GPT-4o

LLM Provider / Model · Multimodal tasks, fast chat, broad general use

At a glance

Input price	$2.50
Output price	$10
Cache price	$1.25
Price tier	Mid
Context window	128K
Max output	16K
Context tier	32K-128K
Speed tier	Fast
Latency	fast
Knowledge cutoff	Oct 2023
Modality	Multimodal (vision + audio)
Model ID	gpt-4o
Provider	OpenAI
HumanEval	90%
MMLU	88%
SWE-Bench	38%
Benchmark	HumanEval: high
Released	May 2024
Hosting	Closed/API
Capabilities	Vision, Audio, Tool use, Streaming, Structured output

Vision, Audio, Tool use, Streaming, Structured output

Multimodal tasks, fast chat, broad general use

Google Antigravity is built around Gemini 3 Pro; Claude and recent GPT-5 models also work, but GPT-4o is not in the supported model list.
Kiro's spec mode is tuned for Claude models — GPT-4o may work but spec-driven flows are best with Claude.
Gemini CLI is locked to Google Gemini models — your LLM is GPT-4o.
Claude Code only works with Claude models — your LLM is GPT-4o.
Devin uses Cognition's proprietary model internally — your selected GPT-4o will be ignored.
OpenAI Codex (Cloud) runs GPT-5.1 Codex internally — your selected GPT-4o will be ignored.
Jules runs Gemini models internally — your selected GPT-4o will be ignored.
The Claude Code SDK is tuned for Claude models — GPT-4o may work via the model adapter but loses Claude-specific features (thinking, prompt caching, sub-agents).
Lovable uses a fixed internal model — your selected GPT-4o will be ignored.
Replit Agent 3 uses its own model selection internally — your selected GPT-4o will be ignored.

Build a full stack around GPT-4o — Flowpicker shows compatibility warnings before you commit.