token plan · alibaba-token-plan-cnInput$0.00 per 1M tokens
Input (cache write)$0.00 per 1M tokens
Input (cached read)$0.00 per 1M tokens
Output$0.00 per 1M tokens
Other · abacusInput$1.74 per 1M tokens
Input (cached read)$0.15 per 1M tokens
Output$3.48 per 1M tokens
Other · aiandInput$1.00 per 1M tokens
Input (cached read)$0.25 per 1M tokens
Output$2.50 per 1M tokens
Other · arceeInput$1.74 per 1M tokens
Input (cached read)$0.20 per 1M tokens
Output$3.48 per 1M tokens
Other · arcee-aiInput$1.74 per 1M tokens
Input (cached read)$0.20 per 1M tokens
Output$3.48 per 1M tokens
Other · basetenInput$1.74 per 1M tokens
Input (cached read)$0.145 per 1M tokens
Output$3.48 per 1M tokens
Other · cloudflare-ai-gatewayInput$1.74 per 1M tokens
Input (cached read)$0.145 per 1M tokens
Output$3.48 per 1M tokens
Other · crossmodelInput$1.35 per 1M tokens
Input (cache write)$1.35 per 1M tokens
Input (cached read)$0.045 per 1M tokens
Output$4.05 per 1M tokens
Other · deepinfraInput$1.30 per 1M tokens
Input (cached read)$0.10 per 1M tokens
Output$2.60 per 1M tokens
Other · doublewordInput$1.74 per 1M tokens
Output$3.48 per 1M tokens
Other · edenaiInput$0.66 per 1M tokens
Input (cached read)$0.022 per 1M tokens
Output$1.98 per 1M tokens
Other · fastrouterInput$1.74 per 1M tokens
Output$3.48 per 1M tokens
Other · gmicloudInput$1.39 per 1M tokens
Input (cached read)$0.116 per 1M tokens
Output$2.78 per 1M tokens
Other · hpc-aiInput$1.74 per 1M tokens
Input (cached read)$0.145 per 1M tokens
Output$3.48 per 1M tokens
Other · huggingfaceInput$0.435 per 1M tokens
Input (cached read)$0.003625 per 1M tokens
Output$0.87 per 1M tokens
Other · impossiblInput$1.74 per 1M tokens
Input (cached read)$0.145 per 1M tokens
Output$3.48 per 1M tokens
Other · iteracomputeInput$1.10 per 1M tokens
Input (cached read)$0.11 per 1M tokens
Output$3.30 per 1M tokens
Other · kiloInput$1.60 per 1M tokens
Input (cached read)$0.135 per 1M tokens
Output$3.20 per 1M tokens
Other · llmgateway-providersInput$0.435 per 1M tokens
Input (cached read)$0.003625 per 1M tokens
Output$0.87 per 1M tokens
Other · merge-gatewayInput$1.74 per 1M tokens
Input (cached read)$0.145 per 1M tokens
Output$3.48 per 1M tokens
Other · nano-gptInput$1.10 per 1M tokens
Input (cached read)$0.11 per 1M tokens
Output$2.20 per 1M tokens
Other · nebiusInput$1.75 per 1M tokens
Input (cached read)$0.15 per 1M tokens
Output$3.50 per 1M tokens
Other · novita-aiInput$1.60 per 1M tokens
Input (cached read)$0.135 per 1M tokens
Output$3.20 per 1M tokens
Other · nvidiaInput$0.435 per 1M tokens
Input (cached read)$0.003625 per 1M tokens
Output$0.87 per 1M tokens
Other · ofoxInput$1.32 per 1M tokens
Input (cached read)$0.044 per 1M tokens
Output$3.96 per 1M tokens
Other · openrouterInput$1.60 per 1M tokens
Input (cached read)$0.135 per 1M tokens
Output$3.20 per 1M tokens
Other · orcarouterInput$0.442 per 1M tokens
Input (cached read)$0.06 per 1M tokens
Output$0.884 per 1M tokens
Other · pioneerInput$0.435 per 1M tokens
Input (cache write)$0.435 per 1M tokens
Input (cached read)$0.003625 per 1M tokens
Output$0.87 per 1M tokens
Other · runinfraInput$0.60 per 1M tokens
Input (cached read)$0.03 per 1M tokens
Output$1.90 per 1M tokens
Other · siliconflowInput$1.50 per 1M tokens
Input (cached read)$0.135 per 1M tokens
Output$3.14 per 1M tokens
Other · siliconflow-cnInput$1.74 per 1M tokens
Input (cached read)$0.145 per 1M tokens
Output$3.48 per 1M tokens
Other · temprInput$0.66 per 1M tokens
Input (cached read)$0.022 per 1M tokens
Output$1.98 per 1M tokens
Output (reasoning)$1.98 per 1M tokens
Other · tensorxInput$1.75 per 1M tokens
Input (cache write)$2.19 per 1M tokens
Input (cached read)$0.4375 per 1M tokens
Output$3.50 per 1M tokens
Other · togetheraiInput$1.32 per 1M tokens
Input (cached read)$0.13 per 1M tokens
Output$3.96 per 1M tokens
Other · tokengoInput$0.435 per 1M tokens
Output$0.87 per 1M tokens
Other · vercelInput$0.66 per 1M tokens
Input (cached read)$0.022 per 1M tokens
Output$1.98 per 1M tokens
Other · wandbInput$1.15 per 1M tokens
Input (cached read)$0.20 per 1M tokens
Output$2.55 per 1M tokens
Other · zenmuxInput$0.435 per 1M tokens
Input (cached read)$0.003625 per 1M tokens
Output$0.87 per 1M tokens

Specifications

Provider
deepseek
Context window
1,048,576
Max output tokens
131,072
Open weights
yes
Released
04/24/2026
Retires
08/27/2026
First seen by this tracker

Price history

No price of this model has changed since we started tracking it.

Input
1.32 per 1M tokens, unchanged since 09/14/2026
Input (cached read)
0.044 per 1M tokens, unchanged since 09/14/2026
Output
3.96 per 1M tokens, unchanged since 09/14/2026
Input (cache write)
0 per 1M tokens, unchanged since 09/14/2026

Last updated 10/04/2026, 02:10