gpt-oss-120b API price comparison
Compare gpt-oss-120b token prices across supported API token platforms.
Cheapest overall
AIHubMix
1.08 USD/M tokens combined per 1M tokens
Lowest input
AIHubMix
0.18 USD/M tokens input per 1M tokens
Lowest output
AIHubMix
0.90 USD/M tokens output per 1M tokens
Last refreshed
Sep 6, 2026
5 listed platforms
Best listed option
gpt-oss-120b is currently cheapest overall on AIHubMix, with input at 0.18 USD/M tokens and output at 0.90 USD/M tokens per million tokens.
Pricing insight
Across 5 listed routes, gpt-oss-120b is cheapest overall on AIHubMix at 1.08 USD/M tokens. The median combined price is 5.50 USD/M tokens, so the cheapest route is about 80% below the median listed route.
-
Lowest total cost
AIHubMix
Best first check for balanced coding-agent sessions: 1.08 USD/M tokens.
-
Prompt-heavy work
AIHubMix
Useful for large repositories and long context reads: 0.18 USD/M tokens input.
-
Response-heavy work
AIHubMix
Useful for long answers, edits, and agent loops: 0.90 USD/M tokens output.
Median combined price
5.50 USD/M tokens
Baseline for judging whether the cheapest route is unusually low.
Cache price coverage
0%
0 of 5 routes publish cache read or write prices.
Fresh rows
3/5
Routes crawled in the last 72 hours.
Use case fit
gpt-oss-120b is suited to general API tasks, coding assistants, and agent workflows across the OpenAI model family. Output price matters most for long-form answers and tool-heavy sessions.
Platform price comparison
| Platform | Ratio | Input | Output | Total |
|---|---|---|---|---|
| AIHubMix | 0.04x | 0.18 USD/M tokens | 0.90 USD/M tokens | 1.08 USD/M tokens |
| Qianduoduo | 0.09x | 0.30 USD/M tokens | 2.50 USD/M tokens | 2.80 USD/M tokens |
| Yunwu | 0.22x | 1.10 USD/M tokens | 4.40 USD/M tokens | 5.50 USD/M tokens |
| DMXAPI | 1.00x | 5.00 USD/M tokens | 20.00 USD/M tokens | 25.00 USD/M tokens |
| ClaudeCN | 1.54x | 7.70 USD/M tokens | 30.80 USD/M tokens | 38.50 USD/M tokens |
FAQ
Where is gpt-oss-120b cheapest?
AIHubMix has the lowest listed combined price at 1.08 USD/M tokens per 1M tokens.
What do input and output prices mean?
Input is charged for prompt tokens you send. Output is charged for tokens generated by the model.
How often are prices refreshed?
Prices are crawler-backed and this page was last refreshed Sep 6, 2026. Always confirm before large purchases.