| Spec | DeepSeek V4 Pro | GLM 5.3 |
|---|---|---|
| Lowest input | $1.30DeepInfra | $0.20Wafer |
| Lowest output | $2.60DeepInfra | $1.80Wafer |
| Lowest cached input | $0.0036Inference.net | $0.125DeepInfra |
| Context | 1.05M | 1.05M |
| Max output | 524K | 524K |
| Providers | 4 | 12 |
| Released | April 24, 2026 | August 14, 2026 |
| Weights | Open | Open |
| Lab | DeepSeek | Z.ai |
| Model ID | deepseek/deepseek-v4-pro | z-ai/glm-5.3 |
USD per 1M tokens, as of November 5, 2026.
| Provider | DeepSeek V4 Pro | GLM 5.3 |
|---|---|---|
| DeepInfra | $1.30 / $2.60 | $0.5625 / $2.50 |
| Inference.net | $2.10 / $4.20 | $0.90 / $3.00 |
| Novita AI | $1.60 / $3.20 | $1.40 / $4.40 |
| StreamLake | $1.74 / $3.48 | $1.40 / $4.40 |
| Doubleword | – | $1.40 / $4.40 |
| Mistral AI | – | $1.40 / $4.40 |
| Morph | – | $1.19 / $6.00 |
| Nebius | – | $1.40 / $4.40 |
| Phala | – | $1.40 / $4.40 |
| RunInfra | – | $1.30 / $4.20 |
| Sail Research | – | $0.98 / $3.08 |
| Wafer | – | $0.20 / $1.80 |
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 |
|---|---|---|---|
| DeepSeek V4 ProDeepInfra | $3.90 | $78.00 | $780.00 |
| GLM 5.3Wafer | $1.30 | $19.00 | $190.00 |
On each model's cheapest provider by input plus output list price.
Input: GLM 5.3 at $0.20 per million input tokens vs $1.30 (DeepSeek V4 Pro), 6.5x lower. Output: GLM 5.3 at $1.80 per million output tokens vs $2.60 (DeepSeek V4 Pro), 44% lower. Lowest listed prices as of November 5, 2026.
Both list 1.05M tokens of context.
4 providers serve both: DeepInfra, Novita AI, Inference.net, StreamLake. DeepSeek V4 Pro has 4 providers in total and GLM 5.3 has 12.
DeepSeek V4 Pro from $0.0036 per million cached input tokens (Inference.net). GLM 5.3 from $0.125 (DeepInfra).
Yes. Both use the same OpenAI-compatible endpoint, https://api.routerplus.com/v1, and key. Change the model field from "deepseek/deepseek-v4-pro" to "z-ai/glm-5.3".
