Modelrun pricing overview
TokenWatch tracks 6 text, 0 image, and 0 video model records for this provider. TokenWatch does not have a provider-wide zero-retention verdict for this page.
Cheapest input price: MiniMax M3.1 Flash at $0.150 per million input tokens and $0.600 per million output tokens. 6 of 6 text models publish a cache-read price; 6 carry a zero-data-retention tag.
Modelrun 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 | modelrun | DeepSeek: DeepSeek V4.1 Flash 1017 | $0.170 | $0.670 | $0.0060 | $0.013 |
| minimax | modelrun | MiniMax: MiniMax M3.1 Flash | $0.150 | $0.600 | $0.015 | $0.021 |
| minimax | modelrun | MiniMax: MiniMax M3 | $0.300 | $1.30 | $0.050 | $0.062 |
| qwen | modelrun | Qwen: Qwen3.8 27B | $0.200 | $2.50 | $0.090 | $0.105 |
| modelrun | Google: Gemma 4 31B | $0.750 | $1.00 | $0.200 | $0.218 | |
| z-ai | modelrun | Z.ai: GLM 5.3 | $2.10 | $6.60 | $0.400 | $0.473 |
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.