Deprecated on Sep 28, 2026. 11 providers still list it at the prices below.
Context
164K
Max output
164K
Serving providers
11
Cheapest input
$0.259 /1M
On-demand listed rates, OpenRouter routed quotes and Vercel reseller quotes. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower. An OpenRouter routed quote is the price of whichever upstream provider OpenRouter prefers today, so it moves day to day.
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 | $0.12 | |||||||||||||||||
| CritPt | 3% | reasoning: true | — | |||||||||||||||||
| ||||||||||||||||||||
| EvalComputeProxyFrozen Aug 18, 2026 | 693.4 | reasoning: true | — | |||||||||||||||||
| ||||||||||||||||||||
| GDPval v2Frozen Aug 18, 2026 | 865.8 | reasoning: true | — | |||||||||||||||||
| ||||||||||||||||||||
| GPQA Diamond | 84% | reasoning: true | — | |||||||||||||||||
| ||||||||||||||||||||
| Humanity's Last Exam | 25% | reasoning: true | — | |||||||||||||||||
| ||||||||||||||||||||
| IFBench | 61% | reasoning: true | — | |||||||||||||||||
| ||||||||||||||||||||
| LiveCodeBench | 86% | reasoning: true | — | |||||||||||||||||
| ||||||||||||||||||||
| Long-Context Reasoning | 73% | reasoning: true | — | |||||||||||||||||
| ||||||||||||||||||||
| MMLU-ProFrozen Aug 18, 2026 | 86% | reasoning: true | — | |||||||||||||||||
| ||||||||||||||||||||
| Omniscience | -22.5 | reasoning: true | — | |||||||||||||||||
| ||||||||||||||||||||
| Omniscience Accuracy | 0.3 | reasoning: true | — | |||||||||||||||||
| ||||||||||||||||||||
| Omniscience Non Hallucination | 0.2 | reasoning: true | — | |||||||||||||||||
| ||||||||||||||||||||
| SciCodeArtificial Analysis did not report this score in its latest run on Oct 14, 2026 | 39% | — | — | |||||||||||||||||
| ||||||||||||||||||||
| TerminalBench Hard | 36% | reasoning: true | — | |||||||||||||||||
| ||||||||||||||||||||
| TerminalBench v2.1 | 47% | reasoning: true | — | |||||||||||||||||
| ||||||||||||||||||||
| τ-bench BankingArtificial Analysis did not report this score in its latest run on Oct 14, 2026 | 19% | — | — | |||||||||||||||||
| τ²-bench | 91% | reasoning: true | — | |||||||||||||||||
| ||||||||||||||||||||
Artificial Analysis last published scores for this benchmark on Sep 9, 2026. Scores here are frozen at that date, and models released since are not on it.
Artificial Analysis last published scores for this benchmark on Aug 18, 2026. Scores here are frozen at that date, and models released since are not on it.
Pricing by serving provider
standard tier · per 1M tokens · click a provider to expandInput pricing runs from $0.259 to $3.00 per 1M tokens across 11 providers, so the dearest route costs 1058% more than the cheapest for the same model.
| Serving provider | Input /1M | Output /1M | Endpoints | |||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| OpenRouterRouted quote | $0.259 | $0.80 | 1 | |||||||||||||
Standarddeepseek/deepseek-v3.2
| ||||||||||||||||
| DeepInfra | $0.26 | $0.38 | 1 | |||||||||||||
Standarddeepinfra/deepseek-ai/DeepSeek-V3.2
| ||||||||||||||||
| Novita | $0.269 | $0.40 | 1 | |||||||||||||
Standardnovita/deepseek/deepseek-v3.2
| ||||||||||||||||
| DeepSeek | $0.28 | $0.40 | 1 | |||||||||||||
Standarddeepseek/deepseek-v3.2
| ||||||||||||||||
| Gmi | $0.28 | $0.40 | 1 | |||||||||||||
Standardgmi/deepseek-ai/DeepSeek-V3.2
| ||||||||||||||||
| Friendliai | $0.50 | $1.50 | 1 | |||||||||||||
Standardfriendliai/deepseek-ai/DeepSeek-V3.2
| ||||||||||||||||
| Fireworks AI | $0.56 | $1.68 | 1 | |||||||||||||
Standardfireworks_ai/accounts/fireworks/models/deepseek-v3p2
| ||||||||||||||||
| Azure | $0.58 | $1.68 | 1 | |||||||||||||
Standardazure_ai/deepseek-v3.2
| ||||||||||||||||
| SambaNova is dearest at $3.00 / $4.50 | ||||||||||||||||
Price history
listed seller prices, input and output per 1M tokens Input Output
Input down 7% since first tracked
Cost calculator
estimate your monthly spend on this model$116
estimated / month
Model IDs
copy the exact identifier for your platformdeepseek/deepseek-v3.2deepinfra/deepseek-ai/DeepSeek-V3.2novita/deepseek/deepseek-v3.2gmi/deepseek-ai/DeepSeek-V3.2deepseek/deepseek-v3.2friendliai/deepseek-ai/DeepSeek-V3.2fireworks_ai/accounts/fireworks/models/deepseek-v3p2azure_ai/deepseek-v3.2bedrock/us-east-1/deepseek.v3.2deepseek/deepseek-v3.2sambanova/DeepSeek-V3.2
Frequently asked questions
DeepSeek V3.2 pricing, context and availabilityIs DeepSeek V3.2 still available?
DeepSeek V3.2 was deprecated on 2026-09-28, but 11 serving providers still list it.
How much does DeepSeek V3.2 cost?
DeepSeek V3.2 costs $0.259 per 1M input tokens as an OpenRouter routed quote, while DeepSeek lists it at $0.28 per 1M input, and $0.38 per 1M output tokens from DeepInfra. An OpenRouter routed quote is the price of whichever upstream provider OpenRouter prefers today, so it moves day to day. Across 11 serving providers, input prices range from $0.259 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 11 serving providers, each with its own pricing and model ID. OpenRouter is currently the cheapest, as a routed quote.
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 lineupDeepSeek V4 Flash 0423$0.09/1M · 18 providersDeepSeek V4 Flash 0731$0.016/1M · 16 providersDeepSeek V4 Pro 0423$0.435/1M · 16 providersR1$0.40/1M · 14 providersDeepSeek V4.1 Flash$0.01/1M · 12 providersDeepSeek V3 0324$0.20/1M · 12 providersDeepSeek V4 Pro 0813$0.66/1M · 12 providersDeepSeek R1 Distill Llama 70B$0.20/1M · 11 providers
Listed prices from LiteLLM, OpenRouter and Vercel · last checked Oct 14, 2026
Every weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI