Compare Kimi K3 from Moonshot AI and Mercury 2.5 Preview from Inception on key metrics including benchmarks, price, context length, and other model features. Access both models and hundreds of others through the AIHubMix API.
Kimi K3
Mercury 2.5 PreviewKimi K3 is Kimi’s flagship model for long-horizon coding and end-to-end knowledge work, with a 1M-token context window and industry-leading intelligence.
Mercury 2.5 is the latest diffusion-based large language model (dLLM) released by Inception. It is the fastest inference LLM; unlike the sequential token-by-token generation approach, Mercury 2.5 can generate and optimize multiple tokens in parallel, achieving a generation speed of 1,107 tokens per second on standard GPUs. Compared to Mercury 2, its intelligence has increased by more than 10 percentage points, and its quality rivals leading cost-optimized frontier models such as GPT-5.6 Luna (Low), Gemini 3.5 Flash-Lite, and Claude Haiku 4.5.
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.
Estimate your monthly bill for the same workload on each model.
Monthly = daily × 30. Discounted rates applied where a promotion is active.
Mercury 2.5 Preview: $0.15/M output tokens; Kimi K3: $13.50/M. Use the cost calculator above to estimate your own workload.
Kimi K3: 3.5s time to first token measured on AIHubMix; see the live performance charts above for how each model behaves across the day.
Kimi K3 accepts 1,048,576 and Mercury 2.5 Preview accepts 260,000 input tokens. Maximum output per request is 1,048,576 tokens on Kimi K3 and 260,000 tokens on Mercury 2.5 Preview.
Mercury 2.5 Preview at 110.1 tok/s and Kimi K3 at 65.6 tok/s, measured as output throughput on AIHubMix — a separate metric from time to first token.
Kimi K3 accepts text, image and video input and supports thinking, function calling and structured outputs; Mercury 2.5 Preview accepts text input and supports thinking and tool calling.
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