Crusoe API pricing
Hosted14 language models
As of Oct 14, 2026, Crusoe lists 14 language models through its API. Its cheapest language model is Gemma 3 12B IT at $0.10 input / $0.10 output per million tokens.
Language models (14)
Prices per million tokens.
crusoe/deepseek-ai/DeepSeek-R1-0528
- Input
- $3.00
- Output
- $7.00
- Context
- 164K
crusoe/deepseek-ai/DeepSeek-V3-0324
- Input
- $1.50
- Output
- $1.50
- Context
- 164K
crusoe/google/gemma-3-12b-it
- Input
- $0.10
- Output
- $0.10
- Context
- 131K
google/gemma-4-31b-it
- Input
- $0.14
- Output
- $0.40
- Context
- 262K
zai/GLM-5.1
- Input
- $1.20
- Output
- $4.40
- Context
- 200K
zai/GLM-5.2
- Input
- $1.40
- Output
- $4.40
- Context
- 1M
crusoe/openai/gpt-oss-120b
- Input
- $0.80
- Output
- $0.80
- Context
- 131K
crusoe/moonshotai/Kimi-K2-Thinking
- Input
- $2.50
- Output
- $2.50
- Context
- 262K
moonshotai/Kimi-K2.6
- Input
- $0.70
- Output
- $3.50
- Context
- 262K
crusoe/meta-llama/Llama-3.3-70B-Instruct
- Input
- $0.20
- Output
- $0.20
- Context
- 131K
crusoe/Qwen/Qwen3-235B-A22B-Instruct-2507
- Input
- $3.00
- Output
- $3.00
- Context
- 262K
Nemotron 3 Nano Omni Reasoning 30B A3B
nvidia/Nemotron-3-Nano-Omni-Reasoning-30B-A3B
- Input
- $0.30
- Output
- $1.83
- Context
- 256K
Nvidia Nemotron 3 Nano 30B A3B
nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B
- Input
- $0.05
- Output
- $0.20
- Context
- 262K
Nvidia Nemotron 3 Super 120B A12B
nvidia/NVIDIA-Nemotron-3-Super-120B-A12B
- Input
- $0.30
- Output
- $2.40
- Context
- 262K
Prices in USD from LiteLLM and models.dev, checked daily; confirm on Crusoe's pricing page before you rely on a number.