Sference pricing overview
TokenWatch tracks 8 text, 0 image, and 0 video model records for this provider. Reviewed metadata says prompts are not retained.
Cheapest input price: GLM 5.3 Flash at $0.200 per million input tokens and $0.600 per million output tokens. 8 of 8 text models publish a cache-read price; 8 carry a zero-data-retention tag.
Sference 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 | sference | DeepSeek V4.1 Flash (1017) | $0.500 | $1.50 | $0.050 | $0.069 |
| deepseek | sference | DeepSeek V4.1 Flash | $0.500 | $1.50 | $0.050 | $0.069 |
| z-ai | sference | GLM 5.3 Flash | $0.200 | $0.600 | $0.070 | $0.076 |
| deepseek | sference | DeepSeek V4 Flash | $0.280 | $0.560 | $0.070 | $0.078 |
| deepseek | sference | DeepSeek V4 Flash (0731) | $0.280 | $0.560 | $0.070 | $0.078 |
| z-ai | sference | GLM 5.2 | $1.20 | $4.20 | $0.260 | $0.303 |
| z-ai | sference | GLM 5.3 | $1.20 | $4.20 | $0.260 | $0.303 |
| moonshot | sference | Kimi K3 | $3.00 | $15.00 | $0.450 | $0.587 |
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.