The Hy3 official version is honed for real-world business scenarios, using a Mixture-of-Experts (MoE) architecture with 295B total parameters and 21B activated parameters. It natively supports a 256K context window and offers multiple thinking modes: no_think (ultra-fast response), think_low (quick thinking), and think_high (deep reasoning), balancing ultra-fast responses, complex reasoning, and invocation cost. Compared with the Preview version, Hy3—based on real business feedback from Tencent Yuanbao, WorkBuddy, ima, Marvis, and others—focuses on improving the Coding Agent, long-form understanding, multi-turn context continuity, search QA, and complex task execution, performing more stably in reducing hallucinations, improving task completion, and engineering usability. It is better suited to practical scenarios such as frontend tasks, cross-file code development, long-document analysis, office automation, and multi-step Agent workflows.
hy3 vs kimi-k3
Output tokens cost $0.62 per million on hy3 and $15.00 per million on kimi-k3. Input tokens cost $0.16 per million on hy3 and $3.00 per million on kimi-k3. Cached input tokens are billed at $0.04 per million on hy3 and $0.30 per million on kimi-k3. Context lengths are 256,000 tokens on hy3 and 1,048,576 tokens on kimi-k3. Time to first token (TTFT) measured on AIHubMix is 3.7s on hy3 and 12.9s on kimi-k3. Measured output throughput is 26.5 tok/s on hy3 and 18.8 tok/s on kimi-k3. On the LMArena coding leaderboard hy3 scores 1503 and kimi-k3 scores 1531.
Kimi 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.
Pricing & Specifications
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.
Activity Past 30 Days
Daily traffic served through AIHubMix — how demand for each model is trending.
Tokens / day
Requests / day
Performance Past 3 Days
Measured on real AIHubMix traffic, hourly buckets. Gaps mean no traffic in that hour.
Throughput (tok/s)
TTFT (s)
Uptime (%)
LMArena Benchmarks
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.
Cost calculator
Estimate your monthly bill for the same workload on each model.
Monthly = daily × 30. Discounted rates applied where a promotion is active.
FAQ
Which is cheaper: hy3, kimi-k3?
hy3: $0.62/M output tokens; kimi-k3: $15.00/M. Use the cost calculator above to estimate your own workload.
How do their coding arena scores compare?
kimi-k3: 1531; hy3: 1503 (LMArena coding leaderboard).
Which responds faster?
hy3: 3.7s time to first token measured on AIHubMix; see the live performance charts above for how each model behaves across the day.
How large is each context window?
hy3 accepts 256,000 and kimi-k3 accepts 1,048,576 input tokens. Maximum output per request is 128,000 tokens on hy3 and 1,048,576 tokens on kimi-k3.
Which one generates tokens faster?
hy3 at 26.5 tok/s and kimi-k3 at 18.8 tok/s, measured as output throughput on AIHubMix — a separate metric from time to first token.
What inputs and capabilities does each model support?
hy3 accepts text input and supports tool calling, function calling, structured outputs, web search, long context and thinking; kimi-k3 accepts text, image and video input and supports thinking, function calling and structured outputs.
Can I call hy3 and kimi-k3 with the same API key?
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.
Popular comparisons
Related model match-ups readers also look at.
