OpenAI GPT OSS 120B
cloudferro-sherlock/openai/gpt-oss-120b · family gpt-oss · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text.
$2.92
Blended $/1M (3:1)
$2.92
Input $/1M
$2.92
Output $/1M
$5.84
1M in + 1M out
—
Cache read $/1M
#5630 of 7,712
Cheapest rank
- Provider
- CloudFerro Sherlock (
cloudferro-sherlock) - Kind
- text (outputs text)
- Context
- 131,000 tokens
- Max output
- 131,000 tokens
- Capabilities
- tools reasoning text
Same model, other providers
“OpenAI GPT OSS 120B” is offered by 3 providers — cheapest-effective first. NovitaAI is the cheapest at $0.10 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| NovitaAI | $0.05 | $0.25 | $0.10 | 131k |
| Venice AI | $0.07 | $0.3 | $0.13 | 128k |
| CloudFerro Sherlock (this) | $2.92 | $2.92 | $2.92 | 131k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at CloudFerro Sherlock 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):