DeepSeek V4 Pro 0813
by IteraCompute · family deepseek-thinking · listed Aug 2026RTW
DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes
Current rates USD per 1M tokens
Input$1.10
Output$3.30
Cache read$0.11
Cache write—
Against the market
On the record
- Model id
deepseek/deepseek-v4-pro-0813- Context window
- 1.0M tokens
- Max output
- 393K tokens
- Input modalities
- text
- Output modalities
- text
- Reasoning
- yes
- Tool calls
- yes
- Open weights
- yes
- Knowledge cutoff
- —
- Released
- 2026-08-12
- Last updated
- 2026-08-22
- Provider docs
- iteracompute.com/docs.html
Back of the envelope
≈
Also listed at
- Alibaba Token Planfree in · free out
- Alibaba Token Plan (China)free in · free out
- SCNet Token Planfree in · free out
- Nvidiafree in · free out
- OpenRouter$0.246 in · $3.50 out
- CrofAI$0.35 in · $0.80 out
- OrcaRouter$0.442 in · $0.884 out
- RunInfra$0.60 in · $1.90 out
- Vercel AI Gateway$0.66 in · $1.98 out
- Eden AI$0.66 in · $1.98 out
- AIHubMix$0.692 in · $2.08 out
- Ofox$0.924 in · $2.77 out
- NanoGPT$1.10 in · $2.50 out
- Deep Infra$1.30 in · $2.60 out
- CoreWeave$1.31 in · $3.96 out