Official site · 🇨🇳 China
| Tier | $/month | Included usage |
|---|---|---|
| Lite | $18.00 | — |
| Pro | $80.00 | — |
| Max | $168.00 | — |
console only quota converts to units
As advertised. 2.000 / 12.000 / 28.000 creditos por 5h; 10.000 / 60.000 / 140.000 por semana (confirmado en docs.z.ai/devpack/overview el 2026-09-06). La pagina de venta ya no ensena creditos: dice '6x Lite' y '14x Lite'.
What that actually means. Publican la formula entera, asi que los creditos SI convierten a tokens: creditos = (tokens de entrada x mult_in + cacheados x mult_cache + salida x mult_out) / 10.000. Multiplicadores por modelo: GLM-5.3 6,9 / 1,7 / 24; GLM-5.3-Flash 2,3 / 0,56 / 8; las llamadas MCP (Web Search, Web Reader, Zread) 1,2 de salida cada una. Y hay tabla de tokens por semana segun el acierto de cache — con GLM-5.3 al 95%, Lite 48-97 M, Pro 290-580 M y Max 676-1.352 M. La propia pagina dice que ahorra hasta un 92% contra llamar a la API por tokens.
Where to check what is left. z.ai subscription page; an undocumented monitor endpoint also exists and was verified directly
Models covered. GLM-5.3, GLM-5.3-Flash
checked 2026-10-09 · high (price and quota, rendered with a real browser) · source
| Model | Intelligence | tok/s | $/M in | $/M out | $ / session | Cache |
|---|---|---|---|---|---|---|
| GLM-5.2 | 33.7 | 85.1 | $0.06 | $7.00 | $0.9447 | 90.5% |
| GLM-5.3 | 44.8 | 71.2 | $0.04 | $4.80 | — | — |
| GLM-5.3-Flash | 41.8 | 58.6 | $0.15 | $0.50 | — | — |
| GLM-5.1 | 26.1 | 54.1 | $0.97 | $3.04 | $0.6288 | 88.5% |
| GLM 4.6 | 18.5 | 34.8 | $0.50 | $2.00 | — | — |
| GLM 4.7 | 22.2 | 41.9 | $0.60 | $2.20 | — | — |
6 endpoints, cheapest first. This is the view the model-by-model tables cannot give you: what one provider actually offers, and at what precision.
| Model | Quant | $/M in | $/M out | Context | Uptime 30m |
|---|---|---|---|---|---|
| GLM-5.3-Flash | fp8 | $0.15 | $0.50 | 1,048,576 | 100.0% |
| GLM 4.6 | fp4 | $0.60 | $2.20 | 202,752 | — |
| GLM 4.7 | fp4 | $0.60 | $2.20 | 202,752 | 100.0% |
| GLM-5.2 | fp8 | $1.40 | $4.40 | 1,048,576 | 100.0% |
| GLM-5.3 | fp8 | $1.40 | $4.40 | 1,048,576 | 100.0% |
| GLM-5.1 | fp8 | $1.40 | $4.40 | 202,752 | 100.0% |
Everyone serving these models, cheapest first, with the numeric precision each one runs. The lab is often not the cheapest place to buy its own model.
| Model | Served by | Quant | $/M in | $/M out | Uptime 30m |
|---|---|---|---|---|---|
| GLM-5.2 | Decart | mxfp4 | $0.27 | $1.68 | 100.0% |
| GLM-5.2 | StreamLake | fp8 | $0.56 | $1.75 | 100.0% |
| GLM-5.2 | DeepInfra | fp4 | $0.56 | $1.80 | 100.0% |
| GLM-5.2 | Novita | fp8 | $0.65 | $2.04 | 100.0% |
| GLM-5.2 | DigitalOcean | unknown | $0.70 | $2.20 | 100.0% |
| GLM-5.2 | CoreWeave | fp4 | $0.76 | $2.42 | 100.0% |
| GLM-5.2 | InferenceNet | fp4 | $0.18 | $4.40 | 100.0% |
| GLM-5.2 | AtlasCloud | fp8 | $0.94 | $2.95 | 100.0% |
| GLM-5.2 | Alibaba / Qwen | fp8 | $0.97 | $3.04 | — |
| GLM-5.2 | Morph | fp8 | $0.18 | $6.00 | 100.0% |
| GLM-5.2 | Phala | fp8 | $1.26 | $3.00 | 100.0% |
| GLM-5.2 | Alibaba / Qwen | fp8 | $1.12 | $3.52 | 100.0% |
| GLM-5.2 | Wafer | unknown | $0.06 | $7.00 | 100.0% |
| GLM-5.2 | SiliconFlow | fp8 | $1.19 | $3.74 | 100.0% |
| GLM-5.2 | Cloudflare | unknown | $0.50 | $6.00 | 100.0% |
| GLM-5.2 | Baidu | fp8 | $1.40 | $4.40 | 100.0% |
| GLM-5.2 | BaseTen | fp8 | $1.40 | $4.40 | 100.0% |
| GLM-5.2 | BaseTen | fp8 | $1.40 | $4.40 | 100.0% |
| GLM-5.2 | Friendli | unknown | $1.40 | $4.40 | 100.0% |
| GLM-5.2 | GMICloud | fp8 | $1.40 | $4.40 | 100.0% |
| GLM-5.2 | Mistral | nvfp4 | $1.40 | $4.40 | 100.0% |
| GLM-5.2 | Nebius | fp4 | $1.40 | $4.40 | 100.0% |
| GLM-5.2 | Parasail | fp4 | $1.40 | $4.40 | 100.0% |
| GLM-5.2 | Together | unknown | $1.40 | $4.40 | 100.0% |
| GLM-5.2 | Venice | fp8 | $1.40 | $4.40 | 100.0% |
| GLM-5.2 | Z.ai / Zhipu | fp8 | $1.40 | $4.40 | 100.0% |
| GLM-5.2 | Inceptron | fp4 | $1.25 | $5.46 | 100.0% |
| GLM-5.2 | Mistral | unknown | $1.54 | $4.84 | 100.0% |
| GLM-5.2 | Wafer | unknown | $0.19 | $10.00 | 100.0% |
| GLM-5.2 | BaseTen | fp8 | $2.10 | $6.60 | 100.0% |
| GLM-5.2 | BaseTen | fp8 | $2.10 | $6.60 | 100.0% |
| GLM-5.2 | Alibaba / Qwen | fp8 | $2.31 | $7.26 | 100.0% |
| GLM-5.2 | Baidu | fp4 | $2.25 | $7.88 | — |
| GLM-5.2 | Decart | fp4 | $2.50 | $9.00 | 100.0% |
| GLM-5.3 | Inceptron | fp4 | $0.60 | $2.20 | 100.0% |
| GLM-5.3 | Sail Research | fp8 | $0.20 | $3.40 | 100.0% |
| GLM-5.3 | Sail Research | fp8 | $0.20 | $3.40 | 100.0% |
| GLM-5.3 | DeepInfra | fp4 | $0.56 | $2.50 | 66.7% |
| GLM-5.3 | Novita | fp8 | $0.70 | $2.20 | 100.0% |
| GLM-5.3 | Reka | unknown | $0.14 | $4.20 | 100.0% |
| GLM-5.3 | InferenceNet | fp4 | $0.08 | $4.40 | 100.0% |
| GLM-5.3 | Makora | fp4 | $0.14 | $4.40 | 100.0% |
| GLM-5.3 | Wafer | unknown | $0.04 | $4.80 | 100.0% |
| GLM-5.3 | AkashML | fp8 | $0.19 | $4.40 | 100.0% |
| GLM-5.3 | Phala | unknown | $0.84 | $2.64 | 100.0% |
| GLM-5.3 | Decart | fp4 | $0.84 | $2.65 | 100.0% |
| GLM-5.3 | Wafer | unknown | $0.17 | $4.80 | 100.0% |
| GLM-5.3 | DigitalOcean | unknown | $0.91 | $2.86 | — |
| GLM-5.3 | Io Net | fp8 | $0.75 | $3.40 | 100.0% |
| GLM-5.3 | GMICloud | fp8 | $0.98 | $3.08 | — |
| GLM-5.3 | SiliconFlow | fp8 | $1.12 | $3.52 | — |
| GLM-5.3 | Alibaba / Qwen | unknown | $1.19 | $3.74 | — |
| GLM-5.3 | Friendli | unknown | $1.26 | $3.96 | 100.0% |
| GLM-5.3 | Morph | fp8 | $0.86 | $6.00 | 100.0% |
| GLM-5.3 | AtlasCloud | fp8 | $1.40 | $4.40 | 100.0% |
| GLM-5.3 | Baidu | fp8 | $1.40 | $4.40 | 100.0% |
| GLM-5.3 | BaseTen | fp4 | $1.40 | $4.40 | 100.0% |
| GLM-5.3 | BaseTen | fp4 | $1.40 | $4.40 | 100.0% |
| GLM-5.3 | Cloudflare | unknown | $1.40 | $4.40 | — |
| GLM-5.3 | Crusoe | fp4 | $1.40 | $4.40 | 100.0% |
| GLM-5.3 | Fireworks | unknown | $1.40 | $4.40 | 100.0% |
| GLM-5.3 | Mistral | nvfp4 | $1.40 | $4.40 | 100.0% |
| GLM-5.3 | Mistral | nvfp4 | $1.40 | $4.40 | 100.0% |
| GLM-5.3 | Modal | unknown | $1.40 | $4.40 | 100.0% |
| GLM-5.3 | Nebius | fp4 | $1.40 | $4.40 | 92.3% |
| GLM-5.3 | Parasail | fp8 | $1.40 | $4.40 | 100.0% |
| GLM-5.3 | PrimeIntellect | unknown | $1.40 | $4.40 | 100.0% |
| GLM-5.3 | Together | unknown | $1.40 | $4.40 | 100.0% |
| GLM-5.3 | Venice | unknown | $1.40 | $4.40 | 100.0% |
| GLM-5.3 | Z.ai / Zhipu | fp8 | $1.40 | $4.40 | 100.0% |
| GLM-5.3 | Mistral | nvfp4 | $1.54 | $4.84 | 100.0% |
| GLM-5.3 | BaseTen | fp8 | $2.10 | $6.60 | 100.0% |
| GLM-5.3 | BaseTen | fp8 | $2.10 | $6.60 | 100.0% |
| GLM-5.3 | Fireworks | unknown | $2.10 | $6.60 | 100.0% |
| GLM-5.3 | Alibaba / Qwen | unknown | $2.80 | $8.80 | — |
| GLM-5.3-Flash | StreamLake | fp8 | $0.07 | $0.23 | 100.0% |
| GLM-5.3-Flash | DeepInfra | fp4 | $0.07 | $0.25 | 100.0% |
| GLM-5.3-Flash | Novita | fp8 | $0.08 | $0.28 | 100.0% |
| GLM-5.3-Flash | GMICloud | fp8 | $0.09 | $0.30 | 100.0% |
| GLM-5.3-Flash | OpenInference | fp4 | $0.04 | $0.45 | 100.0% |
| GLM-5.3-Flash | Decart | fp4 | $0.09 | $0.31 | 100.0% |
| GLM-5.3-Flash | Relace | unknown | $0.04 | $0.50 | 100.0% |
| GLM-5.3-Flash | Near AI | fp8 | $0.10 | $0.35 | 100.0% |
| GLM-5.3-Flash | InferenceNet | fp4 | $0.07 | $0.50 | 100.0% |
| GLM-5.3-Flash | Wafer | unknown | $0.07 | $0.50 | 100.0% |
| GLM-5.3-Flash | Phala | nvfp4 | $0.11 | $0.38 | 100.0% |
| GLM-5.3-Flash | Sail Research | fp4 | $0.04 | $0.60 | 100.0% |
| GLM-5.3-Flash | Sail Research | fp4 | $0.04 | $0.60 | 100.0% |
| GLM-5.3-Flash | Inceptron | fp8 | $0.12 | $0.55 | 100.0% |
| GLM-5.3-Flash | AtlasCloud | fp8 | $0.15 | $0.50 | 7.7% |
| GLM-5.3-Flash | BaseTen | fp8 | $0.15 | $0.50 | 100.0% |
| GLM-5.3-Flash | BaseTen | fp8 | $0.15 | $0.50 | 100.0% |
| GLM-5.3-Flash | CoreWeave | nvfp4 | $0.15 | $0.50 | 100.0% |
| GLM-5.3-Flash | Crusoe | fp4 | $0.15 | $0.50 | 100.0% |
| GLM-5.3-Flash | DigitalOcean | unknown | $0.15 | $0.50 | 100.0% |
| GLM-5.3-Flash | Fireworks | unknown | $0.15 | $0.50 | 100.0% |
| GLM-5.3-Flash | Friendli | unknown | $0.15 | $0.50 | 100.0% |
| GLM-5.3-Flash | Modal | nvfp4 | $0.15 | $0.50 | 100.0% |
| GLM-5.3-Flash | Parasail | fp4 | $0.15 | $0.50 | 100.0% |
| GLM-5.3-Flash | SiliconFlow | fp8 | $0.15 | $0.50 | 55.6% |
| GLM-5.3-Flash | Together | unknown | $0.15 | $0.50 | 100.0% |
| GLM-5.3-Flash | Venice | unknown | $0.15 | $0.50 | 100.0% |
| GLM-5.3-Flash | Z.ai / Zhipu | fp8 | $0.15 | $0.50 | 100.0% |
| GLM-5.3-Flash | Morph | fp8 | $0.11 | $0.75 | 93.3% |
| GLM-5.3-Flash | Parasail | fp4 | $0.19 | $0.62 | 100.0% |
| GLM-5.3-Flash | DekaLLM | unknown | $0.10 | $1.00 | 100.0% |
| GLM-5.3-Flash | Fireworks | unknown | $0.22 | $0.75 | 100.0% |
| GLM-5.3-Flash | Reka | unknown | $0.06 | $1.60 | 100.0% |
| GLM-5.1 | StreamLake | fp8 | $0.97 | $3.04 | 100.0% |
| GLM-5.1 | Chutes | fp8 | $0.98 | $3.08 | — |
| GLM-5.1 | SiliconFlow | fp8 | $1.19 | $3.74 | 100.0% |
| GLM-5.1 | AtlasCloud | fp8 | $1.26 | $3.96 | — |
| GLM-5.1 | Phala | unknown | $1.21 | $4.20 | — |
| GLM-5.1 | Alibaba / Qwen | fp8 | $1.33 | $4.18 | — |
| GLM-5.1 | Novita | fp8 | $1.38 | $4.40 | 100.0% |
| GLM-5.1 | Baidu | fp8 | $1.40 | $4.40 | — |
| GLM-5.1 | Friendli | unknown | $1.40 | $4.40 | 100.0% |
| GLM-5.1 | GMICloud | fp8 | $1.40 | $4.40 | — |
| GLM-5.1 | Nebius | fp8 | $1.40 | $4.40 | 100.0% |
| GLM-5.1 | Z.ai / Zhipu | fp8 | $1.40 | $4.40 | 100.0% |
| GLM-5.1 | Venice | fp8 | $1.40 | $4.40 | — |
| GLM 4.6 | Venice | fp4 | $0.43 | $1.75 | 100.0% |
| GLM 4.6 | DeepInfra | fp4 | $0.50 | $2.00 | 100.0% |
| GLM 4.6 | Novita | bf16 | $0.55 | $2.20 | 100.0% |
| GLM 4.6 | Z.ai / Zhipu | fp4 | $0.60 | $2.20 | — |
| GLM 4.7 | DeepInfra | fp4 | $0.40 | $1.75 | 100.0% |
| GLM 4.7 | Venice | fp4 | $0.40 | $1.93 | 100.0% |
| GLM 4.7 | Novita | fp8 | $0.54 | $1.98 | 100.0% |
| GLM 4.7 | unknown | $0.60 | $2.20 | 100.0% | |
| GLM 4.7 | Z.ai / Zhipu | fp4 | $0.60 | $2.20 | 100.0% |
| GLM 4.7 | Mancer 2 | fp4 | $0.70 | $2.50 | 100.0% |