#GPT-5 and Tools

4 messages · Page 1 of 1 (latest)

spare rapids
#

I want to use gpt-5 in my app with the tools that I made, but "openai/gpt-5-chat" doesn't support tools.

So I looked to use "openai/gpt-5" but I really don't want the reasoning part, because it slows down the model. I tried disabling it but got : {"error": "Reasoning is mandatory for this endpoint and cannot be disabled."}

How do you use gpt-5 and tools?

steep geyserBOT
#

I'm an AI assistant - my answers may be incorrect and I cannot see screenshots. Please verify information with the OpenRouter docs.

You cannot use tools with "openai/gpt-5-chat", and "openai/gpt-5" requires reasoning, which cannot be disabled. For your use case—using GPT-5 with tools and minimal reasoning latency—the best alternative is to use openai/gpt-5-nano. According to the documentation:

"GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments. ... Thanks to its efficient architecture ... o4-mini can chain tools, generate structured outputs, and solve multi-step tasks with minimal delay—often in under a minute."
"Supported parameters: Tools, Tool Choice, Structured Outputs, Response Format, Seed, Max Tokens, 100%."
GPT-5 Nano - API, Providers, Stats

To use GPT-5-Nano with tools, set model: "openai/gpt-5-nano" in your API call and include your tool definitions as you would with other OpenAI-compatible tool-using models.

If you need more control over reasoning effort, consider openai/gpt-5-codex, which allows you to adjust the reasoning.effort parameter and also supports tools and agentic workflows GPT-5 Codex.

You can browse all available models and their tool support at OpenRouter Models.

-# This is an automated response powered by Answer HQ. Use !mute to stop the bot from responding.

The author you are looking for could not be found.

GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments. While limited in reasoning depth compared to its larger counterparts, it retains key instruction-following and safety features. Run GPT-5 Nano with API

The model you are looking for could not be found.

The author you are looking for could not be found.

spare rapids
jolly isle