Expired50% confidenceFactExact time
Starting from GPT-4o, OpenAI natively supports parallel function calling at the API level, allowing the model to return multiple simultaneously executable tool call instructions in a single inference.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/25/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 10/23/2026(expired)
Sources
Related Claims
VerifiedStarting from GPT-4, OpenAI introduced Function Calling (later renamed Tool Calling), where developers pass tool schemas to the model as JSON and the model returns structured invocation instructions.81% similarPartially VerifiedAnthropic proposed the Tool Use specification, and OpenAI upgraded Parallel Function Calling, allowing the model to trigger multiple tool calls simultaneously in a single inference pass.79% similarVerifiedOpenAI 的 Function Calling 和 Anthropic 的 Tool Use API 都是 ReAct 模式的标准化实现79% similarVerifiedThe project connects to large language models via OpenRouter, which serves as an AI model gateway supporting unified API calls to multiple large models such as GPT-4, Claude, and Llama.77% similarUnverifiedMainstream APIs from OpenAI, Anthropic, and others provide a strict mode which, when enabled, allows tool-call parameters to precisely match the Schema.76% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/613599API
curl https://kongchang.com/api/v1/knowledge/claims/613599MCP
get_claim(id=613599)