> For clean Markdown content of this page, append .md to this URL. For the complete documentation index, see https://docs.nvidia.com/dynamo/llms.txt. For full content including API reference and SDK examples, see https://docs.nvidia.com/dynamo/llms-full.txt.

# Reasoning

Some models emit reasoning or thinking content separately from their final
response. Dynamo can split that output into `reasoning_content` and normal
assistant content by configuring a reasoning parser. As with tool calling,
there are two ways to do this to ensure wide coverage and day0 model support.

## Choose a parsing path

| Path | When to use | Page |
|------|-------------|------|
| **Dynamo** | Dynamo ships a Rust parser for the model's reasoning format. Lowest latency, the default path. | [Reasoning Parsing (Dynamo)](/dynamo/v1.1.1/user-guides/reasoning/reasoning-parsing-dynamo) |
| **Engine Fallback** | Use the framework's implementation (vLLM or SGLang) for pre/post processing, including tool call and reasoning parsing - ensure consistency with framework behavior. | [Reasoning Parsing (Engine Fallback)](/dynamo/v1.1.1/user-guides/reasoning/reasoning-parsing-engine-fallback) |

Start with the Dynamo path. Fall back to the engine path only when Dynamo's
registry does not list a parser for your model.

## See Also

- [Tool Calling](/dynamo/v1.1.1/user-guides/tool-calling) -- parse tool calls out of model
  output. Several models need both a reasoning parser and a tool-call parser
  configured together.
- [Frontend Configuration Reference](../components/frontend/configuration.md) --
  full CLI flag reference.

> Separate reasoning content from assistant output for chain-of-thought models

## Docs

- [Reasoning Parsing (Dynamo)](https://docs.nvidia.com/dynamo/v1.1.1/user-guides/reasoning/reasoning-parsing-dynamo.md): Configure Dynamo's built-in reasoning parsers for models that emit thinking content
- [Reasoning Parsing (Engine Fallback)](https://docs.nvidia.com/dynamo/v1.1.1/user-guides/reasoning/reasoning-parsing-engine-fallback.md): Use upstream vLLM or SGLang reasoning parsers when Dynamo does not ship one