GPT-4.1

LLM Provider / Model · Long-context coding, instruction-following, broad general use at mid price

At a glance

Input price	$2
Output price	$8
Cache price	$0.50
Price tier	Mid
Context window	1M+
Max output	32K
Context tier	500K+
Speed tier	Standard
Latency	fast
Knowledge cutoff	Jun 2024
Modality	Multimodal (vision)
Model ID	gpt-4.1
Provider	OpenAI
HumanEval	92%
MMLU	88%
SWE-Bench	55%
Benchmark	high coding
Released	Apr 2025
Hosting	Closed/API
Capabilities	Vision, Tool use, Streaming, Structured output, Long context

Vision, Tool use, Streaming, Structured output, Long context

Long-context coding, instruction-following, broad general use at mid price

Trae's built-in model menu may not include GPT-4.1 — Trae primarily ships with Claude/GPT/Gemini/DeepSeek.
Google Antigravity is built around Gemini 3 Pro; Claude and recent GPT-5 models also work, but GPT-4.1 is not in the supported model list.
Kiro's spec mode is tuned for Claude models — GPT-4.1 may work but spec-driven flows are best with Claude.
Gemini CLI is locked to Google Gemini models — your LLM is GPT-4.1.
Claude Code only works with Claude models — your LLM is GPT-4.1.
Devin uses Cognition's proprietary model internally — your selected GPT-4.1 will be ignored.
OpenAI Codex (Cloud) runs GPT-5.1 Codex internally — your selected GPT-4.1 will be ignored.
Jules runs Gemini models internally — your selected GPT-4.1 will be ignored.
The Claude Code SDK is tuned for Claude models — GPT-4.1 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-4.1 will be ignored.
Replit Agent 3 uses its own model selection internally — your selected GPT-4.1 will be ignored.

Build a full stack around GPT-4.1 — Flowpicker shows compatibility warnings before you commit.