GPT OSS 120B
phase/gpt-oss-120b · family gpt-oss · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text.
$0.07
Blended $/1M (3:1)
$0.0385
Input $/1M
$0.1768
Output $/1M
$0.22
1M in + 1M out
—
Cache read $/1M
#826 of 9,563
Cheapest rank
- Provider
- Phase Router (
phase) - Kind
- text (outputs text)
- Context
- 131,072 tokens
- Max output
- 4,096 tokens
- Capabilities
- tools reasoning text
Same model, other providers
“GPT OSS 120B” is offered by 59 providers — cheapest-effective first. QVAC is the cheapest at $0.00 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| QVAC | free | free | $0.00 | 131k |
| Pendra | free | free | $0.00 | 131k |
| UberLLM | $0.0084 | $0.036 | $0.02 | 128k |
| NanoGPT | $0.03 | $0.15 | $0.06 | 128k |
| Kilo Gateway | $0.03 | $0.15 | $0.06 | 131k |
| OrcaRouter | $0.03 | $0.17 | $0.07 | 131k |
| Deep Infra | $0.037 | $0.17 | $0.07 | 131k |
| Abacus | $0.037 | $0.17 | $0.07 | 128k |
| Phase Router (this) | $0.0385 | $0.1768 | $0.07 | 131k |
| Runcrate | $0.0389 | $0.1785 | $0.07 | 131k |
| Kenari | $0.036 | $0.2 | $0.08 | 131k |
| Synthetic | $0.1 | $0.1 | $0.10 | 131k |
| Novita AI | $0.05 | $0.25 | $0.10 | 131k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Phase Router 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):