ZAI

GLM-5 (Reasoning)

AI model by ZAI. Real-time pricing and benchmark data.

Pricing (per 1M tokens)

Input$1.00
Output$3.20
Blended (3:1)$1.55

Source: Artificial Analysis

Performance

Output Speed46 tok/s
Time to First Token1710ms

Median values from Artificial Analysis

Benchmarks

Editorial Analysis

Profile. GLM-5 (Reasoning) is a budget-tier option from ZAI at $3.20/M output tokens. Despite the low price, it scores competitively on measurable benchmarks — making it a candidate for high-volume production workloads where unit cost dominates.

Latency. On latency, GLM-5 (Reasoning) reports 46 tok/s output speed and 1710ms time-to-first-token. Output speed is on the slower end; for real-time chat consider pairing with a streaming front-end or routing latency-sensitive requests to a faster model.

Cost model. For a workload of 1M input tokens + 100K output tokens, GLM-5 (Reasoning) costs $1.32 per million input-equivalent requests. Multiply by your monthly request volume to project the bill, and compare against the speed/correctness profile above to decide if the trade-off is worth it for your workload.

Editorial summary generated from public pricing and benchmark data (Artificial Analysis API). All numbers are sourced — see the Artificial Analysis methodology for benchmark definitions. Last refreshed 2026-08-24.

Compare with similar models

ModelInputOutputSpeed
GLM-5 (Reasoning)Current
$1.00$3.2046 tok/s
Qwen3.5 122B A10B (Non-reasoning)
$0.40$3.20143 tok/s
Qwen3.5 122B A10B (Reasoning)
$0.40$3.20130 tok/s
Nova Pro
$0.80$3.20
Qwen3.8 27B
$0.45$3.20
Qwen3.8 27B (medium)
$0.50$3.0065 tok/s

Example Costs

Single Request
$0.0026
1.0K in / 500 out
1K Requests/day
$2.60
1.0M in / 500.0K out
10K Requests/day
$26.00
10.0M in / 5.0M out