DeepSeek V4 Pro

deepseek/deepseek-v4-pro-0813

Maker: DeepSeek, China
Released: 2026-08-13
Family: deepseek-thinking
Weights: open
Tasks: text.chat, text.reasoning, code
Cheapest offering: DeepSeek, about $0.001254 for a typical text.chat call

Try it in the sandbox Use it from the API

Offerings

Provider	Model id at the provider	Status	Price per 1M tokens	Per-unit prices	Limits	Capabilities (level)
DeepInfra	`deepseek-ai/DeepSeek-V4-Pro-0813`	ga	Input: $1.3 Output: $2.6 Cache read: $0.1 Since 2026-11-03 · models.dev, MIT	none	Context: 1,048,576 tokens Max output: 384,000 tokens	`input.text` claimed `output.text` claimed `tools` claimed `structured_output` claimed `reasoning` claimed `tool_choice` claimed `prompt_caching` claimed
DeepSeek	`deepseek-v4-pro`	ga	Input: $0.66 Output: $1.98 Cache read: $0.022 Reasoning: $1.98 Unverified: sources disagree by more than 5%Since 2026-11-03 · models.dev, MIT	none	Context: 1,048,576 tokens Max output: 393,216 tokens	`input.text` claimed `output.text` claimed `tools` claimed `structured_output` claimed `reasoning` claimed `parallel_tools` claimed `tool_choice` claimed `prompt_caching` claimed
OpenRouter	`deepseek/deepseek-v4-pro-0813`	ga	Input: $0.115 Output: $4 Cache read: $0.11 Unverified: sources disagree by more than 5%Since 2026-11-03 · models.dev, MIT	none	Context: 1,048,576 tokens Max output: 943,718 tokens	`input.text` claimed `output.text` claimed `tools` claimed `structured_output` claimed `reasoning` claimed
Together AI	`deepseek-ai/DeepSeek-V4-Pro-0813`	ga	Input: $1.32 Output: $3.96 Cache read: $0.13 Since 2026-11-03 · models.dev, MIT	none	Context: 1,048,576 tokens Max output: 384,000 tokens	`input.text` claimed `output.text` claimed `tools` claimed `structured_output` claimed `reasoning` claimed `parallel_tools` claimed `tool_choice` claimed `prompt_caching` claimed
Volcengine Ark	`deepseek-v4-pro-ga-260813`	ga	Input: $1.3359 Output: $4.00771 Cache read: $0.04453 Since 2026-11-03 · models.dev, MIT	none	Context: 1,000,000 tokens Max output: 384,000 tokens	`input.text` claimed `output.text` claimed `tools` claimed `structured_output` claimed `reasoning` claimed

Quality scores

Basis	Score (0–1)	Raw	Measured	Source
`epoch:gpqa_diamond`	0.951	0.9167	2026-08-18	Epoch AI, CC-BY-4.0, normalized by Nanner Tech
`epoch:frontiermath`	0.689	0.6456	2026-08-19	Epoch AI, CC-BY-4.0, normalized by Nanner Tech

Aliases

Other names the API accepts for this model.

deepseek-ai/deepseek-v4-pro-0813
deepseek-v4-pro-ga-260813

Use it from the API

Look this model up, or ask for the best model for its task on the providers that offer it. See the quickstart and the API reference.

Look up this model

curl 'https://rhumbdata.com/v1/models/deepseek/deepseek-v4-pro-0813' \
  -H "Authorization: Bearer $RHUMB_KEY"

Resolve text.chat on its providers

curl 'https://rhumbdata.com/v1/resolve?task=text.chat&providers=deepinfra,deepseek,openrouter,together,volcengine' \
  -H "Authorization: Bearer $RHUMB_KEY"

Built from catalog version 2026-11-04.3 of 2026-11-04. Prices are list prices per 1M tokens unless marked otherwise; every score shows its source's notice (see Attributions).