DeepSeekGeneralReleased 29 September 2025
DeepSeek V3.2 Exp pricing, context and benchmark
DeepSeek-V3.2-Exp is an experimental large language model released by DeepSeek as an intermediate step between V3.1 and future architectures.
164K
Input context
147K
Output context
$0.27
Official input
$0.41
Official output
n/a
AA index
01 · Model Overview
Everything that matters, in one table
Context, pricing, cache, modalities and tooling, from the model registry and Artificial Analysis.
| Model | DeepSeek V3.2 Exp |
| Model ID | deepseek/deepseek-v3.2-exp |
| Provider | DeepSeek |
| Release date | 29 September 2025 |
| Status | Generally available |
| Input context | 163,840 tokens |
| Output context | 147,456 tokens |
| Official input pricing | $0.27 per 1M tokens |
| Official output pricing | $0.41 per 1M tokens |
| Cache read pricing | Not published |
| Market input pricing | $0.27 per 1M (cheapest route) |
| Market output pricing | $0.41 per 1M (cheapest route) |
| Reasoning tokens | Billed as output at $0.41 per 1M |
| Input modalities | text |
| Output modalities | text |
| Reasoning control | Yes, effort levels exposed |
| Tool support | Functions, tool choice, structured outputs |
| Tokenizer | DeepSeek |
| Provider routes | 1 endpoint |
| Artificial Analysis index | Not published |
| Speed | Not published |
| Knowledge cutoff | Not publicly stated |
Input and output support
| Modality | Input | Output | Billed at |
|---|---|---|---|
| Text | ✓ yes | ✓ yes | $0.27 in |
| Image | no | no | not supported |
| Audio | no | no | not supported |
| Video | no | no | not supported |
| File (PDF) | no | no | not supported |
02 · Overview
What is DeepSeek V3.2 Exp?
DeepSeek-V3.2-Exp is an experimental large language model released by DeepSeek as an intermediate step between V3.1 and future architectures.
It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...
DeepSeek V3.2 Exp carries a 164K token window, uses the DeepSeek tokenizer and is served by DeepSeek. On Hoodgen it sits in the General tier of the model menu next to its siblings, so you can switch mid conversation without losing the thread.
03 · Release
Release and what changed from the previous version
Released29 September 2025
| Property | DeepSeek V3.1 Terminus | DeepSeek V3.2 Exp | Change |
|---|---|---|---|
| Released | 2025 | 2025 | Same release window |
| Context | 164K | 164K | Unchanged |
| Max output | 147K | 147K | Unchanged |
| Input price | $0.27 | $0.27 | Unchanged |
| Output price | $1 | $0.41 | Cheaper |
| Input modalities | text | text | Unchanged |
| AA index | n/a | n/a | Newer benchmark run |
04 · Capabilities
Features and capabilities
◈
Thinking control
Reasoning effort can be dialled per request, so one model covers deep analysis and fast chat.
⚙
Function calling
Tools, tool choice and parallel calls, which is what agent loops need to act on results.
{ }
Structured outputs
Schema constrained JSON with response_format, so no parse and retry loop in your code.
05 · Reasoning
Thinking and reasoning capabilities
DeepSeek V3.2 Exp can think before answering and exposes the effort level per request. Reasoning tokens bill as output at $0.41 per million, and the trace can be returned with include_reasoning.
| Level | First token | Cost per task | Best for |
|---|---|---|---|
| Measured | n/a | n/a | Artificial Analysis measures the default reasoning configuration |
| Low effort | Faster | Lower | Chat, autocomplete, classification |
| High effort | Slower | Higher | Debugging, planning, multi step agents |
07 · Use cases
What can you do with DeepSeek V3.2 Exp?
Everyday writing
Drafts, rewrites, summaries and replies.
Research
Source material condensed with the key numbers kept.
Chat
General questions where latency and cost both matter.
Tooling inside Hoodgen
Writer, Humanizer, Coding and the rest of the tool suite.
09 · Pricing
DeepSeek V3.2 Exp pricing
Official pricing
List price
$0.27 / 1M in
$0.41 / 1M out
- 164K context
- text input
Cheapest route
$0.27 / 1M in
$0.41 / 1M out
- 1 route on OpenRouter
- What Hoodgen routes to first
- Same model, lower bill
Market pricing, every route
| Provider | Tier | Input | Output | Cache read | Uptime 24h |
|---|---|---|---|---|---|
| SiliconFlow | standard | $0.27 | $0.41 | n/a | 100.0% |
API pricing and cost calculator
| Rate | Per call | Total | Credits |
|---|---|---|---|
| Cheapest route | $0.0060 | $3.01 | 2858 |
| List price | $0.0060 | $3.01 | 2858 |
10 · Developers
API and developer information
| Model ID | deepseek/deepseek-v3.2-exp |
| Endpoint | https://openrouter.ai/api/v1/chat/completions |
| Parameters | frequency_penalty · include_reasoning · max_tokens · reasoning · response_format · structured_outputs · temperature · tool_choice · tools · top_k · top_p |
| Streaming | Yes, server sent events |
| Modality string | text->text |
| Max prompt tokens | 163,840 |
| Max completion tokens | 147,456 |
curl https://openrouter.ai/api/v1/chat/completions \
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek/deepseek-v3.2-exp",
"messages": [{ "role": "user", "content": "Summarise this document." }],
"max_tokens": 1024
}'11 · Limitations
Model limitations
| Text only output | It cannot generate images, audio or video. Pair it with an image model on Hoodgen when you need visuals. |
| Output cap | 147,456 tokens per request. Long deliverables have to be chunked. |
| Benchmarks not published | Artificial Analysis does not publish an Intelligence Index for this release, so no benchmark score is claimed here. |
| Knowledge cutoff | The provider does not state a fixed cutoff for every release. Verify very recent events against search. |
12 · Comparison
DeepSeek V3.2 Exp vs other DeepSeek models
| Model | Context | Input /1M | Output /1M | AA index | Released |
|---|---|---|---|---|---|
| DeepSeek V3.2 Exp | 164K | $0.27 | $0.41 | n/a | 2025 |
| DeepSeek V4 Pro | 1.05M | $0.9 | $1.5 | 23 | 2026 |
| DeepSeek V3.1 Terminus | 164K | $0.27 | $1 | n/a | 2025 |
| DeepSeek V3 0324 | 164K | $0.25 | $1 | n/a | 2025 |
| DeepSeek V3.2 | 164K | $0.209 | $0.31 | n/a | 2025 |
| DeepSeek V4.1 Flash 1017 | 1.05M | $0.038 | $0.5 | 33 | Oct 2026 |
13 · Privacy
Privacy and data policy
- On Hoodgen, prompts and attachments answer that request and stay in your conversation history so you can reopen it. They are not used to train models.
- Requests route through OpenRouter to DeepSeek and are covered by that provider's API terms.
- Do not paste secrets or personal data you would not send to any hosted model.
14 · FAQ
DeepSeek V3.2 Exp questions, answered
DeepSeek V3.2 Exp is a general model from DeepSeek, released 29 September 2025. DeepSeek-V3.2-Exp is an experimental large language model released by DeepSeek as an intermediate step between V3.1 and future architectures.
✦
Start chatting with DeepSeek V3.2 Exp
Free to try on Hoodgen AI, with a live credit estimate before every send. No API key, no setup.