Output tokens cost $1.68 per million on DeepSeek V3.1 Thinking and $3.94 per million on GLM 5.2. Input tokens cost $0.56 per million on DeepSeek V3.1 Thinking and $1.13 per million on GLM 5.2. Cached input tokens are billed at $0.56 per million on DeepSeek V3.1 Thinking and $0.28 per million on GLM 5.2. Context lengths are 128,000 tokens on DeepSeek V3.1 Thinking and 1,000,000 tokens on GLM 5.2. Time to first token (TTFT) measured on AIHubMix is 1.3s on DeepSeek V3.1 Thinking and 0.6s on GLM 5.2. Measured output throughput is 31.5 tok/s on DeepSeek V3.1 Thinking and 45.3 tok/s on GLM 5.2. On the LMArena coding leaderboard DeepSeek V3.1 Thinking scores 1458 and GLM 5.2 scores 1505.
DeepSeek V3.1 Thinking
GLM 5.2Thinking mode of DeepSeek-V3.1; DeepSeek V3.1 is a text generation model provided by DeepSeek, featuring a hybrid reasoning architecture that achieves an effective integration of thinking and non-thinking modes.
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. 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.
DeepSeek V3.1 Thinking: $1.68/M output tokens; GLM 5.2: $3.94/M. Use the cost calculator above to estimate your own workload.
GLM 5.2: 1505; DeepSeek V3.1 Thinking: 1458 (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.
DeepSeek V3.1 Thinking accepts 128,000 and GLM 5.2 accepts 1,000,000 input tokens. Maximum output per request is 32,000 tokens on DeepSeek V3.1 Thinking and 128,000 tokens on GLM 5.2.
GLM 5.2 at 45.3 tok/s and DeepSeek V3.1 Thinking at 31.5 tok/s, measured as output throughput on AIHubMix — a separate metric from time to first token.
DeepSeek V3.1 Thinking accepts text input and supports thinking, tool calling, function calling and structured outputs; 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