DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modesDeepSeek V4 Pro 0813 is offered by 67 providers on this page. Public prices are shown for 61 of them. Its official list price is $0.66 per 1M input tokens and $1.98 per 1M output tokens. Prices vary about 7.1× across the providers that host it. It also has 1 free ($0) channel and 4 covered by a paid subscription; free tiers usually carry rate limits, and subscription-covered access bills $0 per token only after the subscription fee.
Artificial Analysis rates it 23.1 on the Intelligence Index, with 41.1 for Strategy & Ops, its strongest domain. Against its lowest blended price of $0.897 per 1M, that is roughly 26 index points per dollar, which is the value ratio the leaderboards rank on. Median output speed is 69 tokens per second, with 1.68s to the first token. Running one task of the Artificial Analysis suite costs about $1.7691, which reflects how many tokens its reasoning consumes rather than the unit price alone.
The context window is 1,048,576 tokens at the reference host, but hosts report different limits, from 979,000 to 1,048,600, so the usable window depends on the provider you pick. It supports reasoning, tool use, and structured output. The weights are open, so it can also be self-hosted or served through a gateway of your choice.
Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| SCNet Token Plan DeepSeek-V4-Pro-0813 | Gateway | Subscription | $0 | — | 1,000,000 ⚠ | 384,000 | ||
| Alibaba Token Plan | Gateway | Subscription | $0 | $0 | 1,000,000 ⚠ | 384,000 | ||
| Alibaba Token Plan (China) | Gateway | Subscription | $0 | $0 | 1,000,000 ⚠ | 384,000 | ||
| SenseNova (China) deepseek-v4-pro | Gateway | Free | $0 | — | 1,048,576 | 65,536 | ||
| IteraCompute | Gateway | $0.60 | $1.79 | $0.044 | — | 1,048,576 | 393,216 | |
| RunInfra deepseek-ai/DeepSeek-V4-Pro-0813 | Gateway | $0.60 | $1.90 | $0.03 | — | 1,048,576 | 32,768 | deprecated |
| DeepSeekOfficial deepseek-v4-pro | First-party | $0.66 | $1.98 | $0.022 | — | 1,048,576 | 393,216 | |
| Tokenify deepseek/deepseek-v4-pro | Gateway | $0.66 | $1.98 | $0.044 | — | 1,000,000 ⚠ | 384,000 | |
| Eden AI | Gateway | $0.66 | $1.98 | $0.066 | — | 1,000,000 ⚠ | 384,000 | |
| Eden AI | Gateway | $0.66 | $1.98 | $0.022 | — | 1,000,000 ⚠ | 384,000 |
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.
Interleaved thinking (reasoning between tool calls) is declared by 29 of 67 providers.
1 / 67 providers expose no reasoning control (reasoning_options: []).
4 more channels offer $0 (SCNet Token Plan, Alibaba Token Plan, Alibaba Token Plan (China) etc.); free tiers usually have rate limits and no SLA, excluded from ranking.
| Name | Conditions | Score | Metric | Source |
|---|---|---|---|---|
| Humanity's Last Exam | variant: without tools | 42.7 | score | Source ↗ |
| Humanity's Last Exam | variant: with tools | 60 | score | Source ↗ |
| Terminal-Bench | harness: DeepSeek Harness minimal mode · variant: max effort · v2.1 | 87.9 | score | Source ↗ |
| NL2Repo | harness: DeepSeek Harness minimal mode · variant: max effort | 61.5 | score | Source ↗ |
| CyberGym | harness: DeepSeek Harness minimal mode · variant: max effort | 83.3 | score | Source ↗ |
| DeepSWE | harness: DeepSeek Harness minimal mode · variant: max effort | 62.7 | score | Source ↗ |
| Toolathlon-Verified | — | 74.1 | score | Source ↗ |
| Agents' Last Exam | — | 25.7 | score | Source ↗ |
| AutomationBench | dataset: public | 31.8 | score | Source ↗ |
| DSBench-FullStack | dataset: internal | 71.1 | score | Source ↗ |
| DSBench-Hard | dataset: internal | 67.2 | score | Source ↗ |
The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.
Individual evaluations run by Artificial Analysis, on the same reasoning tier as the intelligence score above. Each benchmark has its own task set and scale (percent correct, points or an index), so rows are not comparable with one another.