OpenScale pricing overview
TokenWatch tracks 9 text, 0 image, and 0 video model records for this provider. Reviewed metadata says prompts are not retained. Retention: Chat Completions and Messages are never stored. Responses API stores responses for 30 days unless store:false or account ZDR is enabled; that is not the calculator default path.
Cheapest input price: DeepSeek V4.1 Flash at $0.060 per million input tokens and $0.240 per million output tokens. 9 of 9 text models publish a cache-read price; 9 carry a zero-data-retention tag.
OpenScale 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 |
|---|---|---|---|---|---|---|
| deepseek | openscale | DeepSeek: DeepSeek V4.1 Flash | $0.060 | $0.240 | $0.0030 | $0.0056 |
| deepseek | openscale | DeepSeek: DeepSeek V4.1 Flash 1017 | $0.060 | $0.240 | $0.0030 | $0.0056 |
| deepseek | openscale | DeepSeek: DeepSeek V4.1 Flash 0910 | $0.060 | $0.240 | $0.0030 | $0.0056 |
| z-ai | openscale | Z.ai: GLM 5.3 Flash | $0.120 | $0.400 | $0.024 | $0.028 |
| z-ai | openscale | Z.ai: GLM 5.3 Flash 0828 | $0.120 | $0.400 | $0.024 | $0.028 |
| deepseek | openscale | DeepSeek: DeepSeek V4.1 Flash (fast) | $0.280 | $1.10 | $0.028 | $0.040 |
| deepseek | openscale | DeepSeek: DeepSeek V4.1 Flash 1017 (fast) | $0.280 | $1.10 | $0.028 | $0.040 |
| deepseek | openscale | DeepSeek: DeepSeek V4.1 Flash 0910 (fast) | $0.280 | $1.10 | $0.028 | $0.040 |
| muse | openscale | Muse: Muse Glimmer 30B | $0.300 | $1.20 | $0.040 | $0.052 |
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.