GLM API pricing
GLM API prices per million tokens, context windows, open-weights status and independent benchmark scores from Z.ai.
Prices updated . Benchmarks updated .
Prices are the current OpenRouter rate, refreshed about hourly. This page does not chart older prices.
| Model | You send / 1M | It replies / 1M | Context | ECI | Launched |
|---|---|---|---|---|---|
| GLM 5.3Open weights | $0.070 | $1.40 | 1M | 156.2 | 2026-08-14 |
| GLM 5.3 FlashOpen weights | $0.016 | $0.148 | 1M | 153.2 | 2026-08-26 |
| GLM 5.2Open weights | $0.0060 | $6.80 | 1M | 152.1 | 2026-06-13 |
| GLM 5.1Open weights | $1.40 | $4.40 | 200K | 149.9 | 2026-04-07 |
| GLM 5Open weights | $1.00 | $3.20 | 200K | 145.8 | 2026-02-12 |
| GLM 4.7Open weights | $0.540 | $1.98 | 200K | 143.7 | 2025-12-22 |
| GLM 5.3 PrimeClosed | $2.80 | $8.80 | 1M | n/a | 2026-09-23 |
| GLM 5.3 FlashXClosed | $0.370 | $1.25 | 1M | n/a | 2026-09-18 |
| GLM 5V TurboClosed | $1.20 | $4.00 | 200K | n/a | 2026-04-01 |
| GLM 5 TurboClosed | $1.20 | $4.00 | 200K | n/a | 2026-03-16 |
| GLM 4.7 FlashOpen weights | $0.060 | $0.400 | 200K | n/a | 2026-01-19 |
| GLM 4.6VOpen weights | $0.300 | $0.900 | 131K | n/a | 2025-12-08 |
| GLM 4.6Open weights | $0.500 | $2.00 | 205K | n/a | 2025-09-30 |
| GLM 4.5VOpen weights | $0.600 | $1.80 | 128K | n/a | 2025-08-11 |
| GLM 4.5Open weights | $0.600 | $2.20 | 128K | n/a | 2025-07-28 |
| GLM 4.5 AirOpen weights | $0.130 | $0.850 | 128K | n/a | 2025-07-28 |
Which Z.ai model ranks highest?
GLM 5.3 has the highest Epoch Capabilities Index among Z.ai models on this page, at 156.2. GLM 5.3 Flash is next at 153.2. GLM 5.3 costs $1.40 per million output tokens and reads 1M of context. The index is an independent score from Epoch AI. Lab-reported numbers are kept off this ranking.
Which Z.ai model is cheapest?
GLM 5.3 Flash has the lowest published output price among Z.ai models here, at $0.148 per million tokens. Input tokens cost $0.016 per million and the context window is 1M. GLM 4.7 Flash is next at $0.400 per million output tokens. Its Epoch Capabilities Index is 153.2. Prices are the current public rate and can change.
Which Z.ai open-weight models lead?
GLM 5.3 leads Z.ai open-weight models that have a published Epoch Capabilities Index, at 156.2. It is from Z.ai, costs $1.40 per million output tokens, and reads 1M. GLM 5.3 Flash from Z.ai follows at 153.2. Open weights means the lab published the weights. The license on the model page says what you can do with them.
FAQ
Which Z.ai model ranks highest?
GLM 5.3 has the highest Epoch Capabilities Index among Z.ai models on this page, at 156.2. GLM 5.3 Flash is next at 153.2. GLM 5.3 costs $1.40 per million output tokens and reads 1M of context. The index is an independent score from Epoch AI. Lab-reported numbers are kept off this ranking.
Which Z.ai model is cheapest?
GLM 5.3 Flash has the lowest published output price among Z.ai models here, at $0.148 per million tokens. Input tokens cost $0.016 per million and the context window is 1M. GLM 4.7 Flash is next at $0.400 per million output tokens. Its Epoch Capabilities Index is 153.2. Prices are the current public rate and can change.
How many Z.ai models are listed?
This page lists 16 Z.ai models with a public price or an independent score. Open the comparison table to filter the full catalogue.
Sources and licenses
- OpenRouter: Prices, context windows, modalities and the model list come from the OpenRouter public API. Data: OpenRouter.
- Vercel AI Gateway: The no-training flag comes from the Vercel AI Gateway model list.
- models.dev: Lab launch dates, open-weights flags and knowledge cutoffs come from models.dev. Copyright (c) 2025 models.dev, MIT License.
- Epoch AI: Independent benchmark scores and the Epoch Capabilities Index (ECI) come from Epoch AI's Benchmarking Hub, used under CC BY 4.0. Epoch AI, Capabilities & benchmarking, epoch.ai/benchmarks. Scores Epoch marks as external keep their original license, and the source is named on each score.
- LMArena: Arena Elo (text, webdev and vision) comes from the LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset), CC BY 4.0, leaderboard date 2026-10-28.
- Lab-reported scores, when an editor has added them, are the lab's own numbers. Each one links to the source and is labeled lab-reported. They are not used to rank the lists.
- What a score measures: the benchmark guide.