DeepSeek V3.2
deepseek/deepseek-v3.2Frontier-adjacent open-weight flagship at roughly a tenth of typical flagship cost, with reliable tool calling.
Model overview
Context window
128K
tokens
Input price
—
quoted on request
Output price
—
quoted on request
Weekly volume
—
tokens / week
Open weights
Yes
self-hostable
Capabilities
5
of 11 tags
Description
DeepSeek V3.2 is a language model from DeepSeek. Webparam does not stock this model yet and can source it on request — tell us what you need it for and we will come back with availability and a price. DeepSeek’s stated focus is open-weight frontier reasoning at disruptive economics. Its mean it can also be self-hosted under its licence.
Capabilities
- Tool calling
- Calls functions you define and returns their arguments as structured data, the basis of agents.
- JSON mode
- Constrains the response to valid JSON matching a schema you supply.
- Streaming
- Emits tokens as they are generated, so answers appear progressively rather than all at once.
- Caching
- Reuses already-processed prompt prefixes across requests, cutting input cost for repeated context.
- Open weights
- The parameters are published, so the model can be inspected, fine-tuned and self-hosted under its licence.
Strengths & weaknesses
Strengths
- Frontier-adjacent quality at ~1/10 typical flagship cost
- Strong tool-calling reliability
- Open weights permit self-hosting later
Weaknesses
- English long-form prose trails Western flagships
- No vision input
- Reasoning line (R1) is a separate model
Pricing
Free| Rate | Price | Unit |
|---|---|---|
| Input | $0.00 | per 1M tokens |
| Output | — not charged | — |
Prompt caching is supported, so repeated prefixes bill below the listed input rate. Free at the point of use; fair-use rate limits apply to the free tier. Illustrative placeholder pricing.
Context window
128Ktokens
covers prompt and response together, so a long input leaves less room for the answer.
Supported features
| Feature | Support |
|---|---|
| Tool calling | Supported |
| JSON mode | Supported |
| Streaming | Supported |
| Vision input | Not supported |
| Audio input | Not supported |
| Long context | Not supported |
| Open weights | Supported |
| Reasoning | Not supported |
| Fine-tunable | Not supported |
| Batch | Not supported |
| Caching | Supported |
Example use cases
Bulk summarisation
Frontier-adjacent quality at ~1/10 typical flagship cost
Agent loops
Strong tool-calling reliability
Cost-sensitive production
Open weights permit self-hosting later
Example prompt
Extract every commitment, owner and deadline from this meeting transcript as JSON.Comparison
| Attribute | DeepSeek V3.2 | DeepSeek R1 | Qwen3 235B A22B Instruct 2507 |
|---|---|---|---|
| Context window | 128K | 164K | 256K |
| Input price | $0.00 | $0.00 | $0.00 |
| Output price | — not charged | — not charged | — not charged |
| Tool calling | Supported | Supported | Supported |
| JSON mode | Supported | Not supported | Supported |
| Vision input | Not supported | Not supported | Not supported |
| Open weights | Supported | Supported | Supported |
| Prompt caching | Supported | Not supported | Not supported |
Best value in each row is highlighted. Illustrative placeholder data.
Provider information
View DeepSeek →DeepSeek · 深度求索 · Hangzhou, China · est. 2023
Spun out of a quantitative trading firm, DeepSeek built its reputation by releasing open-weight models that matched closed frontier quality at a fraction of the price. Its V-series redefined cost expectations for production LLMs, and its R-series brought open reasoning models into serious enterprise conversations.
Recent releases
Documentation
Frequently asked questions
Input is billed at $0.00 per 1M tokens, and there is no separate output charge. Prompt caching bills repeated prefixes below the listed input rate. Every figure on this page is an illustrative placeholder.