deepseek
DeepSeek: DeepSeek V3
deepseek/deepseek-chat
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
DeepSeek Chat is the OpenRouter listing for DeepSeek's DeepSeek-V3 chat model, canonically identified as deepseek/deepseek-chat-v3. According to the model card, it is a Mixture-of-Experts model with 671B total parameters and 37B activated per token, pretrained on 14.8T tokens and post-trained with reasoning distillation from the DeepSeek-R1 series. It handles text input and output only. Vendor-published evaluations emphasize math and code results, but those figures are self-reported and have not been independently verified in this source pack.[1][2]
Strengths
- Long context handling: the model card documents a 128K window with reported solid Needle-in-a-Haystack results, while the catalog lists a somewhat larger window.[1][2]
- Catalog-listed API parameters include tool calling and structured outputs, supporting function-driven integrations.[1]
- Vendor-reported evaluations claim top results among open models on math and code benchmarks.[2]
Limitations
- Text input and output only; no other modalities are listed in the catalog.[1]
- Most capability evidence is vendor-reported; OpenRouter's design-arena entries show middling placements in design categories, and sources disagree on exact context length, so validate on your own workload.[1][2]
- The catalog reports a knowledge cutoff of 2024-07-31.[1]
Where to use it
- A candidate for code and math assistance, where vendor-reported results are strongest; confirm against your own tasks first.[2]
- Potentially suitable for tool-calling or structured-output API workflows, given the catalog-listed parameters.[1]
- May fit long-document processing within its documented context window, per the model card.[2]
Sources
- [1] OpenRouter catalog · DeepSeek: DeepSeek V3Sources checked: Nov 13, 2026
- [2] Model documentation · DeepSeek: DeepSeek V3Sources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions. Pre-trained on nearly 15 trillion tokens, the reported evaluations...
Specifications
- Model ID
- deepseek/deepseek-chat
- Canonical ID
- deepseek/deepseek-chat-v3
- Creator
- deepseek
- Added to OpenRouter
- 26.12.2024
- Context length
- 163,840
- Modality
- text->text
- Input modalities
- text
- Output modalities
- text
- Token pricing
- USD per 1M tokens: in $0.320 / out $0.890
- Knowledge cutoff
- 31.07.2024
- 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 | No measurement | — |
| Coding | No measurement | — |
| Agents | No measurement | parameters: structured_outputs, tool_choice, tools |
| Writing | No measurement | output: text |
| Reasoning | No measurement | — |
| 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 |
|---|---|---|---|---|
| Design Arena | models · 3dwin rate 50.5% · rank 101 | 1,069Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · codecategorieswin rate 48.4% · rank 110 | 1,099Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · datavizwin rate 50% · rank 105 | 1,087Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · gamedevwin rate 43.7% · rank 117 | 1,044Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · svgwin rate 38.8% · rank 96 | 968Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · uicomponentwin rate 52.7% · rank 107 | 1,084Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · websitewin rate 48.5% · rank 108 | 1,113Elo | CC — below the B band | 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) |
|---|---|---|---|---|---|---|
| DeepInfrafp4 | 163,840 | $0.256 | $0.712 | — | — | 100% |
| StreamLake | 128,000 | $0.257 | $1.03 | — | — | 100% |
| DeepInfrafp4 | 163,840 | $0.320 | $0.890 | — | — | 96.67% |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.