GLM API pricing, every Z.ai model per million tokens
On 10 October 2026, Z.ai models on this list cost from $0.06 per million input tokens (GLM 4.7 Flash) to $2.80 (GLM 5.3 Prime), and from $0.40 per million output tokens (GLM 4.7 Flash) to $8.80 (GLM 5.3 Prime).
| Model | Input | Output | Cached input | Batch in / out | Context | Your month | Listed |
|---|---|---|---|---|---|---|---|
| GLM 5.3 Prime served by Alibaba | $2.80 | $8.80 | $0.56 | 1M | $300.00 | 2026-09-23 | |
| GLM 5.3 FlashX | $0.37 | $1.25 | $0.09 | 1.05M | $40.95 | 2026-09-18 | |
| GLM 5.3 Flash | $0.15 | $0.50 | $0.03 | $0.06 / $0.20 | 1.05M | $16.50 | 2026-08-26 |
| GLM 5.3 | $1.40 | $4.40 | $0.26 | $0.45 / $2.00 | 1.05M | $150.00 | 2026-08-18 |
| GLM 5.2 | $1.40 | $4.40 | $0.26 | 1.05M | $150.00 | 2026-06-16 | |
| GLM 5.1 | $1.40 | $4.40 | $0.26 | 205K | $150.00 | 2026-04-07 | |
| GLM 5V Turbo | $1.20 | $4.00 | $0.24 | 203K | $132.00 | 2026-04-01 | |
| GLM 5 Turbo | $1.20 | $4.00 | $0.24 | 203K | $132.00 | 2026-03-15 | |
| GLM 5 | $1.00 | $3.20 | $0.20 | 205K | $108.00 | 2026-02-11 | |
| GLM 4.7 Flash Venice, cheapest of 3 hosts | $0.06 | $0.40 | $0.01 | 200K | $9.60 | 2026-01-19 | |
| GLM 4.7 retiring 2026-12-31 | $0.60 | $2.20 | $0.11 | 205K | $69.00 | 2025-12-22 | |
| GLM 4.6V | $0.30 | $0.90 | $0.05 | 131K | $31.50 | 2025-12-08 | |
| GLM 4.6 | $0.60 | $2.20 | $0.11 | 205K | $69.00 | 2025-09-30 | |
| GLM 4.5V | $0.60 | $1.80 | $0.11 | 66K | $63.00 | 2025-08-11 | |
| GLM 4.5 retiring 2026-12-31 | $0.60 | $2.20 | $0.11 | 131K | $69.00 | 2025-07-25 | |
| GLM 4.5 Air | $0.20 | $1.10 | $0.03 | 131K | $28.50 | 2025-07-25 |
2 of these 16 models are not served by Z.ai itself on OpenRouter, so their price is the cheapest regular price among the hosts that run them, and the host is named under the model. Compare Z.ai with every other provider
Common questions
How much does the GLM API cost?
On 10 October 2026, Z.ai models on this list cost from $0.06 per million input tokens (GLM 4.7 Flash) to $2.80 (GLM 5.3 Prime), and from $0.40 per million output tokens (GLM 4.7 Flash) to $8.80 (GLM 5.3 Prime).
What is the cheapest GLM model?
For a typical mix of three input tokens to every output token, the cheapest is GLM 4.7 Flash at $0.06 per million input tokens and $0.40 per million output tokens.
What is the newest GLM model on the list?
GLM 5.3 Prime, listed on 23 September 2026, at $2.80 per million input tokens and $8.80 per million output tokens.
Which GLM model has the largest context window?
GLM 5.3 FlashX, with 1.05M tokens of context.
Does Z.ai offer batch pricing?
Yes, 2 of its models on this list show a batch price, with batch input at a median of 36 percent of the standard price. Batch suits work that can wait for its answer.
Choosing a model for a production agent
Price is one input. Quality on your own cases, latency and the cost of retries decide the rest. Tell me what you are building.