← Model list

DeepSeek V4 Pro 0813 Thinking

deepseek·deepseek/deepseek-v4-pro-0813-thinking·GA·Closed·deepseek-thinking series·NEW

DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes

At a glance
Reference price$1.10 / $2.50 per 1M
Cache read $0.04 · NanoGPT
Lowest paid$1.10 / $2.50
NanoGPT Gateway
Context1,048,576
Output limit384,000
Capabilities
ReasoningTool useStructured outputTemperatureAttachments
Modalities
Text
Knowledge cutoff
Released / updated2026-08-12 / 2026-08-12

Quality & performance

Artificial Analysis doesn't cover this model (267 of 2059 have data). Quality data comes from independent evals covering widely used models.

Available at 1 providers1 with public prices

ProviderTierInputOutputCache readCache writeContextOutput limitStatus
NanoGPT
deepseek/deepseek-v4-pro-0813:thinking
Gateway$1.10$2.50$0.041,048,576384,000

Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.

Your usage cost

1NanoGPT$217.80
The cheapest paid channel is the only channel.

Benchmark

No upstream benchmark data for this model. For quality, see the Artificial Analysis intelligence score above.

Reasoning control

effort = noneeffort = loweffort = higheffort = max

Related models

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$3.96$02026-08-132026-08-152026-08-13 · Input list $0.4352026-08-14 · Input list $1.322026-08-15 · Input list $1.102026-08-13 · Output list $0.872026-08-14 · Output list $3.962026-08-15 · Output list $2.502026-08-13 · Min blended $0.5442026-08-14 · Min blended $1.982026-08-15 · Min blended $1.45