GPT OSS 120B
crusoe/openai/gpt-oss-120b · family gpt-oss · in: text → out: text · price provider-declared (via models.dev). Capabilities: toolsreasoningtext.
$0.09Blended $/1M (3:1)
$0.05Input $/1M
$0.2Output $/1M
$0.251M in + 1M out
$0.05Cache read $/1M
#674 of 5,860Cheapest rank
- Provider
- Crusoe (
crusoe) - Kind
- text (outputs text)
- Context
- 131,072 tokens
- Max output
- 32,768 tokens
- Capabilities
- toolsreasoningtext
Same model, other providers
“GPT OSS 120B” is offered by 39 providers — cheapest-effective first. QVAC is the cheapest at $0.00 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| QVAC | free | free | $0.00 | 131k |
| Kenari | free | free | $0.00 | 131k |
| LLM Gateway | $0.032 | $0.14 | $0.06 | 131k |
| OpenRouter | $0.03 | $0.17 | $0.07 | 131k |
| Kilo Gateway | $0.03 | $0.17 | $0.07 | 131k |
| Deep Infra | $0.037 | $0.17 | $0.07 | 131k |
| Eden AI | $0.037 | $0.17 | $0.07 | 131k |
| TensorX | $0.04 | $0.2 | $0.08 | 131k |
| Crusoe (this) | $0.05 | $0.2 | $0.09 | 131k |
| Synthetic | $0.1 | $0.1 | $0.10 | 131k |
| DInference | $0.0675 | $0.27 | $0.12 | 131k |
| Databricks | $0.072 | $0.28 | $0.12 | 131k |
| Neon | $0.072 | $0.28 | $0.12 | 131k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Crusoe and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"openai/gpt-oss-120b","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):