Side-by-side comparison of pricing, 12 benchmarks, and generation speed.
| Metric | GLM-4.5V (Non-reasoning) | DeepSeek V3.1 (Non-reasoning) |
|---|---|---|
| Input ($/M tokens) | $0.6 | $0.56 |
| Output ($/M tokens) | $1.8 | $1.68 |
Verdict. DeepSeek V3.1 (Non-reasoning) takes the aggregate benchmark matchup 1–0 across 1 categories. Real workloads usually care about a handful of specific tasks — see the per-benchmark table above.
Pricing. Both models sit in the budget bracket for output-token pricing. At 1.1× the per-million-token cost, DeepSeek V3.1 (Non-reasoning) is meaningfully cheaper if your traffic is output-heavy (long completions, document generation, agent loops). DeepSeek V3.1 (Non-reasoning) makes more sense when output volume is low and absolute reasoning quality justifies the premium.
Strengths. GLM-4.5V (Non-reasoning) is strongest on Intelligence Index (6.8). DeepSeek V3.1 (Non-reasoning) leads on Intelligence Index (21.4).
Speed. Speed data is incomplete for this pair; benchmark and price should decide.
Provider. Z AI and DeepSeek sell to overlapping but distinct developer audiences: Z AI tends to ship frontier reasoning models with premium positioning, while DeepSeek 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-4.5V (Non-reasoning) costs $45.00 ($540/year); DeepSeek V3.1 (Non-reasoning) costs $42.00 ($504/year). At a smaller 5M-input/2M-output scale (single-developer tool or prototype): GLM-4.5V (Non-reasoning) ≈ $6.60/run, DeepSeek V3.1 (Non-reasoning) ≈ $6.16/run. At agent/realtime scale (200M input / 100M output per million requests): GLM-4.5V (Non-reasoning) ≈ $300/run, DeepSeek V3.1 (Non-reasoning) ≈ $280/run. DeepSeek V3.1 (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.
Data from Artificial Analysis API — 12 benchmarks
DeepSeek V3.1 (Non-reasoning) is cheaper overall. Its blended price (3:1 input/output ratio) is $0.84/M tokens vs $0.90/M for GLM-4.5V (Non-reasoning).
DeepSeek V3.1 (Non-reasoning) wins 1 out of 12 benchmarks compared to 0 for GLM-4.5V (Non-reasoning). See the detailed benchmark chart above for per-category results.
GLM-4.5V (Non-reasoning) generates tokens faster at 92 tok/s vs — tok/s. GLM-4.5V (Non-reasoning) also has lower time-to-first-token (1.85s vs —s).
Choose based on your priorities: DeepSeek V3.1 (Non-reasoning) for lower cost, DeepSeek V3.1 (Non-reasoning) for stronger benchmark performance, and GLM-4.5V (Non-reasoning) for faster generation. For latency-sensitive apps, check the TTFT comparison above.