prices synced 2026-09-11

DeepSeek V4 Pro 0813 (batch)

DeepSeek · Released Aug 2026

Compare

DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model and the general availability release of DeepSeek V4 Pro, with a 1-million-token context window.

Strengths
It handles frontier-class reasoning and generation tasks with a very large context window that supports long-form documents and multi-turn conversations.
Best for
Production workloads requiring high reasoning capability and the ability to process extended context without truncation.
Limitations
As a larger frontier model, it is slower and more resource-intensive than DeepSeek V4 Flash, making it less suitable for latency-sensitive or cost-constrained applications.

Input / 1M

$0.66

Output / 1M

$1.98

Cached input / 1M

$0.022

Context window

1.05M

Price history

Input (solid)Output (dashed)
Price per 1M tokens over timeOutput went from $3.96 to $1.98; Input went from $1.32 to $0.66 between Aug 2026 and Sep 2026.$0$1.00$2.00$3.00$4.00Output on 29 Aug 2026: $3.96Output on 8 Sep 2026: $1.98Out $1.98Input on 29 Aug 2026: $1.32Input on 8 Sep 2026: $0.66In $0.66Aug 2026Sep 2026

Price change

30d
in decreased 50.0% out decreased 50.0%
90d
in decreased 50.0% out decreased 50.0%
1y
in decreased 50.0% out decreased 50.0%
Since launch
in decreased 50.0% out decreased 50.0%

Snapshots

Effective Input Output Cached in Note Source
8 Sep 2026 $0.66 $1.98 $0.022 Imported from OpenRouter openrouter.ai
29 Aug 2026 $1.32 $3.96 $0.13 Imported from OpenRouter openrouter.ai

More from DeepSeek

Report a problem