Output tokens cost $3.94 per million on GLM 5.2 and $0.50 per million on grok-4-fast-non-reasoning. Input tokens cost $1.13 per million on GLM 5.2 and $0.20 per million on grok-4-fast-non-reasoning. Cached input tokens are billed at $0.28 per million on GLM 5.2 and $0.05 per million on grok-4-fast-non-reasoning. Context lengths are 1,000,000 tokens on GLM 5.2 and 2,000,000 tokens on grok-4-fast-non-reasoning. Time to first token (TTFT) measured on AIHubMix is 0.6s on GLM 5.2 and 2.7s on grok-4-fast-non-reasoning. Measured output throughput is 45.0 tok/s on GLM 5.2 and 136.9 tok/s on grok-4-fast-non-reasoning. On the LMArena coding leaderboard GLM 5.2 scores 1505 and grok-4-fast-non-reasoning scores 1459.
GLM 5.2
grok-4-fast-non-reasoningGLM-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.
Grok-4-fast is a cost-effective inference model developed by xAI that delivers cutting-edge performance with excellent token efficiency. The model features a 2 million token context window, advanced Web and X search capabilities, and a unified architecture supporting both "inference" and "non-inference" modes. Compared to Grok 4, it reduces thinking tokens by an average of 40% and lowers the price by 98% while achieving the same performance.
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.
grok-4-fast-non-reasoning: $0.50/M output tokens; GLM 5.2: $3.94/M. Use the cost calculator above to estimate your own workload.
GLM 5.2: 1505; grok-4-fast-non-reasoning: 1459 (LMArena coding leaderboard).
GLM 5.2: 0.6s 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 grok-4-fast-non-reasoning accepts 2,000,000 input tokens. Maximum output per request is 128,000 tokens on GLM 5.2 and 30,000 tokens on grok-4-fast-non-reasoning.
grok-4-fast-non-reasoning at 136.9 tok/s and GLM 5.2 at 45.0 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; grok-4-fast-non-reasoning accepts text and image input and supports 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