GPT 5.6 Luna
OpenAI · text, image → text
GPT-5.6 Luna is designed for cost-sensitive, high-volume workloads. It roughly corresponds to the nano model tier used in earlier GPT-5 families.
Input$1 /M
Output$6 /M
Cache read$0.1 /M
← ModelsGPT 5.6 LunaGPT Oss 20B (free)
GPT 5.6 Luna vs GPT Oss 20B (free)
Compare GPT 5.6 Luna from OpenAI and GPT Oss 20B (free) 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 5.6 LunaGPT Oss 20B (free)+ Add model · 2/4
GPT Oss 20B (free)
OpenAI · text → text
Developed by OpenAI, gpt-oss-20b-free is an open-weight 21B parameter model released under the Apache 2.0 license. The model utilizes a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass to ensure efficient processing. Additionally, it supports an expansive context length of 131,072 tokens for handling large-scale inputs.
Input$0 /M
Output$0 /M
Pricing & Specifications
Prices are per million tokens. Time to First Token and throughput are rolling averages measured on AIHubMix.
GPT 5.6 Luna
GPT Oss 20B (free)
Input /M
$1
$0
Output /M
$6
$0
Cache read /M
$0.1
-
Context length
1,050,000
131,072
Max output
128,000
131,072
Time to First Token
2.2 s
-
Throughput
88.4 tok/s
-
Modalities
textimage
text
Supported Parameters
toolsthinkingstructured outputs
reasoningtool callinglong context
API Formats
chat_completions · responses
chat_completions
Released
-
-
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-5.6-lunagpt-oss-20b-free
Tokens / day
-
Requests / day
-
Performance Past 3 Days
Measured on real AIHubMix traffic, hourly buckets. Gaps mean no traffic in that hour.
gpt-5.6-lunagpt-oss-20b-free
Throughput (tok/s)
-
TTFT (s)
-
Uptime (%)
-
Cost calculator
Estimate your monthly bill for the same workload on each model.
GPT Oss 20B (free)
$0.00 /mo
GPT 5.6 Luna
$150 /mo
Monthly = daily × 30. Discounted rates applied where a promotion is active.
FAQ
How large is each context window?
GPT 5.6 Luna accepts 1,050,000 and GPT Oss 20B (free) accepts 131,072 input tokens. Maximum output per request is 128,000 tokens on GPT 5.6 Luna and 131,072 tokens on GPT Oss 20B (free).
What inputs and capabilities does each model support?
GPT 5.6 Luna accepts text and image input and supports tool calling, thinking and structured outputs; GPT Oss 20B (free) accepts text input and supports reasoning, tool calling and long context.
Can I call GPT 5.6 Luna and GPT Oss 20B (free) 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.
