deepseek
DeepSeek: DeepSeek V4 Pro 0813
deepseek/deepseek-v4-pro-0813
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
deepseek/deepseek-v4-pro-0813 is the general-availability release of DeepSeek V4 Pro, described by its developer as a large-scale mixture-of-experts model that supersedes the preview version with stronger agentic capabilities. The OpenRouter catalog lists it as text-to-text with a context length of about one million tokens and configurable reasoning effort levels. The developer credits a DSpark speculative decoding module and reports competitive results on coding and agent benchmarks, though most cited evaluations are vendor-supplied and include internal test sets.[1][2]
Strengths
- According to its developer, it substantially improves on the preview release in agentic and coding tasks and is broadly competitive with top proprietary models.[2]
- The catalog lists a context window of roughly one million tokens and adjustable reasoning effort levels, including an option to disable reasoning.[1][2]
- The model card states the weights are released under the MIT license and provides serving recipes for vLLM and SGLang with DSpark speculative decoding.[2]
Limitations
- Reported benchmark figures come from the developer and include internal test sets, so results should be validated on your own workloads before adoption.[2]
- Text is the only listed input and output modality, and these sources do not specify a knowledge cutoff or training details.[1]
- The card notes that no standard Jinja chat template is included, requiring the provided custom encoding scripts for message formatting and output parsing.[2]
Where to use it
- Agentic software-engineering workflows, where the vendor reports its largest improvements over the preview release.[2]
- Long-context tasks such as repository-scale code or document analysis, given the roughly one-million-token window.[1]
- Tool-calling and structured-output pipelines, which the catalog lists among its supported parameters.[1]
Sources
- [1] OpenRouter catalog · DeepSeek: DeepSeek V4 Pro 0813Sources checked: Nov 13, 2026
- [2] Model documentation · DeepSeek: DeepSeek V4 Pro 0813Sources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.
Specifications
- Model ID
- deepseek/deepseek-v4-pro-0813
- Canonical ID
- deepseek/deepseek-v4-pro-20260813
- Creator
- deepseek
- Added to OpenRouter
- 12.08.2026
- Context length
- 1,048,576
- Modality
- text->text
- Input modalities
- text
- Output modalities
- text
- Token pricing
- USD per 1M tokens: in $0.111 / out $4.44
- Knowledge cutoff
- —
- Expiration date
- —
Tasks and capabilities
A grade appears only where the source supplies a matching measurement for that task, the model is active and the cohort holds at least 10 comparable models. The capability column lists facts the source declares — supported formats, reasoning and tool parameters — which are not measured quality.
| Task | Grade | Source-declared capability |
|---|---|---|
| General quality | CC — below the B band | reasoning: optional · default high · efforts: max, high, low, none · parameters: include_reasoning, reasoning, reasoning_effort |
| Coding | AA — next 20% of the cohort | — |
| Agents | AA — next 20% of the cohort | parameters: structured_outputs, tool_choice, tools |
| Writing | No measurement | output: text |
| Reasoning | No measurement | reasoning: optional · default high · efforts: max, high, low, none · parameters: include_reasoning, reasoning, reasoning_effort |
| Document analysis | No measurement | — |
| Vision | No measurement | — |
| Image generation | No measurement | — |
| Audio | No measurement | — |
| Video | No measurement | — |
| Embeddings | No measurement | — |
Evaluations
| Source | Benchmark | Value | Grade | Data retrieved |
|---|---|---|---|---|
| Artificial Analysis | Intelligence index | 23.1 | CC — below the B band | 13.11.2026 |
| Artificial Analysis | Coding index | 68.8 | AA — next 20% of the cohort | 13.11.2026 |
| Artificial Analysis | Agentic index | 41.3 | AA — next 20% of the cohort | 13.11.2026 |
How grades work
Each letter grade compares a model only against other models scored by the same source and metric in the current snapshot. S means the top 10%, A the next 20%, B the next 30%, C the rest. Models without a published measurement are shown as not rated — a supported format alone never implies measured quality.
- S — S — top 10% of the cohort
- A — A — next 20% of the cohort
- B — B — next 30% of the cohort
- C — C — below the B band
Providers
Optional live provider statistics from OpenRouter. Missing values are unknown, not zero.
| Provider | Context length | Price in /1M | Price out /1M | Latency p50 (30m, s) | Throughput p50 (30m, tok/s) | Uptime (30m) |
|---|---|---|---|---|---|---|
| Relacefp4 | 1,048,576 | $0.100 | $8 | — | — | 100% |
| Wafermxfp4 | 1,048,576 | $0.111 | $4.44 | — | — | 90% |
| Wafermxfp4 | 1,048,576 | $0.285 | $4.3 | — | — | 90% |
| Alibaba | 1,000,000 | $0.581 | $1.74 | — | — | 100% |
| Baidufp8 | 1,048,576 | $0.659 | $1.98 | — | — | 100% |
| Alibaba | 1,000,000 | $0.660 | $1.98 | — | — | 100% |
| StreamLake | 1,024,000 | $0.660 | $1.98 | — | — | 100% |
| DeepSeek | 1,048,576 | $0.660 | $1.98 | — | — | 100% |
| Novitafp8 | 1,048,576 | $0.990 | $2.97 | — | — | 100% |
| GMICloudfp8 | 1,048,575 | $1.06 | $3.17 | — | — | 100% |
| DeepInfrafp8 | 1,048,576 | $1.3 | $2.6 | — | — | 100% |
| CoreWeavefp8 | 1,048,576 | $1.31 | $3.96 | — | — | 100% |
| BaseTenfp4 | 1,048,576 | $1.32 | $3.96 | — | — | — |
| AtlasCloudfp8 | 1,048,576 | $1.32 | $3.96 | — | — | 100% |
| Nebiusfp8 | 1,048,576 | $1.32 | $3.96 | — | — | 100% |
| Parasailfp8 | 1,048,576 | $1.32 | $3.96 | — | — | 100% |
| Together | 1,048,576 | $1.32 | $3.96 | — | — | 100% |
| DigitalOcean | 1,048,576 | $1.32 | $3.96 | — | — | 100% |
| SiliconFlowfp8 | 1,048,576 | $1.32 | $3.96 | — | — | 100% |
| Cloudflare | 1,048,576 | $1.32 | $3.96 | — | — | 54.55% |
| Sail Researchfp4 | 1,048,576 | $1.35 | $2.4 | — | — | 0% |
| Sail Researchfp4 | 1,048,576 | $1.35 | $2.4 | — | — | — |
| Venice | 1,000,000 | $1.65 | $4.95 | — | — | — |
| Parasailfp8 | 1,048,576 | $1.98 | $5.94 | — | — | 100% |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.