Side-by-side comparison of pricing, 12 benchmarks, and generation speed.
| Metric | GLM-4.7 (Non-reasoning) | Kimi K2 |
|---|---|---|
| Input ($/M tokens) | $0.6 | $0.57 |
| Output ($/M tokens) | $2.2 | $2.3 |
Verdict. GLM-4.7 (Non-reasoning) wins the overall benchmark matchup 1–0 across 1 overlapping categories, but raw benchmark score is only one input to the decision.
Pricing. Both models sit in the budget bracket for output-token pricing. At 1.0× the per-million-token cost, GLM-4.7 (Non-reasoning) is meaningfully cheaper if your traffic is output-heavy (long completions, document generation, agent loops). GLM-4.7 (Non-reasoning) makes more sense when output volume is low and absolute reasoning quality justifies the premium.
Strengths. GLM-4.7 (Non-reasoning) is strongest on Intelligence Index (17.4). Kimi K2 leads on Intelligence Index (12.7).
Speed. On throughput, GLM-4.7 (Non-reasoning) generates tokens at 103 tok/s versus 39 tok/s — about 62% faster. On time-to-first-token, GLM-4.7 (Non-reasoning) responds in 1130ms vs 1590ms, which matters most for chat-style UIs.
Provider. Z AI and Kimi sell to overlapping but distinct developer audiences: Z AI tends to ship frontier reasoning models with premium positioning, while Kimi often prices more aggressively. Your existing vendor relationships, billing, and SLA preferences may matter as much as the raw numbers above.
Workload cost. Workload scenarios (per million requests at 30M input + 15M output tokens): GLM-4.7 (Non-reasoning) costs $51.00 ($612/year); Kimi K2 costs $51.60 ($619/year). At a smaller 5M-input/2M-output scale (single-developer tool or prototype): GLM-4.7 (Non-reasoning) ≈ $7.40/run, Kimi K2 ≈ $7.45/run. At agent/realtime scale (200M input / 100M output per million requests): GLM-4.7 (Non-reasoning) ≈ $340/run, Kimi K2 ≈ $344/run. GLM-4.7 (Non-reasoning) becomes more attractive at higher volume — the absolute per-token pricing difference compounds when you ship at scale.
Recommendation. Both models have legitimate use cases — the right answer depends on whether you are optimizing for benchmark ceiling, latency, or unit cost. Start with the cheaper / faster model, evaluate against your specific task, and only switch if the upgrade shows a meaningful lift.
Head-to-head deltas
Data from Artificial Analysis API — 12 benchmarks
GLM-4.7 (Non-reasoning) is cheaper overall. Its blended price (3:1 input/output ratio) is $1.00/M tokens vs $1.00/M for Kimi K2.
GLM-4.7 (Non-reasoning) wins 1 out of 12 benchmarks compared to 0 for Kimi K2. See the detailed benchmark chart above for per-category results.
GLM-4.7 (Non-reasoning) generates tokens faster at 103 tok/s vs 39 tok/s. GLM-4.7 (Non-reasoning) also has lower time-to-first-token (1.13s vs 1.59s).
Choose based on your priorities: GLM-4.7 (Non-reasoning) for lower cost, GLM-4.7 (Non-reasoning) for stronger benchmark performance, and GLM-4.7 (Non-reasoning) for faster generation. For latency-sensitive apps, check the TTFT comparison above.