---
title: "What are parallel tool calls? Several calls in one turn"
description: "Parallel tool calls let a model request several functions in one response. How parallel_tool_calls works, how to return the results, and how to turn it off."
url: https://broadrouter.com/glossary/parallel-tool-calls/
lang: en
updated: 2026-11-15
publisher: BroadRouter (a BroadNet site); API by BroadNet Inference, https://inference.broadnet.ai
---

# Parallel tool calls

Updated 2026-11-15

Parallel tool calls are when a model returns more than one tool call in a single response, for example three file reads at once. In the OpenAI format they arrive as several entries in tool\_calls, and parallel\_tool\_calls set to false limits the model to zero or one call per turn.

Also called: parallel tool calling, parallel function calling, parallel\_tool\_calls, multiple tool calls

An agent that needs three files does not have to ask for them one round trip at a time. With parallel tool calls the model asks for all three at once.

## How it works

In a [tool calling](https://broadrouter.com/glossary/tool-calling/) response, `message.tool_calls` is a list. With parallel calls it has more than one entry, each with its own `id`, function name and JSON arguments.

```json
"tool_calls": [
  {"id": "call_1", "type": "function", "function": {"name": "read_file", "arguments": "{\"path\": \"a.py\"}"}},
  {"id": "call_2", "type": "function", "function": {"name": "read_file", "arguments": "{\"path\": \"b.py\"}"}}
]
```

Your code runs the calls and appends one `tool` message per call, each with the matching `tool_call_id`, then calls the model again.

-   **OpenAI:** `parallel_tool_calls` defaults to `true`. Setting it to `false` “ensures exactly zero or one tool is called.” The guide warns that one model snapshot sometimes repeated calls to the same tool and recommends turning the feature off there.
-   **Anthropic:** parallel use is on by default. Turn it off with `disable_parallel_tool_use: true` inside the [tool\_choice](https://broadrouter.com/glossary/tool-choice/) object. Anthropic says the API “doesn’t prescribe an execution order”, and that all tool results should come back in a single user message to keep parallelism working.

## Why it matters

-   **Latency.** Fewer model round trips. Independent, read-only tools can run at the same time on your side.
-   **Ordering.** Calls with side effects, such as write then read, may depend on each other. Anthropic suggests running those sequentially. Or turn the feature off.
-   **Bookkeeping.** Every call needs a result with the right ID. A missing result is a common cause of the next request failing.

## On BroadNet Inference

BroadNet’s [API reference](https://inference.broadnet.ai/docs?utm_source=broadrouter&utm_medium=referral&utm_campaign=glossary-parallel-tool-calls&utm_content=body) documents tool calling for [GLM 5.3](https://broadrouter.com/models/glm-5.3/) and [Qwen3.8 27B](https://broadrouter.com/models/qwen3.8-27b/) and does not document `parallel_tool_calls`. Test whether your prompt gets several calls back and whether `false` is honoured. Parallel calls arrive in one response, so they do not add to your request count. Running the tools is on your side. Note that a BroadNet unlimited [plan](https://broadrouter.com/plans/) session allows one request at a time, and is for DeepSeek V4.1 Flash only; on pay-as-you-go keys the [concurrency](https://broadrouter.com/glossary/concurrency/) limit is 4 requests in flight. The [open-model tool calling post](https://broadrouter.com/blog/tool-calling-open-models/) has a working loop.

## Common mistakes

-   Returning results in a different message format for each call, or dropping one.
-   Running dependent tools concurrently because the model listed them together.

## Questions

### Do parallel tool calls mean parallel API requests?

No. The model returns several calls in one response. Your code runs them, concurrently or one by one, and sends all the results back in the next request.

### How do I turn parallel tool calls off?

In the OpenAI format set parallel\_tool\_calls to false; OpenAI says this "ensures exactly zero or one tool is called." In Anthropic's API set disable\_parallel\_tool\_use to true inside tool\_choice.

### Does BroadNet Inference support parallel\_tool\_calls?

BroadNet's API reference does not document parallel\_tool\_calls. Tool calling is documented for GLM 5.3 and Qwen3.8 27B; test whether they return several calls and whether the flag is honoured.

## See also

-   [Tool calling](https://broadrouter.com/glossary/tool-calling/) (term)
-   [tool\_choice](https://broadrouter.com/glossary/tool-choice/) (term)
-   [AI agent](https://broadrouter.com/glossary/agent/) (term)
-   [Concurrency](https://broadrouter.com/glossary/concurrency/) (term)
-   [Latency](https://broadrouter.com/glossary/latency/) (term)
-   [ReAct (reason and act)](https://broadrouter.com/glossary/react-agent/) (term)
-   [Request timeout](https://broadrouter.com/glossary/request-timeout/) (term)
-   [Tool calling with open models: schemas, parallel calls, retries](https://broadrouter.com/blog/tool-calling-open-models/) (article)
-   [What multi-agent setups really cost: per token vs flat sessions](https://broadrouter.com/blog/multi-agent-cost/) (article)

Try it on your real workload. New accounts start with $5 of credit for Gemma and transcription. DeepSeek, GLM and Qwen3.8 need a top-up.

[Get started](https://inference.broadnet.ai/account/?utm_source=broadrouter&utm_medium=referral&utm_campaign=glossary-parallel-tool-calls&utm_content=page-cta) ·

**Sources**

-   [OpenAI API reference, create chat completion (parallel\_tool\_calls) (checked 2026-11-15)](https://developers.openai.com/api/reference/resources/chat/subresources/completions/methods/create)
-   [OpenAI, function calling guide (parallel function calling) (checked 2026-11-15)](https://developers.openai.com/api/docs/guides/function-calling)
-   [Anthropic docs, parallel tool use (checked 2026-11-15)](https://platform.claude.com/docs/en/agents-and-tools/tool-use/parallel-tool-use)
