DeepSeek V3.2
DeepSeek V3.2 is the extended reasoning variant of DeepSeek-V3.2. Available on AI Gateway since December 1, 2025, it generates up to 163K tokens of chain-of-thought reasoning for complex analytical, scientific, and multi-step problem-solving tasks.
import { streamText } from 'ai'
const result = streamText({ model: 'deepseek/deepseek-v3.2-thinking', prompt: 'Why is the sky blue?'})Playground
Try out DeepSeek V3.2 by DeepSeek. Usage is billed to your team at API rates. Free users (those who haven't made a payment) get $5 of credits every 30 days.
Providers
Route requests across multiple providers. Copy a provider slug to set your preference. Visit the docs for more info. Using a provider means you agree to their terms, listed under Legal.
| Provider |
|---|
| 164K | 1.5s | 39tps | $0.28/M | $0.42/M | Read:$0.13/M Write:— | — | — | 12/01/2025 | ||||
| 128K | 1.5s | 134tps | $0.28/M | $0.42/M | Read:$0.03/M Write:— | — | — | 12/01/2025 | ||||
| 163K | $0.56/M | $1.68/M | Read:$0.28/M Write:— | — | — | 12/01/2025 | ||||||
| 128K | 1.1s | 30tps | $0.62/M | $1.85/M | — | — | 12/01/2025 | |||||
| 164K | 5.0s | 6tps | $0.26/M | $0.38/M | Read:$0.13/M Write:— | — | — | 12/01/2025 |
P50 throughput on live AI Gateway traffic, in tokens per second (TPS). Visit the docs for more info.
P50 time to first token (TTFT) on live AI Gateway traffic, in milliseconds. View the docs for more info.
Direct request success rate on AI Gateway and per-provider. Visit the docs for more info.
More models by DeepSeek
| Model |
|---|
| 1M | 0.6s | 144tps | $0.14/M | $0.28/M | Read:$0.0/M Write:— | — | — |    | 04/23/2026 | ||||
| 1M | 1.3s | 58tps | $0.43/M | $0.87/M | Read:$0.0/M Write:— | — | — |  +1 | 04/23/2026 | ||||
| 164K | 0.7s | 117tps | $0.28/M | $0.42/M | Read:$0.03/M Write:— | — | — |  +2 | 12/01/2025 | ||||
| 131K | 1.6s | 30tps | $0.27/M | $1.00/M | Read:$0.14/M Write:— | — | — | | 09/22/2025 | ||||
| 164K | 0.3s | 43tps | $0.50/M | $1.50/M | Read:$0.13/M Write:— | — | — |  +3 | 08/21/2025 | ||||
| 164K | 0.3s | 43tps | $0.77/M | $0.77/M | Read:$0.14/M Write:— | — | — | | 12/26/2024 |
About DeepSeek V3.2
DeepSeek V3.2 became available on AI Gateway on December 1, 2025 as the reasoning-optimized variant of the V3.2 release. It operates exclusively in thinking mode, generating extended chain-of-thought reasoning traces before producing a final answer. The output token budget extends to 163K tokens, compared to 8K for the standard V3.2 chat variant. That headroom accommodates complex multi-step reasoning chains.
The trade-off is explicit: DeepSeek V3.2 does not support tool use. This makes it a pure reasoning engine rather than a tool-augmented agent. Where the standard DeepSeek-V3.2 supports tool calls across both reasoning and non-reasoning modes, the Thinking variant trades tool integration for a deeper reasoning budget. Use it when the reasoning process itself is the primary value, such as complex scientific analysis, multi-step mathematical derivation, or structured argument construction.
The Thinking variant and standard V3.2 are accessible through AI Gateway under the deepseek provider without separate account setup.
What To Consider When Choosing a Provider
- Configuration: DeepSeek V3.2 does not support tool use. If your pipeline needs both extended reasoning and tool calls, use the standard DeepSeek-V3.2 model, which supports tool calls in both reasoning and non-reasoning modes.
- Zero Data Retention: AI Gateway supports Zero Data Retention for this model via direct gateway requests (BYOK is not included). To configure this, check the documentation.
- Authentication: AI Gateway authenticates requests using an API key or OIDC token. You do not need to manage provider credentials directly.
When to Use DeepSeek V3.2
Best For
- Complex scientific problems: A reasoning budget of 163K tokens allows thorough exploration of solution paths for mathematical and logical tasks
- Structured document analysis: Multi-step inference for legal reasoning, regulatory interpretation, and academic literature synthesis
- Chain-of-thought output: Research contexts where seeing the full reasoning trace is part of the desired output
- Reasoning model evaluation: The extended output budget lets you observe how the model approaches ambiguous or difficult prompts
Consider Alternatives When
- Tool calls required: Use standard DeepSeek-V3.2, which supports tool use alongside reasoning in both modes
- General chat or summarization: Standard DeepSeek-V3.2 costs less per output token for instruction-following without complex reasoning
- Latency-critical responses: Extended reasoning traces produce longer responses with higher time-to-complete
Conclusion
DeepSeek V3.2 gives you a high-capacity reasoning engine with an output budget of 163K tokens through a single AI Gateway endpoint, without requiring separate provider credentials. It's most valuable when problem complexity justifies deep chain-of-thought exploration and you don't need tool-use integration.
Frequently Asked Questions
Does DeepSeek V3.2 support tool calling?
No. The Thinking variant is a pure reasoning engine without tool-use support. For tool calls alongside reasoning, use the standard DeepSeek-V3.2 model.
What is the maximum output token budget for DeepSeek V3.2?
Up to 163K tokens per response, compared to 8K for the standard V3.2 chat variant.
When would I use DeepSeek V3.2 over DeepSeek-R1?
Choose DeepSeek V3.2 for the V3.2 stack and reasoning output up to 163K tokens. DeepSeek-R1 is MIT-licensed. If license terms matter for your deployment, confirm the license for the model you pick.
Why does the output token budget matter for reasoning models?
Reasoning models generate a chain-of-thought trace before the final answer. Complex problems can require thousands of reasoning tokens. A budget of 163K tokens provides headroom for multi-step derivations that would exceed an 8K limit.
How do I access DeepSeek V3.2 through AI Gateway?
Use the model ID
deepseek/deepseek-v3.2-thinkingwith an AI Gateway API key or OIDC token. No separate DeepSeek platform account is required.