AI Rate CardGLM API pricing: GLM-5.3, GLM-5.3 Flash and GLM-5.2 at every provider
Updated Oct 22, 2026
GLM models from Zhipu AI (sold internationally as Z.ai) have open weights, so besides Z.ai's own API they are sold by around 70 hosts and routers each. The tables below are rebuilt from today's prices on every page view.
The models in short
In the 21 October 2026 collection, price per 1 million tokens, input / output:
- GLM-5.3 - about $1.20 / $4.18 at Z.ai, $1.40 / $4.40 at most US hosts, from about $0.50 / $2.00 at the cheapest; 1 million tokens of context.
- GLM-5.3 Flash - the small fast model: about $0.12 / $0.42 at Z.ai, $0.15 / $0.50 typical, from $0.075 / $0.25; it also reads images and video.
- GLM-5.2 - the previous generation, about the same list price as 5.3 at Z.ai, from about $0.55 / $1.75 elsewhere.
- Free: NVIDIA's free endpoints serve GLM-5.3 and GLM-5.3 Flash at no charge, with rate limits; some routers have free coding variants.
GLM-5.3: every provider
| Provider | Model | Input, $ | Output, $ |
|---|---|---|---|
| aihubmix | Coding GLM 5.3 (free) | Free | Free |
| nvidia | GLM-5.3 | Free | Free |
| trustedrouter | Z.ai: GLM 5.3 | $0.19 | $1.58 |
| edenai | GLM-5.3 | $0.20 | $0.64 |
| edenai | GLM-5.3 | $0.20 | $0.64 |
| wafer.ai | GLM-5.3 | $0.20 | $1.80 |
| kenari | GLM-5.3 | $0.28 | $3.31 |
| openrouter | Z.ai: GLM 5.3 (batch) | $0.45 | $2.00 |
| cortecs | GLM-5.3 | $0.51 | $2.05 |
| fastrouter | Z.ai: GLM-5.3 | $0.56 | $2.48 |
| deepinfra | GLM-5.3 | $0.56 | $2.50 |
| vultr | GLM-5.3 | $0.75 | $3.00 |
| iteracompute | GLM-5.3 | $0.82 | $2.88 |
| deepinfra | GLM-5.3 | $0.90 | $4.00 |
| zhipuai | GLM-5.3 | $1.20 | $4.18 |
Live data: this table is built from today's prices.
GLM-5.3 Flash: every provider
| Provider | Model | Input, $ | Output, $ |
|---|---|---|---|
| aihubmix | Coding GLM 5.3 Flash (free) | Free | Free |
| nvidia | GLM-5.3-Flash | Free | Free |
| opencode | GLM-5.3-Flash | Free | Free |
| orcarouter | GLM-5.3-Flash (free) | Free | Free |
| openrouter | Z.ai: GLM 5.3 Flash | $0.0269 | $0.0996 |
| aihubmix | Coding GLM 5.3 Flash | $0.02817 | $0.0986 |
| openrouter | Z.ai: GLM 5.3 Flash (batch) | $0.05 | $0.18 |
| wafer.ai | GLM-5.3-Flash | $0.05 | $0.20 |
| trustedrouter | Z.ai: GLM 5.3 Flash | $0.05275 | $0.21 |
| 302ai | GLM-5.3-Flash | $0.075 | $0.25 |
| empiriolabs | GLM 5.3 Flash | $0.033 / request | $0.25 |
| fastrouter | Z.ai: GLM-5.3-Flash | $0.075 | $0.25 |
| edenai | GLM-5.3-Flash | $0.08 | $0.50 |
| iteracompute | GLM-5.3-Flash | $0.08 | $0.28 |
| zhipuai | GLM-5.3-Flash | $0.12 | $0.42 |
Live data: this table is built from today's prices.
GLM-5.2: every provider
| Provider | Model | Input, $ | Output, $ |
|---|---|---|---|
| aihubmix | Coding GLM 5.2 (free) | Free | Free |
| edenai | GLM-5.2 | $0.17 | $0.54 |
| edenai | GLM-5.2 | $0.17 | $0.54 |
| wafer.ai | GLM-5.2 | $0.19 | $4.40 |
| kenari | GLM-5.2 | $0.28 | $3.31 |
| trustedrouter | Z.ai: GLM 5.2 | $0.36 | $1.58 |
| iteracompute | GLM-5.2 | $0.53 | $1.72 |
| fastrouter | Z.ai: GLM 5.2 | $0.56 | $1.80 |
| standardcompute | GLM 5.2 | $0.56 | $1.80 |
| deepinfra | GLM-5.2 | $0.56 | $1.80 |
| ambient | GLM 5.2 | $0.60 | $2.00 |
| requesty | GLM-5.2 | $0.60 | $1.92 |
| edenai | GLM-5.2 | $0.70 | $2.20 |
| deepinfra | GLM-5.2 | $0.75 | $2.40 |
| zhipuai | GLM-5.2 | $1.20 | $4.18 |
Live data: this table is built from today's prices.
How to choose
- The strongest GLM, long documents, agents: GLM-5.3.
- High volume at a low price: GLM-5.3 Flash - roughly a tenth of GLM-5.3.
- Trying it out: a free endpoint, but expect rate limits and no guarantees.
- A very cheap row: check the card - some routers list a batch or flex price, and a price far below the others is marked for review. All GLM models in one table: Zhipu GLM at every provider. To estimate a month, use the cost calculator.
All prices in US dollars per 1 million tokens, before taxes, as the providers publish them; Z.ai prices quoted in yuan are converted at the day's rate. Every row links to a card with its source and check date.