Crusoe pricing overview
TokenWatch tracks 11 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: gpt-oss-120b at $0.050 per million input tokens and $0.250 per million output tokens. 11 of 11 text models publish a cache-read price; 11 carry a zero-data-retention tag.
Crusoe 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 | crusoe | DeepSeek: DeepSeek V4.1 Flash 1017 | $0.290 | $1.20 | $0.0070 | $0.020 |
| deepseek | crusoe | DeepSeek: DeepSeek V4.1 Flash | $0.290 | $1.20 | $0.0070 | $0.020 |
| deepseek | crusoe | DeepSeek: DeepSeek V4 Flash 0423 | $0.140 | $0.280 | $0.030 | $0.034 |
| z-ai | crusoe | Z.ai: GLM 5.3 Flash | $0.150 | $0.500 | $0.030 | $0.035 |
| openai | crusoe | OpenAI: gpt-oss-120b | $0.050 | $0.250 | $0.050 | $0.051 |
| nvidia | crusoe | NVIDIA: Nemotron 3.5 Super VL | $0.100 | $0.400 | $0.080 | $0.082 |
| crusoe | Google: Gemma 4 31B | $0.140 | $0.400 | $0.140 | $0.141 | |
| nvidia | crusoe | NVIDIA: Nemotron 3 Super | $0.300 | $2.40 | $0.150 | $0.165 |
| deepseek | crusoe | DeepSeek: DeepSeek V4 Pro 0423 | $1.74 | $3.48 | $0.150 | $0.206 |
| z-ai | crusoe | Z.ai: GLM 5.3 | $1.40 | $4.40 | $0.260 | $0.309 |
| moonshot | crusoe | MoonshotAI: Kimi K2.6 | $0.700 | $3.50 | $0.350 | $0.374 |
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.