DeepSeek-V3.2
deepseek/v3-2By DeepSeek · family: deepseek · released 2025-12-01 · knowledge: 2024-07
Prices in USD per 1M tokens. Unknown means the provider does not publish per-token pricing.
Capabilities
Model fit scores
0–100 · higher is betterThese scores reward declared capabilities, context size, price and provider availability — they are not benchmark results. Use them as a directional signal alongside your own evaluation.
Coding64
- Tool calling40/40
- Structured output0/20
- Reasoning10/10
- Context window (100K → 1M)4/20
- Provider availability10/10
Agents75
- Tool calling35/35
- Structured output0/25
- Reasoning15/15
- Output token limit15/15
- Provider availability10/10
JSON / structured output49
- Structured output / JSON mode0/50
- Tool calling20/20
- Temperature control10/10
- Price-friendly for high-volume19/20
Cost efficiency72
- Headline price (log-scaled)67/95
- Has prompt-cache pricing5/5
Long context51
- Context window (100K → 2M)41/90
- Has published price for full window10/10
Production-readiness94
- Number of independent providers40/40
- Has published per-token price20/20
- Context window ≥ 8K15/15
- No data inconsistencies across providers4/10
- Official model (not derivative)15/15
Cost Efficiency Index
Open full calculator →Estimated cost using the recommended provider's headline rate. Each scenario fixes average input/output tokens — the assumptions are shown in the third column.
| Scenario | Cost | Assumption |
|---|---|---|
RAG answer per 1,000 RAG answers | $1.49 < $0.01 per request | 5K input tokens (query + 4 retrieved chunks of ~1K each) and a 500-token answer. Typical SaaS knowledge-base bot. |
Support ticket triage per 10,000 tickets | $2.98 < $0.01 per request | 1K input tokens (ticket body + system prompt) and a 100-token JSON classification reply. High-volume customer support. |
Data extraction per 1,000 documents | $0.71 < $0.01 per request | 2K input tokens (a single document page) and a 500-token JSON extraction. ETL / invoice / form pipelines. |
Code review per 1,000 PRs | $2.46 < $0.01 per request | 8K input tokens (diff + surrounding files) and a 1K-token review comment. PR-bot workloads. |
Agent step per 1,000 steps | $3.35 < $0.01 per request | 12K input tokens (long-running tool history) and a 600-token tool-call decision. Cost per agent step. |
Pricing detail
Recommended pricing from deepinfra · deepseek-ai/DeepSeek-V3.2
Cheapest provider: iflowcn · Unknown input + Unknown output
Available on 31 providers
| Provider | Provider model id | Input / 1M | Output / 1M | Context | Released |
|---|---|---|---|---|---|
| Amazon Bedrock amazon-bedrock | deepseek.v3.2 | $0.620 | $1.85 | 164K | 2026-02-06 |
| Azure azure | deepseek-v3.2 | $0.580 | $1.68 | 128K | 2025-12-01 |
| OpenRouter openrouter | deepseek/deepseek-v3.2 | $0.280 | $0.400 | 164K | 2025-12-01 |
| Vercel AI Gateway vercel | deepseek/deepseek-v3.2 | $0.270 | $0.400 | 164K | 2025-12-01 |
| Deep Infra deepinfra | deepseek-ai/DeepSeek-V3.2 | $0.260 | $0.380 | 164K | 2025-12-02 |
| Hugging Face huggingface | deepseek-ai/DeepSeek-V3.2 | $0.280 | $0.400 | 164K | 2025-12-01 |
| 302.AI 302ai | deepseek-v3.2 | $0.290 | $0.430 | 128K | 2025-12-01 |
| NanoGPT nano-gpt | TEE/deepseek-v3.2 | $0.500 | $1.00 | 164K | 2025-12-01 |
| NanoGPT nano-gpt | deepseek/deepseek-v3.2 | $0.280 | $0.420 | 163K | 2025-12-01 |
| Abacus abacus | deepseek-ai/DeepSeek-V3.2 | $0.270 | $0.400 | 128K | 2025-06-15 |
| SiliconFlow (China) siliconflow-cn | Pro/deepseek-ai/DeepSeek-V3.2 | $0.270 | $0.420 | 164K | 2025-12-03 |
| SiliconFlow (China) siliconflow-cn | deepseek-ai/DeepSeek-V3.2 | $0.270 | $0.420 | 164K | 2025-12-03 |
| Alibaba (China) alibaba-cn | siliconflow/deepseek-v3.2 | $0.270 | $0.420 | 164K | 2025-12-03 |
| iFlow iflowcn | deepseek-v3.2 | Unknown | Unknown | 128K | 2025-01-01 |
| ZenMux zenmux | deepseek/deepseek-v3.2 | $0.280 | $0.430 | 128K | 2025-12-05 |
| NovitaAI novita-ai | deepseek/deepseek-v3.2 | $0.269 | $0.400 | 164K | 2025-12-01 |
| Vivgrid vivgrid | deepseek-v3.2 | $0.280 | $0.420 | 128K | 2025-12-01 |
| Kilo Gateway kilo | deepseek/deepseek-v3.2 | $0.260 | $0.380 | 164K | 2025-12-01 |
| Nebius Token Factory nebius | deepseek-ai/DeepSeek-V3.2 | $0.300 | $0.450 | 163K | 2026-01-20 |
| Helicone helicone | deepseek-v3.2 | $0.270 | $0.410 | 164K | 2025-09-22 |
| Ollama Cloud ollama-cloud | deepseek-v3.2 | Unknown | Unknown | 164K | 2025-06-15 |
| Baseten baseten | deepseek-ai/DeepSeek-V3.2 | $0.300 | $0.450 | 164K | 2025-12-01 |
| Venice AI venice | deepseek-v3.2 | $0.330 | $0.480 | 160K | 2025-12-04 |
| Azure Cognitive Services azure-cognitive-services | deepseek-v3.2 | $0.580 | $1.68 | 128K | 2025-12-01 |
| Meganova meganova | deepseek-ai/DeepSeek-V3.2 | $0.260 | $0.380 | 164K | 2025-12-03 |
| Synthetic synthetic | hf:deepseek-ai/DeepSeek-V3.2 | $0.270 | $0.400 | 163K | 2025-12-01 |
| Nvidia nvidia | deepseek-ai/deepseek-v3.2 | Unknown | Unknown | 164K | 2025-12-01 |
| Vultr vultr | DeepSeek-V3.2 | $0.550 | $1.65 | 127K | 2025-12-01 |
| Cortecs cortecs | deepseek-v3.2 | $0.266 | $0.444 | 164K | 2025-12-01 |
| SiliconFlow siliconflow | deepseek-ai/DeepSeek-V3.2 | $0.270 | $0.420 | 164K | 2025-12-03 |
| LLM Gateway llmgateway | deepseek-v3.2 | $0.280 | $0.420 | 164K | 2025-09-29 |
Data inconsistencies across providers
- context_window varies: 127000, 128000, 160000, 162816, 163000, 163800, 163840, 163842, 164000
- release_date varies (span 401d): 2025-01-01, 2025-06-15, 2025-09-22, 2025-09-29, 2025-12-01, 2025-12-02, 2025-12-03, 2025-12-04, 2025-12-05, 2026-01-20, 2026-02-06
- modalities varies across offerings
Different providers report different values for this model. Quick facts above use the representative provider; consult the table for per-provider truth.
Frequently asked questions
How much does DeepSeek-V3.2 cost?
DeepSeek-V3.2 costs $0.260 per 1M input tokens and $0.380 per 1M output tokens, sourced from deepinfra. Cache reads, audio tokens and >200K-context tiers (where applicable) are listed in the Pricing detail block above.
What is the context window of DeepSeek-V3.2?
DeepSeek-V3.2 has a context window of 164K tokens, with a max output of 82K tokens per reply. This is the total combined size of prompt + completion.
Does DeepSeek-V3.2 support tool calling?
Yes. DeepSeek-V3.2 supports tool calling (function calling). This makes it suitable for production agent and automation workloads where the model has to invoke external functions reliably.
Does DeepSeek-V3.2 support structured output / JSON mode?
Support for structured output / JSON-schema-constrained decoding is not reported for DeepSeek-V3.2 in our data source. Verify with DeepSeek's official documentation before relying on it in production.
Can DeepSeek-V3.2 accept image input?
No. DeepSeek-V3.2 only accepts text as input. If you need image input, see our /capabilities/vision list for current vision-capable models.
Is DeepSeek-V3.2 open-weight?
Yes. DeepSeek-V3.2's weights are publicly available, so you can self-host or fine-tune. Note that open weights ≠ open source — the training data and code are typically not released.
What are the best alternatives to DeepSeek-V3.2?
If DeepSeek-V3.2 doesn't fit, consider DeepSeek V4 Pro, DeepSeek-R1-0528, DeepSeek-R1. Each one targets the same use case — see the Related links below for direct head-to-head pages.
Where does this data come from?
All numbers come from the public models.dev API and are normalised into a single canonical model record. We re-pull daily and write any changes (price, context, capability) to the /changelog page.
Explore more
Direct comparisons
More DeepSeek models
- DeepSeek V4 Pro$1.74 in / $3.48 out
- DeepSeek-R1-0528$0.40 in / $1.70 out
- DeepSeek-R1$0.40 in / $1.70 out
- DeepSeek-V3.1$0.20 in / $0.70 out
- DeepSeek V4 Flash$0.14 in / $0.28 out
Capability lists this model is in
Last updated:
Data is sourced from models.dev and normalized for comparison. Prices and capabilities may change. Always verify critical production decisions with the provider's official documentation.