GPT-OSS-20B
OpenAI · → text
Input$0.11 /M
Output$0.55 /M
← ModelsGPT-OSS-20BAuto
GPT-OSS-20B vs Auto
Compare GPT-OSS-20B from OpenAI and Auto from OpenAI on key metrics including benchmarks, price, context length, and other model features. Access both models and hundreds of others through the AIHubMix API.
GPT-OSS-20BAuto+ Add model · 2/4
Auto
OpenAI · text, audio, image, video → text
AIHubMix Smart Router: Fill in the model name as auto, and the gateway will automatically select the optimal model based on the request content; The auto without a suffix uses the default strategy cost_optimized. You can explicitly specify the focus using auto:<strategy>, such as auto (= auto:cost_optimized) cost priority: choose the cheapest as long as the capability meets the standard; auto:balanced balanced: considers capability / cost / latency auto:quality_first quality priority: prioritize selecting the strongest capability for complex reasoning and critical outputs auto:latency_critical low latency priority: prioritize selecting the fastest response
Input$2 /M
Output$2 /M
Pricing & Specifications
Prices are per million tokens. Time to First Token and throughput are rolling averages measured on AIHubMix.
GPT-OSS-20B
Auto
Input /M
$0.11
$2
Output /M
$0.55
$2
Cache read /M
-
-
Context length
0
1,000,000
Max output
0
0
Time to First Token
0.1 s
-
Throughput
2619.0 tok/s
-
Modalities
textaudioimagevideo
Supported Parameters
thinkingwebdeepsearchtoolsfunction callingstructured outputslong context
API Formats
Released
August 5, 2025
January 1, 2024
Promotional prices show the discounted rate; see each model page for promotion windows.
Activity Past 30 Days
Daily traffic served through AIHubMix — how demand for each model is trending.
GPT-OSS-20Bauto
Tokens / day
-
Requests / day
-
Performance Past 3 Days
Measured on real AIHubMix traffic, hourly buckets. Gaps mean no traffic in that hour.
GPT-OSS-20Bauto
Throughput (tok/s)
-
TTFT (s)
-
Uptime (%)
-
Cost calculator
Estimate your monthly bill for the same workload on each model.
GPT-OSS-20B
$14.85 /mo
Auto
$150 /mo
Monthly = daily × 30. Discounted rates applied where a promotion is active.
FAQ
Which is cheaper: GPT-OSS-20B, Auto?
GPT-OSS-20B: $0.55/M output tokens; Auto: $2/M. Use the cost calculator above to estimate your own workload.
Can I call GPT-OSS-20B and Auto with the same API key?
Yes. AIHubMix serves every model on this page behind one OpenAI-compatible endpoint, so switching between them is a one-line change to the model field — no second account, key or SDK.
Popular comparisons
Related model match-ups readers also look at.
