| Spec | GLM 5.3 | GLM 5.3 Flash |
|---|---|---|
| Lowest input | $0.20Wafer | $0.05Wafer |
| Lowest output | $1.80Wafer | $0.20Wafer |
| Lowest cached input | $0.125DeepInfra | $0.0255Particle AI |
| Context | 1.05M | 1.05M |
| Max output | 524K | 524K |
| Providers | 12 | 12 |
| Released | August 14, 2026 | August 26, 2026 |
| Weights | Open | Open |
| Lab | Z.ai | Z.ai |
| Model ID | z-ai/glm-5.3 | z-ai/glm-5.3-flash |
USD per 1M tokens, as of November 5, 2026.
| Provider | GLM 5.3 | GLM 5.3 Flash |
|---|---|---|
| DeepInfra | $0.5625 / $2.50 | $0.15 / $0.50 |
| Doubleword | $1.40 / $4.40 | $0.15 / $0.50 |
| Inference.net | $0.90 / $3.00 | $0.10 / $0.45 |
| Morph | $1.19 / $6.00 | $0.20 / $0.70 |
| Nebius | $1.40 / $4.40 | $0.15 / $0.50 |
| Novita AI | $1.40 / $4.40 | $0.15 / $0.50 |
| Phala | $1.40 / $4.40 | $0.15 / $0.50 |
| RunInfra | $1.30 / $4.20 | $0.11 / $0.45 |
| StreamLake | $1.40 / $4.40 | $0.15 / $0.50 |
| Wafer | $0.20 / $1.80 | $0.05 / $0.20 |
| Mistral AI | $1.40 / $4.40 | – |
| Munito AI | – | $0.13 / $0.45 |
| Particle AI | – | $0.1275 / $0.425 |
| Sail Research | $0.98 / $3.08 | – |
Input / output, USD per 1M tokens.
| Model | 1,000 chat replies2K in, 500 out each | 1,000 agent tasks50K in, 5K out each | Monthly batch job500M in, 50M out |
|---|---|---|---|
| GLM 5.3Wafer | $1.30 | $19.00 | $190.00 |
| GLM 5.3 FlashWafer | $0.20 | $3.50 | $35.00 |
On each model's cheapest provider by input plus output list price.
Input: GLM 5.3 Flash at $0.05 per million input tokens vs $0.20 (GLM 5.3), 4x lower. Output: GLM 5.3 Flash at $0.20 per million output tokens vs $1.80 (GLM 5.3), 9x lower. Lowest listed prices as of November 5, 2026.
Both list 1.05M tokens of context.
10 providers serve both: Morph, DeepInfra, Nebius, Novita AI, Inference.net, RunInfra, StreamLake, Doubleword, Wafer, Phala. GLM 5.3 has 12 providers in total and GLM 5.3 Flash has 12.
GLM 5.3 from $0.125 per million cached input tokens (DeepInfra). GLM 5.3 Flash from $0.0255 (Particle AI).
Yes. Both use the same OpenAI-compatible endpoint, https://api.routerplus.com/v1, and key. Change the model field from "z-ai/glm-5.3" to "z-ai/glm-5.3-flash".
