gpt-oss-120b
wandb/openai/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)
$0.03
Input $/1M
$0.17
Output $/1M
$0.20
1M in + 1M out
$0.03
Cache read $/1M
#719 of 8,504
Cheapest rank
- Provider
- CoreWeave (
wandb) - Kind
- text (outputs text)
- Context
- 131,072 tokens
- Max output
- 131,072 tokens
- Capabilities
- tools reasoning text
Same model, other providers
“gpt-oss-120b” is offered by 8 providers — cheapest-effective first. This one (CoreWeave) is the cheapest.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| CoreWeave (this) | $0.03 | $0.17 | $0.07 | 131k |
| OVHcloud AI Endpoints | $0.09 | $0.47 | $0.18 | 131k |
| Amazon Bedrock | $0.15 | $0.6 | $0.26 | 131k |
| Tinfoil | $0.15 | $0.6 | $0.26 | 131k |
| Nebius Token Factory | $0.15 | $0.6 | $0.26 | 131k |
| Privatemode AI | $0.2311 | $0.7511 | $0.36 | 128k |
| Prime Inference | $0.35 | $0.75 | $0.45 | 131k |
| Regolo AI | $1.12 | $4.71 | $2.02 | 128k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at CoreWeave 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):