Capabilities
7-day heat trend
−4.4%Pricing breakdown
Typical 3:1 output-to-input mix, per 1M tokens
Estimated monthly cost by workload
Market position
- Cheaper than 25% of tracked models
- Faster than 78% of tracked models
- Efficiency rank: #410 of 1105
Best suited for
General-purpose text generation, chat, summarization and content workloads where broad capability and low cost matter most.
About deepseek/deepseek-v3.2
Novita AI serverless route for DeepSeek V3.2 with official token pricing, cache-read, and reasoning metadata.
deepseek/deepseek-v3.2 is a Text model from Novita AI (US). HotON.ai tracks it at $0.27 per 1M input tokens and $0.40 per 1M output tokens, with a 164K-token context window, ~163 tokens/sec throughput and 99.6% availability. Its composite efficiency score is 89/100 at an estimated $0.001 per successful task.
Compare deepseek/deepseek-v3.2
Related market news
Frequently asked questions
How much does deepseek/deepseek-v3.2 cost per 1M tokens?+
deepseek/deepseek-v3.2 is tracked at $0.27 per 1M input tokens and $0.40 per 1M output tokens. A typical 3:1 output-to-input workload blends to roughly $0.37 per 1M tokens. Figures are illustrative demo data.
What is deepseek/deepseek-v3.2 best for?+
General-purpose text generation, chat, summarization and content workloads where broad capability and low cost matter most.
How fast is deepseek/deepseek-v3.2?+
deepseek/deepseek-v3.2 delivers about 163 tokens/sec with 99.6% tracked availability, suitable for latency-sensitive, real-time applications.
Is deepseek/deepseek-v3.2 cheaper than other AI models?+
Within the HotON.ai tracked set, deepseek/deepseek-v3.2 is cheaper than 25% of models on input price and ranks #410 of 1105 by overall efficiency.
Related models
Pricing is real (via the TestKey catalog, updated daily). Quality (Arena Elo) is real where the model is ranked on LMArena. Speed, availability and efficiency are modeled estimates.