deepseek-v3.2Novita AI
- api
- chat
- hosting
- US
- model lab
- DeepSeek
- weights
- open
- added
- December 2025
- model id
- novita/deepseek/deepseek-v3.2
capabilities 3/8
2 providers serve deepseek-v3.2. This page is one of them. Compare all endpoints
- input
- $0.27
- output
- $0.40
- cache write
- -
- cache read
- $0.13
worked cost
| volume | cost |
|---|---|
| 100K in + 10K out | $0.0309 |
| 1M in + 100K out | $0.31 |
| 10M in + 1M out | $3.09 |
Requesty charges what the upstream provider charges, with no markup and no per-request fee. Prompt caching and smart routing cut the effective cost further on repeated context. Gateway pricing
no measured traffic for this endpoint yet. pricing above is the provider's own
| 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.
- retention
- none
- trains on prompts
- no
- hosted in
- US
Terms are the provider's, not Requesty's: routing a request here puts it under them. Novita AI Privacy Policy
Need every request to stay in one jurisdiction? EU hosting routes only through EU-hosted providers.
novita/deepseek/deepseek-v3.2this id pins the novita ai deployment, with no routing and no failover. the managed id on the canonical page routes across all 2 providers instead
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 to https://router.requesty.ai/v1, use your Requesty key, set the model to the id above. Existing OpenAI SDK code needs no other edit, and the same key reaches every other model in the catalog. 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 6
How much does deepseek-v3.2 cost?
What is the context window of deepseek-v3.2?
How does deepseek-v3.2 perform on benchmarks?
What can deepseek-v3.2 do?
How do I use deepseek-v3.2 with the OpenAI SDK?
Can I run deepseek-v3.2 through Requesty?
more from novita ai 8
| endpoint | ctx | in /M |
|---|---|---|
| deepseek-v4.1-flash | 1.0M | $0.30 |
| glm-5.3-flash | 1.0M | $0.15 |
| inclusionai/ling-3.0-tiny | 262K | free |
| qwen/qwen3.8-max | 1M | $2.00 |
| deepseek-v4-flash-0731 | 1.0M | $0.14 |
| tencent/hy3 | 262K | $0.14 |
| stepfun/step-3.7-flash | 262K | $0.20 |
| inclusionai/ring-2.6-1t | 262K | $0.30 |
call deepseek-v3.2 through one endpoint
One key for this endpoint and 600+ other models. No markup on provider prices, automatic failover when a provider degrades, and prompt caching built in. Methodology