Context
164K
Max output
164K
Serving providers
6
Cheapest input
$0.27 /1M
Prices are on-demand list rates. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.
Benchmarks
independent evaluations · source: ARC Prize and Artificial AnalysisHeadline indices
Individual benchmarks · click a row for effort variants
| Benchmark | Best score | Effort | Cost / task | |||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| APEX Agents | 15% | reasoning: true | — | |||||||||||||
| ARC-AGI-2 | 4% | default | $0.120 | |||||||||||||
| CritPt | 3% | reasoning: true | — | |||||||||||||
| ||||||||||||||||
| EvalComputeProxy | 4392.7 | reasoning: true | — | |||||||||||||
| ||||||||||||||||
| GDPval | 865.5 | reasoning: true | — | |||||||||||||
| GPQA Diamond | 84% | reasoning: true | — | |||||||||||||
| ||||||||||||||||
| Humanity's Last Exam | 22% | reasoning: true | — | |||||||||||||
| ||||||||||||||||
| IFBench | 61% | reasoning: true | — | |||||||||||||
| ||||||||||||||||
| LiveCodeBench | 86% | reasoning: true | — | |||||||||||||
| ||||||||||||||||
| Long-Context Reasoning | 65% | reasoning: true | — | |||||||||||||
| ||||||||||||||||
| MMLU-Pro | 86% | reasoning: true | — | |||||||||||||
| ||||||||||||||||
| Omniscience | -20.9 | reasoning: true | — | |||||||||||||
| ||||||||||||||||
| SciCode | 39% | reasoning: true | — | |||||||||||||
| ||||||||||||||||
| TerminalBench Hard | 36% | reasoning: true | — | |||||||||||||
| ||||||||||||||||
| TerminalBench v2.1 | 47% | reasoning: true | — | |||||||||||||
| τ-bench Banking | 19% | reasoning: true | — | |||||||||||||
| τ²-bench | 91% | reasoning: true | — | |||||||||||||
| ||||||||||||||||
Pricing by serving provider
standard tier · per 1M tokens · click a provider to expandInput pricing runs from $0.27 to $3.00 per 1M tokens across 6 providers, so the dearest route costs 1015% more than the cheapest for the same model.
| Serving provider | Input /1M | Output /1M | Endpoints | |||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| NovitaCheapest | $0.27 | $0.40 | 1 | |||||||||||||||||||||
| ||||||||||||||||||||||||
| DeepSeek | $0.28 | $0.40 | 1 | |||||||||||||||||||||
| ||||||||||||||||||||||||
| Gmi | $0.28 | $0.40 | 1 | |||||||||||||||||||||
| ||||||||||||||||||||||||
| OpenRouter | $0.28 | $0.40 | 1 | |||||||||||||||||||||
| ||||||||||||||||||||||||
| Azure | $0.58 | $1.68 | 1 | |||||||||||||||||||||
| ||||||||||||||||||||||||
| SambaNova | $3.00 | $4.50 | 1 | |||||||||||||||||||||
| ||||||||||||||||||||||||
Price history
input + output $/1M since we started tracking Input Output
Input down 4% since first tracked
Cost calculator
estimate your monthly spend on this model$86
estimated / month
Model IDs
copy the exact identifier for your platformnovita/deepseek/deepseek-v3.2deepseek/deepseek-v3.2gmi/deepseek-ai/DeepSeek-V3.2openrouter/deepseek/deepseek-v3.2azure_ai/deepseek-v3.2sambanova/DeepSeek-V3.2
Frequently asked questions
DeepSeek V3.2 pricing, context and availabilityHow much does DeepSeek V3.2 cost?
DeepSeek V3.2 costs $0.27 per 1M input tokens and $0.40 per 1M output tokens at its cheapest provider via Novita. Across 6 serving providers, input prices range from $0.27 to $3.00 per 1M tokens.
What is the context window of DeepSeek V3.2?
DeepSeek V3.2 accepts up to 164K tokens of context and can return up to 164K output tokens.
Which providers serve DeepSeek V3.2?
DeepSeek V3.2 is available from 6 serving providers, each with its own pricing and model ID. Novita is currently the cheapest.
What can DeepSeek V3.2 do?
DeepSeek V3.2 supports tool use, reasoning, prompt caching and structured output.
Other DeepSeek models
compare pricing across the DeepSeek lineup Pricing verified against LiteLLM + OpenRouter + provider pages · refreshed daily
Every weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI