ovhcloud/gpt-oss-120b · price provider-declared (via models.dev), USD per 1M tokens. Capabilities: toolsreasoningtext.
ovhcloud)“gpt-oss-120b” is offered by 9 providers — cheapest-effective first. Nvidia is the cheapest at $0.00 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Nvidia | free | free | $0.00 | 128k |
| Privatemode AI | free | free | $0.00 | 128k |
| Weights & Biases | $0.03 | $0.17 | $0.07 | 131k |
| OVHcloud AI Endpoints (this) | $0.09 | $0.47 | $0.18 | 131k |
| Nebius Token Factory | $0.15 | $0.6 | $0.26 | 128k |
| Amazon Bedrock | $0.15 | $0.6 | $0.26 | 128k |
| Amazon Bedrock | $0.15 | $0.6 | $0.26 | 128k |
| Tinfoil | $0.15 | $0.6 | $0.26 | 131k |
| Berget.AI | $0.22 | $0.83 | $0.37 | 128k |
jishie indexes & prices models; it does not proxy inference. Most providers are OpenAI-compatible — point base_url at OVHcloud AI Endpoints and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"gpt-oss-120b","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):