DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes
DeepSeek V4 Pro 0813 is offered by 42 providers on this page. Public prices are shown for 38 of them. Its reference price is $2.00 per 1M input tokens and $4.00 per 1M output tokens. The lowest paid channel is CrofAI at $0.35 / $0.80 per 1M, about 5.7× below the reference price. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it. It also has 1 free ($0) channel and 3 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 36 on the Intelligence Index, with 68.8 for coding and 41.3 for agentic tasks. Against its lowest blended price of $0.463 per 1M, that is roughly 78 index points per dollar, which is the value ratio the leaderboards rank on. Median output speed is 110 tokens per second, with 1.67s to the first token. Running one task of the Artificial Analysis suite costs about $0.6740, 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 1,048,576, 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. Providers report the capability flags inconsistently, so verify a specific feature against the host you plan to use.
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 |
|---|---|---|---|---|---|---|---|---|
| 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 | ||
| SCNet Token Plan DeepSeek-V4-Pro-0813 | Gateway | Subscription | $0 | — | 1,000,000 ⚠ | 384,000 | ||
| Nvidia | Cloud | Free | — | — | 1,000,000 ⚠ | 384,000 | deprecated | |
| CrofAI | Gateway | $0.35 | $0.80 | $0.01 | — | 1,000,000 ⚠ | 131,072 | |
| OrcaRouter | Gateway | $0.44 | $0.88 | $0.06 | — | 1,000,000 ⚠ | 384,000 | |
| RunInfra deepseek-ai/DeepSeek-V4-Pro-0813 | Gateway | $0.60 | $1.90 | $0.03 | — | 1,048,576 | 32,768 | |
| Ollama Cloud deepseek-v4-pro:0813 | Cloud | $0.66 | $1.98 | $0.022 | — | 1,048,576 | 1,048,576 | |
| Vercel AI Gateway | Cloud | $0.66 | $1.98 | $0.066 | — | 1,000,000 ⚠ | 384,000 | |
| Eden AI | Gateway | $0.66 | $1.98 | $0.066 | — | 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 15 of 42 providers.
1 / 42 providers expose no reasoning control (reasoning_options: []).
4 more channels offer $0 (Alibaba Token Plan, Alibaba Token Plan (China), SCNet Token Plan 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 harness, so rows are not comparable with one another. The Intelligence Index above draws on a different, newer set of evaluations.