> 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 Parsing (Dynamo) Some models emit reasoning separately from their final response. Dynamo can split that output into `reasoning_content` and normal assistant `content` by configuring `--dyn-reasoning-parser` on the backend worker. This page covers Dynamo-native parsing; if your model is not listed, use [engine fallback](/dynamo/dev/parsing/chat-processors), which also explains valid combinations of `--dyn-reasoning-parser`, `--dyn-chat-processor`, and `--dyn-tool-call-parser`. ## Configure Reasoning Parsing Select `--dyn-reasoning-parser` from the supported list below. The backend can be SGLang, TensorRT-LLM, vLLM, or another installed backend. For vLLM structured output or SGLang required/named tool choice, also configure the engine's native `--reasoning-parser`. The native parser controls when the grammar starts; Dynamo's parser populates `reasoning_content`. Parser names can differ between registries. To inspect the available worker flags, run: ```bash python -m dynamo. --help ``` The following example starts an SGLang worker for Qwen3.5: ```bash python -m dynamo.sglang \ --model Qwen/Qwen3.5-4B \ --dyn-tool-call-parser qwen3_coder \ --reasoning-parser qwen3 \ --dyn-reasoning-parser qwen3 ```

Some models need both parsers configured together. Common pairings include:

- `openai/gpt-oss-*`: `--dyn-tool-call-parser harmony --dyn-reasoning-parser gpt_oss` - `deepseek-ai/DeepSeek-V4-*`: `--dyn-tool-call-parser deepseek_v4 --dyn-reasoning-parser deepseek_v4` - `zai-org/GLM-4.7`: `--dyn-tool-call-parser glm47 --dyn-reasoning-parser glm45` - `moonshotai/Kimi-K2.5*` / Kimi K2.6 format-compatible outputs: `--dyn-tool-call-parser kimi_k2 --dyn-reasoning-parser kimi_k25` - `google/gemma-4-*` thinking models: `--dyn-tool-call-parser gemma4 --dyn-reasoning-parser gemma4 --custom-jinja-template examples/chat_templates/gemma4_tool.jinja` - `Qwen/Qwen3.5*`: `--dyn-tool-call-parser qwen3_coder --dyn-reasoning-parser qwen3` - MiniMax M2 style outputs: `--dyn-tool-call-parser minimax_m2 --dyn-reasoning-parser minimax_m2` - MiniMax M3 style outputs: `--dyn-tool-call-parser minimax_m3 --dyn-reasoning-parser minimax_m3` `minimax_append_think` is deprecated for MiniMax M2 tool-calling deployments. Use `--dyn-reasoning-parser minimax_m2` with `--dyn-tool-call-parser minimax_m2` so Dynamo can separate reasoning and pass MiniMax XML tool calls to the tool parser.

Reasoning parsing happens before tool call parsing. See [Tool Call Parsing (Dynamo)](/dynamo/dev/parsing/tool-call-parsing) for supported `--dyn-tool-call-parser` values. Start the Dynamo frontend in another terminal: ```bash python -m dynamo.frontend ``` Wait for the frontend health endpoint to return a successful response: ```bash curl --fail http://localhost:8000/health ``` Send an OpenAI-compatible chat completion request: ```bash curl -s http://localhost:8000/v1/chat/completions \ -H 'Content-Type: application/json' \ -d '{ "model": "Qwen/Qwen3.5-4B", "messages": [ { "role": "user", "content": "If a train leaves at 3pm going 60 mph and another leaves at 4pm going 80 mph, when does the second catch up?" } ] }' ``` Dynamo places the chain of thought in `reasoning_content` and the user-facing answer in `content`. ```json { "choices": [ { "index": 0, "message": { "role": "assistant", "reasoning_content": "The first train has a 1-hour head start at 60 mph, so it is 60 miles ahead at 4pm. The second train closes the gap at 80 - 60 = 20 mph. 60 / 20 = 3 hours after 4pm.", "content": "The second train catches up at 7pm." }, "finish_reason": "stop" } ] } ``` ## Supported Reasoning Parsers Choose a model family, then expand the matching model option to see its parser name and configuration details. The **Upstream name** column shows where the vLLM or SGLang parser name differs from Dynamo's. This is relevant for engine fallback and when configuring the native structured-output reasoning gate. A blank upstream column means the same name works everywhere. `Dynamo-only` means no upstream parser exists for this format. Parsers marked **Force-reasoning: Yes** emit reasoning content from token one without requiring an explicit opening tag such as ``. All others require the opening tag in the model output. **Parser:** `kimi_k25` **Upstream name:** Dynamo-only **Force-reasoning:** Yes **Notes:** `...` with force-reasoning **Parser:** `kimi` **Upstream name:** Dynamo-only **Force-reasoning:** No **Notes:** `◁think▷...◁/think▷` Kimi K2.7 may ignore `chat_template_kwargs.thinking=false` and continue to generate reasoning. Dynamo can separate emitted reasoning when a compatible parser is configured, but it cannot force the model to disable reasoning. Treat the request flag as best-effort for Kimi K2.7. **Parser:** `minimax_m2` **Upstream name:** vLLM: `minimax_m2` **Force-reasoning:** Yes **Notes:** `...` with force-reasoning **Parser:** `minimax_m3` **Upstream name:** vLLM: `minimax_m3` **Force-reasoning:** No **Notes:** `...`; recovers a prompt-prefilled opener **Parser:** `minimax_append_think` Deprecated **Upstream name:** Dynamo-only **Force-reasoning:** No **Notes:** Legacy pass-through with an implicit `` opener. Use `minimax_m2` for MiniMax M2 tool-calling deployments. **Parser:** `deepseek_v4` **Upstream name:** vLLM: `deepseek_v4`; SGLang: `deepseek-v4` **Force-reasoning:** No **Notes:** `...`. Aliases: `deepseek-v4`, `deepseekv4` **Parser:** `deepseek_r1` **Upstream name:** Same name across Dynamo, vLLM, and SGLang **Force-reasoning:** Yes **Notes:** Pass explicitly for V3.1/V3.2 (no alias) **Parser:** `qwen3` **Upstream name:** Same name across Dynamo, vLLM, and SGLang **Force-reasoning:** No **Notes:** `...` **Parser:** `glm45` **Upstream name:** Dynamo-only **Force-reasoning:** No **Notes:** Alias for `nemotron_deci`. `...` **Parser:** `nemotron3` **Upstream name:** vLLM: `nemotron_v3` **Force-reasoning:** Yes **Notes:** Alias for `deepseek_r1`. Also accepts `nemotron_v3` **Parser:** `nemotron_deci` **Upstream name:** Dynamo-only **Force-reasoning:** No **Notes:** `...` **Parser:** `nemotron_nano` **Upstream name:** Dynamo-only **Force-reasoning:** Yes **Notes:** Alias for `deepseek_r1` **Parser:** `gemma4` **Upstream name:** vLLM: `gemma4` **Force-reasoning:** No **Notes:** `<\|channel>thought\n...` with `thought\n` role label stripped. Aliases: `gemma-4` **Parser:** `gpt_oss` **Upstream name:** Dynamo-only **Force-reasoning:** No **Notes:** Harmony channel reasoning format **Parser:** `mistral` **Upstream name:** Same name across Dynamo, vLLM, and SGLang **Force-reasoning:** Yes **Notes:** `[THINK]...[/THINK]` **Parser:** `granite` **Upstream name:** Same name across Dynamo, vLLM, and SGLang **Force-reasoning:** No **Notes:** `Here's my thought process:` / `Here's my response:` **Parser:** `step3` **Upstream name:** Dynamo-only **Force-reasoning:** Yes **Notes:** `...` **Parser:** `basic` **Upstream name:** Dynamo-only **Force-reasoning:** No **Notes:** Plain `...`