# DeepSeek V3.2

DeepSeek V3.2 is a text generation model from DeepSeek, available through the Impossibl API. Its published context window is 163,840 tokens. The advertised input rate is $0.58 per million input tokens. The advertised output rate is $1.68 per million output tokens.

- Model identifier: ` deepseek/deepseek-v3-2 `
- Creator: DeepSeek
- Model type: Text generation
- Canonical model page: [DeepSeek V3.2](<https://impossibl.com/deepseek/deepseek-v3-2>)
- API availability: Listed as serving through Impossibl.
- Creator release date: 2025-12-01

## Capabilities and limits

- Context window: 163,840 tokens
- Maximum output tokens: Not published in the public catalog; this is separate from the context window.
- Inputs: text
- Outputs: text
- Tool calling: Not published

## API access

Use ` deepseek/deepseek-v3-2 ` as the model identifier through the Impossibl API.

Published API endpoints:

- ` /v1/chat/completions `

[API quickstart](<https://impossibl.com/docs/agent-quickstart>) · [Models and billing documentation](<https://impossibl.com/docs/models>)

## Published API prices

All rates are in USD. An unpublished rate is unknown, not zero. Workspace-specific pricing, taxes, balance-purchase fees, billing adjustments, and tool charges can affect the amount paid.

| Usage | Published base rate | Billing unit |
| --- | --- | --- |
| Input | $0.58 | per million input tokens |
| Output | $1.68 | per million output tokens |
| Cache read | Not published | per million cached input tokens |
| Cache write (default retention) | Not published | per million tokens |
| Cache write (one-hour retention) | Not published | per million tokens |
| Audio input | Not published | per million audio input tokens |

## Independent benchmarks

Source: [Artificial Analysis](<https://artificialanalysis.ai/>). Last checked: 2026-09-11T11:52:20.926Z.
Configurations are evaluated separately. API scores retain their original units. Unmeasured scores are omitted.

### DeepSeek V3.2 (Non-reasoning)

Source: [Evaluation source](<https://artificialanalysis.ai/models/deepseek-v3-2>)

| Benchmark | Score |
| --- | --- |
| Intelligence Index | 16.04 |
| Omniscience Index | -46.88 |
| GPQA | 75.05% |
| Humanity’s Last Exam | 11.21% |
| CritPt | 0.86% |
| Terminal-Bench Hard | 32.58% |
| AA-LCR | 45.67% |
| IFBench | 49.05% |
| Tau2 | 78.95% |
| LiveCodeBench | 59.26% |
| AIME 2025 | 59.00% |
| intelligence index (API) | 16 |

### DeepSeek V3.2 (Reasoning)

Source: [Evaluation source](<https://artificialanalysis.ai/models/deepseek-v3-2-reasoning>)

| Benchmark | Score |
| --- | --- |
| Intelligence Index | 21.49 |
| Omniscience Index | -22.48 |
| GPQA | 84.04% |
| Humanity’s Last Exam | 24.56% |
| CritPt | 2.86% |
| Terminal-Bench v2.1 | 46.82% |
| Terminal-Bench Hard | 35.61% |
| AA-LCR | 73.33% |
| GDPval Elo | 810.24 |
| IFBench | 60.68% |
| Tau2 | 90.64% |
| APEX-Agents | 14.53% |
| LiveCodeBench | 86.24% |
| AIME 2025 | 92.00% |
| coding index (API) | 44.2 |
| intelligence index (API) | 21.5 |

Full benchmark data and breakdowns: [Complete benchmark snapshot](<https://api.impossibl.com/v1/models/deepseek/deepseek-v3-2/benchmarks>).


## Availability and retirement

The model is listed as serving. No retirement is announced in the current public catalog.

## Frequently asked questions

### What is DeepSeek V3.2?

DeepSeek V3.2 is a text-generation model from DeepSeek, available through the Impossibl API.

### How much does DeepSeek V3.2 cost?

DeepSeek V3.2 costs $0.58 per million input tokens and $1.68 per million output tokens through the Impossibl API. All rates are in USD.

### What is the context length of DeepSeek V3.2?

DeepSeek V3.2 has a 163,840-token context window through the Impossibl API.

### What inputs and outputs does DeepSeek V3.2 support?

DeepSeek V3.2 accepts text as input. DeepSeek V3.2 returns text.

### How do I use DeepSeek V3.2 through an API?

DeepSeek V3.2 is available through the Impossibl API. Use deepseek/deepseek-v3-2 as the model identifier with /v1/chat/completions. The quickstart explains how to create an API key and send your first request.

### When was DeepSeek V3.2 released?

DeepSeek released DeepSeek V3.2 on December 1, 2025.

Sources: [Creator release announcement](<https://api-docs.deepseek.com/updates/>)

## Sources and related links

Prices, limits, capabilities, endpoints, and availability come from the public Impossibl catalog. Creator documentation supplies descriptions and release dates where available; it does not override the published API offering.

- [Public Impossibl model catalog](<https://api.impossibl.com/v1/models>)
- [Full model directory as JSON](<https://impossibl.com/models.json>)
- [DeepSeek V3.2: model details and pricing](<https://impossibl.com/deepseek/deepseek-v3-2>)
- [Model directory](<https://impossibl.com/models>)