Output tokens cost $2.76 per million on glm-5.2 and $0.62 per million on hy3. Input tokens cost $0.79 per million on glm-5.2 and $0.16 per million on hy3. Cached input tokens are billed at $0.20 per million on glm-5.2 and $0.04 per million on hy3. Discounted rates are shown where a promotion is active. Context lengths are 1,000,000 tokens on glm-5.2 and 256,000 tokens on hy3. Time to first token (TTFT) measured on AIHubMix is 1.0s on glm-5.2 and 3.7s on hy3. Measured output throughput is 46.1 tok/s on glm-5.2 and 26.5 tok/s on hy3. On the LMArena coding leaderboard glm-5.2 scores 1507 and hy3 scores 1503.
glm-5.2
hy3GLM-5.2 is Z.ai’s flagship model for the era of long-horizon tasks. With a truly usable 1M-token context window, it can handle project-level engineering context, execute long-running tasks more reliably, follow engineering standards more consistently, and complete the full development workflow from requirements to multi-platform deployment in a single task.
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.
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.
hy3: $0.62/M output tokens; glm-5.2: $2.76/M. Use the cost calculator above to estimate your own workload.
glm-5.2: 1507; hy3: 1503 (LMArena coding leaderboard).
glm-5.2: 1.0s time to first token measured on AIHubMix; see the live performance charts above for how each model behaves across the day.
glm-5.2 accepts 1,000,000 and hy3 accepts 256,000 input tokens. Maximum output per request is 128,000 tokens on glm-5.2 and 128,000 tokens on hy3.
glm-5.2 at 46.1 tok/s and hy3 at 26.5 tok/s, measured as output throughput on AIHubMix — a separate metric from time to first token.
glm-5.2 accepts text input and supports thinking, tool calling, function calling and structured outputs; hy3 accepts text input and supports tool calling, function calling, structured outputs, web search, long context and thinking.
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