Synthetic pricing overview
TokenWatch tracks 13 text, 0 image, and 0 video model records for this provider. Reviewed metadata says prompts are not retained.
Cheapest input price: openai/gpt-oss-120b at $0.100 per million input tokens and $0.100 per million output tokens. 13 of 13 text models publish a cache-read price; 13 carry a zero-data-retention tag.
Synthetic text-model pricing
Text offerings ranked by the Agentic workload mix (2.5% input, 97% cached input, 0.5% output). Change the calculator mix for a workload-specific estimate.
| Org | Provider | Model | Input $/M | Output $/M | Cache $/M | Blended $/M |
|---|---|---|---|---|---|---|
| openai | synthetic | openai/gpt-oss-120b | $0.100 | $0.100 | $0.020 | $0.022 |
| z-ai | synthetic | syn:small:text | $0.100 | $0.500 | $0.020 | $0.024 |
| z-ai | synthetic | zai-org/GLM-4.7-Flash | $0.100 | $0.500 | $0.020 | $0.024 |
| z-ai | synthetic | zai-org/GLM-5.3-Flash | $0.150 | $0.500 | $0.030 | $0.035 |
| nvidia | synthetic | nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4 | $0.300 | $1.00 | $0.060 | $0.071 |
| qwen | synthetic | Qwen/Qwen3.8-27B | $0.450 | $2.20 | $0.090 | $0.110 |
| deepseek | synthetic | syn:large:text | $0.600 | $1.20 | $0.120 | $0.137 |
| deepseek | synthetic | syn:small:vision | $0.600 | $1.20 | $0.120 | $0.137 |
| deepseek | synthetic | deepseek-ai/DeepSeek-V4.1-Flash-1017 | $0.600 | $1.20 | $0.120 | $0.137 |
| deepseek | synthetic | deepseek-ai/DeepSeek-V4.1-Flash | $0.600 | $1.20 | $0.120 | $0.137 |
| z-ai | synthetic | zai-org/GLM-5.3 | $1.40 | $4.40 | $0.280 | $0.329 |
| moonshot | synthetic | syn:large:vision | $3.00 | $15.00 | $0.600 | $0.732 |
| moonshot | synthetic | moonshotai/Kimi-K3 | $3.00 | $15.00 | $0.600 | $0.732 |
Catalog snapshot 2026-10-29 from direct-provider APIs, OpenRouter endpoint data, and maintained fallbacks. See the sources and calculation rules; verify rates on the provider's official pricing page before committing spend.