Pricingby GlyphCrusoe
Inference host · 9 models · 9 priced routes · crusoe.ai
Models on Crusoe
| Model | In / out per 1M | Vs headline | |
|---|---|---|---|
| $0.05 / $0.25+497% vs headline | +497% | bf16 · gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. | |
| $0.1 / $0.4+32% vs headline | +32% | bf16 · NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total. | |
| $0.14 / $0.4+28% vs headline | +28% | bf16 · Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. | |
| $0.15 / $0.5+389% vs headline | +389% | fp4 · GLM-5.3-Flash is a native multimodal model from Z.ai. | |
| $0.29 / $1.2+376% vs headline | +376% | fp8 · DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. | |
| $0.29 / $1.2+97% vs headline | +97% | fp8 · DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the deepseek-flash API model name. | |
| $0.3 / $2.4+428% vs headline | +428% | fp8 · NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. | |
| $0.7 / $3.5-18% vs headline | -18% | bf16 · Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. | |
| $1.4 / $4.4+344% vs headline | +344% | fp4 · GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. |
About Crusoe
The round values the data center giant at $30.9 billion.