Output tokens cost $82.50 per million on Claude Opus 4.1 and $3.75 per million on Gemini 3.7 Flash. Input tokens cost $16.50 per million on Claude Opus 4.1 and $0.75 per million on Gemini 3.7 Flash. Cached input tokens are billed at $16.50 per million on Claude Opus 4.1 and $0.08 per million on Gemini 3.7 Flash. Context lengths are 200,000 tokens on Claude Opus 4.1 and 1,048,576 tokens on Gemini 3.7 Flash. Time to first token (TTFT) measured on AIHubMix is 1.7s on Claude Opus 4.1 and 4.3s on Gemini 3.7 Flash. Measured output throughput is 40.6 tok/s on Claude Opus 4.1 and 84.1 tok/s on Gemini 3.7 Flash. On the LMArena coding leaderboard Claude Opus 4.1 scores 1505 and Gemini 3.7 Flash scores 1522.
Claude Opus 4.1
Gemini 3.7 FlashOpus 4.1 is an upgraded version of Claude Opus 4, with improvements mainly in agent tasks, practical coding, and reasoning. Compared to Opus 4, there is a slight improvement in software engineering accuracy; Opus 4.1 has higher accuracy at 74.5%.
Gemini 3.7 Flash is Google’s natively multimodal reasoning model for coding, agents, web development, and knowledge work. It supports a 1M-token context window and adjustable thinking levels. Compared with Gemini 3.6 Flash, it improves coding, tool use, multi-step planning, and instruction following.
Prices are per million tokens. Time to First Token and throughput are rolling averages measured on AIHubMix.
Promotional prices show the discounted rate; see each model page for promotion windows.
Daily traffic served through AIHubMix — how demand for each model is trending.
Measured on real AIHubMix traffic, hourly buckets. Gaps mean no traffic in that hour.
LMArena ratings by capability (Bradley-Terry, commonly called Elo). Higher is better.
Source: LMArena (arena.ai) leaderboard, imported by AIHubMix. Models without published ratings are omitted per chart.
Estimate your monthly bill for the same workload on each model.
Monthly = daily × 30. Discounted rates applied where a promotion is active.
Gemini 3.7 Flash: $3.75/M output tokens; Claude Opus 4.1: $82.50/M. Use the cost calculator above to estimate your own workload.
Gemini 3.7 Flash: 1522; Claude Opus 4.1: 1505 (LMArena coding leaderboard).
Claude Opus 4.1: 1.7s time to first token measured on AIHubMix; see the live performance charts above for how each model behaves across the day.
Claude Opus 4.1 accepts 200,000 and Gemini 3.7 Flash accepts 1,048,576 input tokens. Maximum output per request is 32,000 tokens on Claude Opus 4.1 and 65,536 tokens on Gemini 3.7 Flash.
Gemini 3.7 Flash at 84.1 tok/s and Claude Opus 4.1 at 40.6 tok/s, measured as output throughput on AIHubMix — a separate metric from time to first token.
Claude Opus 4.1 accepts text and image input and supports thinking, tool calling, function calling and structured outputs; Gemini 3.7 Flash accepts text, image, audio and video input and supports thinking, tool calling, function calling, structured outputs, web search and long context.
Yes. AIHubMix serves every model on this page behind one OpenAI-compatible endpoint, so switching between them is a one-line change to the model field — no second account, key or SDK.
Related model match-ups readers also look at.
AIHubMix