Output tokens cost $0.15 per million on agnes-2.5-flash and $1.97 per million on glm-5.2. Input tokens cost $0.03 per million on agnes-2.5-flash and $0.56 per million on glm-5.2. Cached input tokens are billed at $0.03 per million on agnes-2.5-flash and $0.14 per million on glm-5.2. Discounted rates are shown where a promotion is active. Context windows are 512,000 tokens on agnes-2.5-flash and 1,000,000 tokens on glm-5.2.
glm-5.2Agnes 2.5 Flash is Agnes AI’s fast and efficient language model, an upgraded, fully available model based on Agnes 2.0 Flash. It continues to use an OpenAI-compatible Chat Completions interface and has been optimized for coding tasks, agent workflows, tool calls, multi-turn dialogue, reasoning, and image understanding.
GLM-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.
Prices are per million tokens. Latency 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.
agnes-2.5-flash: $0.15/M output tokens; glm-5.2: $1.97/M. Use the cost calculator above to estimate your own workload.
agnes-2.5-flash accepts 512,000 and glm-5.2 accepts 1,000,000 input tokens. Maximum output per request is 56,500 tokens on agnes-2.5-flash and 128,000 tokens on glm-5.2.
agnes-2.5-flash accepts text and image input and supports thinking; glm-5.2 accepts text input and supports thinking, tool calling, function calling and structured outputs.
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