Openinference pricing overview
TokenWatch tracks 3 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: DeepSeek V4.1 Flash at $0.030 per million input tokens and $1.37 per million output tokens. 3 of 3 text models publish a cache-read price; 3 carry a zero-data-retention tag.
No reviewed policy links are currently listed.
Openinference 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 | openinference | DeepSeek: DeepSeek V4.1 Flash | $0.030 | $1.37 | $0.027 | $0.034 |
| z-ai | openinference | Z.ai: GLM 5.3 Flash | $0.053 | $0.083 | $0.048 | $0.048 |
| deepseek | openinference | DeepSeek: DeepSeek V4.1 Flash 1017 | $0.054 | $1.64 | $0.054 | $0.062 |
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.