deepseek-v3.2DeepSeek
- endpoints
- 2
- regions
- 1
- api
- chat
- released
- December 2025
capabilities 5/8
The same weights cost 2.1x more on google llc (vertex ai) than on novita ai. That is what the endpoints table is for.
| # | flags | ||||||
|---|---|---|---|---|---|---|---|
| 1 |  Novita AI | Global | 164K | $0.27 | $0.40 | $0.13 | zdr |
| 2 |  Google LLC (Vertex AI) | Global | 164K | $0.56 | $1.68 | $0.06 | zdr |
no measured traffic for this model yet. the endpoints table above carries provider pricing
| eval | Score as a share of 100 | /100 |
|---|---|---|
| Math Index | 92.0 | |
| AIME 2025 | 92.0 | |
| τ²-Bench | 90.6 | |
| LiveCodeBench | 86.2 | |
| MMLU Pro | 86.2 | |
| GPQA Diamond | 84.0 | |
| Coding Index | 44.2 | |
| Terminal-Bench Hard | 35.6 | |
| Humanity's Last Exam | 24.6 | |
| Intelligence Index | 21.5 | |
| 10 evals | mean | 65.7 |
Scores from Artificial Analysis and public leaderboards, normalised to 100. Bar colour is the band, not the rank: green 80 and up, blue 55 and up, amber 30 and up. Benchmarks measure narrow skills, so test on your own workload before committing. Released 2025-12-01.
novita/deepseek/deepseek-v3.2this model has no managed policy yet, so call the provider endpoint directly. every id in the endpoints table works the same way
Base url is https://router.requesty.ai/v1 for every id here. One key reaches the whole catalog.
from openai import OpenAI client = OpenAI( api_key="YOUR_REQUESTY_API_KEY", base_url="https://router.requesty.ai/v1",) response = client.chat.completions.create( model="novita/deepseek/deepseek-v3.2", messages=[ {"role": "user", "content": "Explain quantum computing in one paragraph."}, ],) print(response.choices[0].message.content)
Change the base url, use your Requesty key, set the model to any id in the call pane. Existing OpenAI SDK code needs no other edit, and the same key reaches every other model in the catalog, so switching later is a one-parameter change. Browse all models
DeepSeek-V3.2 is a next-generation foundation model designed to unify high computational efficiency with state-of-the-art reasoning and agentic performance. Built upon DeepSeek Sparse Attention (DSA) for efficient long-context reasoning, a scalable reinforcement learning framework reaching frontier-level performance, and a large-scale agentic task synthesis pipeline for reliable tool-use and multi-step decision-making.
questions 5
Which providers serve deepseek-v3.2?
How much does deepseek-v3.2 cost?
Is deepseek-v3.2 open weights?
What is the context window of deepseek-v3.2?
How do I use deepseek-v3.2 with the OpenAI SDK?
more from deepseek 6
| model | context | from /M | providers |
|---|---|---|---|
| deepseek-v4.1-flash | 1.0M | $0.22 | 3 |
| deepseek-v4-flash-vision-exp | 1.0M | $0.22 | 1 |
| deepseek-v4-pro-0813 | 1.0M | $1.30 | 4 |
| deepseek-v4-flash-0731 | 1.0M | $0.07 | 8 |
| deepseek-v4-pro-0424 | 1.0M | $1.04 | 4 |
| deepseek-v4-flash-0424 | 1.0M | $0.07 | 4 |
route deepseek-v3.2 through one endpoint
One key for 2 providers on this model and 600+ others. No markup on provider prices, automatic failover, caching built in. Weekly aggregates in the measured pane come from production traffic routed through Requesty, one line per provider on a shared axis. Methodology