User Guides

Tool Calling

Parse tool calls from model output and surface them as OpenAI-compatible tool_calls

View as MarkdownOpen in Claude

Dynamo can connect models to external tools and services by parsing tool-call syntax out of raw model output and surfacing it as OpenAI-compatible tool_calls on the response. Tool calling is controlled by the tool_choice and tools request parameters on the chat completions API.

There are two ways to parse tool calls in Dynamo, depending on whether the parser lives in Dynamo’s own registry or in the upstream engine (vLLM, SGLang).

Choose a parsing path

PathWhen to usePage
DynamoDynamo ships a Rust parser for the model’s tool-call format. Lowest latency, the default path.Tool Call Parsing (Dynamo)
Engine FallbackUse the framework’s implementation (vLLM or SGLang) for pre/post processing, including tool call and reasoning parsing - ensure consistency with framework behavior.Tool Call 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.

Troubleshooting

If a tool call comes back wrong, add logprobs: true to a single repro request and share the response. See Troubleshooting Tool Calls for what to capture and include when reporting an issue.

See Also

  • Troubleshooting Tool Calls — capture raw model output with logprobs so tool-call issues can be localized.
  • Reasoning — separate reasoning_content from assistant content for chain-of-thought models. Several models need both a tool-call parser and a reasoning parser configured together.
  • Frontend Configuration Reference — full CLI flag reference.