deepseek
DeepSeek: DeepSeek V3 0324
deepseek/deepseek-chat-v3-0324
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
OpenRouter catalogs DeepSeek V3 0324 as a text-only, 685B-parameter mixture-of-experts chat model with a 163,840-token context and a July 2024 knowledge cutoff. The independent model card describes this revision as an update to DeepSeek V3, with reported gains in reasoning benchmarks, front-end code, Chinese writing and search analysis, and function calling. Listed features include tools, structured or JSON output, and FIM completion.[1][2]
Strengths
- The model card reports higher benchmark results than DeepSeek V3 and more accurate function calling; OpenRouter also records a coding-oriented measurement.[1][2]
- A 163,840-token text context and parameters for tools, structured outputs, seeds, penalties, and sampling support long and controlled API workflows.[1]
- The documentation lists function calling, JSON output, and FIM completion, and reports better executable front-end code and medium-to-long Chinese writing.[2]
Limitations
- Evidence is limited to an OpenRouter catalog record and the model card; validate accuracy, latency, cost, and tool behavior on your workload.[1][2]
- It accepts and returns text only, and OpenRouter exposes no dedicated reasoning-mode flag.[1]
- The model card says Hugging Face Transformers was not directly supported at publication; the knowledge cutoff is July 31, 2024.[1][2]
Where to use it
- Consider it for long-context chat, document question answering, or interactive rewriting when text-only input is sufficient.[1][2]
- It may suit coding assistance, executable front-end generation, or fill-in-the-middle completion, subject to project testing.[1][2]
- It could fit workflows needing function calls, tool choice, structured or JSON outputs, or Chinese-language report analysis.[1][2]
Sources
- [1] OpenRouter catalog · DeepSeek: DeepSeek V3 0324Sources checked: Nov 13, 2026
- [2] Model documentation · DeepSeek: DeepSeek V3 0324Sources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team. It succeeds the [DeepSeek V3](/deepseek/deepseek-chat-v3) model and performs really well...
Specifications
- Model ID
- deepseek/deepseek-chat-v3-0324
- Creator
- deepseek
- Added to OpenRouter
- 24.03.2025
- Context length
- 163,840
- Modality
- text->text
- Input modalities
- text
- Output modalities
- text
- Token pricing
- USD per 1M tokens: in $0.290 / out $1.14
- 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 | CC — below the B band | — |
| Agents | CC — below the B band | 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 |
|---|---|---|---|---|
| Artificial Analysis | Coding index | 21.2 | CC — below the B band | 13.11.2026 |
| Artificial Analysis | Agentic index | 0.8 | 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) |
|---|---|---|---|---|---|---|
| SiliconFlowfp8 | 163,840 | $0.250 | $1 | — | — | 100% |
| GMICloudfp8 | 128,000 | $0.290 | $1.14 | — | — | 100% |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.