Ionstream 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: Qwen3.8 27B at $0.040 per million input tokens and $1.95 per million output tokens. 3 of 3 text models publish a cache-read price; 3 carry a zero-data-retention tag.
Ionstream 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 | ionstream | DeepSeek: DeepSeek V4.1 Flash 1017 | $0.165 | $0.495 | $0.010 | $0.017 |
| qwen | ionstream | Qwen: Qwen3.8 27B | $0.040 | $1.95 | $0.020 | $0.030 |
| deepseek | ionstream | DeepSeek: DeepSeek V4 Pro 0813 | $0.370 | $2.93 | $0.088 | $0.109 |
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.