Models and pricing
| Model ID | Input / 1M tokens | Output / 1M tokens | Cache read / 1M tokens | Cache write / 1M tokens |
|---|---|---|---|---|
| deepseek-ai/Deepseek-V4-Flash | $0.14 | $0.28 | $0.03 | — |
| deepseek-ai/DeepSeek-V4-Pro | $1.74 | $3.48 | $0.15 | — |
| deepseek-ai/DeepSeek-V4.1-Flash | $0.29 | $1.2 | $0.007 | — |
| google/gemma-4-31b-it | $0.14 | $0.4 | $0.14 | — |
| nvidia/Nemotron-3-Nano-Omni-Reasoning-30B-A3B | $0.3 | $1.83 | $0.3 | — |
| nvidia/Nemotron-3.5-Lightning-30B-A3B | $0.05 | $0.2 | $0.03 | — |
| nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B | $0.05 | $0.2 | $0.03 | — |
| nvidia/NVIDIA-Nemotron-3-Super-120B-A12B | $0.3 | $2.4 | $0.15 | — |
| nvidia/NVIDIA-Nemotron-3.5-Super-VL | $0.1 | $0.4 | $0.08 | — |
| openai/gpt-oss-120b | $0.05 | $0.25 | $0.05 | — |
| Qwen/Qwen3.8-27B | $0.25 | $2 | $0.15 | — |
| zai-org/GLM-5.3 | $1.4 | $4.4 | $0.26 | — |
| zai-org/GLM-5.3-Flash | $0.15 | $0.5 | $0.03 | — |
curl --request GET \
--url 'https://api.narev.ai/v1/prices?provider_id=crusoe&model_id=deepseek-ai%2FDeepseek-V4-Flash'
{
"model_id": "deepseek-ai/Deepseek-V4-Flash",
"provider_id": "crusoe",
"pricing": {
"prompt": 1.4e-7,
"completion": 2.8e-7,
"discount": 0,
"request": 0,
"web_search": 0,
"input_cache_read": 3e-8,
"input_cache_write": 0,
"image": 0,
"image_output": 0,
"audio": 0,
"audio_output": 0,
"input_audio_cache": 0,
"internal_reasoning": 0
}
}
Provider details
| Property | Value |
|---|---|
| Headquarters | US |
| API base URL | https://api.inference.crusoecloud.com/v1 |
| SDK package | @ai-sdk/openai-compatible |
| Environment variables | [“CRUSOE_API_KEY”] |
Data policies
| Policy | Value |
|---|---|
| Uses data for training | No |
| Retains prompts | No |
| Can publish data | No |