Gemini 2.5 Pro

LLM Provider / Model · Advanced reasoning, multimodal workflows, massive context tasks, agentic coding

At a glance

Input price	$1.25
Output price	$10
Price tier	Premium
Context window	1M+
Max output	65K
Context tier	500K+
Speed tier	Standard
Latency	medium
Knowledge cutoff	Jan 2025
Modality	Multimodal (vision + audio)
Model ID	gemini-2.5-pro
Provider	Google
HumanEval	92%
MMLU	90%
SWE-Bench	63%
Benchmark	top-tier
Released	Mar 2025
Hosting	Closed/API
Capabilities	Vision, Audio, Tool use, Extended thinking, Streaming, Structured output, Long context

Vision, Audio, Tool use, Extended thinking, Streaming, Structured output, Long context

Advanced reasoning, multimodal workflows, massive context tasks, agentic coding

Kiro's spec mode is tuned for Claude models — Gemini 2.5 Pro may work but spec-driven flows are best with Claude.
OpenAI Codex (VS Code) is tied to OpenAI's GPT-5.1 Codex family — Gemini 2.5 Pro is not selectable inside this integration.
Claude Code only works with Claude models — your LLM is Gemini 2.5 Pro.
Devin uses Cognition's proprietary model internally — your selected Gemini 2.5 Pro will be ignored.
OpenAI Codex (Cloud) runs GPT-5.1 Codex internally — your selected Gemini 2.5 Pro will be ignored.
The Claude Code SDK is tuned for Claude models — Gemini 2.5 Pro may work via the model adapter but loses Claude-specific features (thinking, prompt caching, sub-agents).
Lovable uses a fixed internal model — your selected Gemini 2.5 Pro will be ignored.
Replit Agent 3 uses its own model selection internally — your selected Gemini 2.5 Pro will be ignored.

Build a full stack around Gemini 2.5 Pro — Flowpicker shows compatibility warnings before you commit.