Output tokens cost $30.00 per million on gpt-5.5 and $1.20 per million on gpt-5.6-luna. Input tokens cost $5.00 per million on gpt-5.5 and $0.20 per million on gpt-5.6-luna. Cached input tokens are billed at $0.50 per million on gpt-5.5 and $0.02 per million on gpt-5.6-luna. Context windows are 1,050,000 tokens on gpt-5.5 and 1,050,000 tokens on gpt-5.6-luna. First-token latency measured on AIHubMix is 5.4s on gpt-5.5 and 3.1s on gpt-5.6-luna. Measured output throughput is 49.1 tokens/s on gpt-5.5 and 93.6 tokens/s on gpt-5.6-luna.
gpt-5.5gpt-5.6-lunaGPT-5.5 raises the baseline for complex production workflows. It’s a strong fit for coding use cases, tool-heavy agents, grounded assistants, long-context retrieval, product-spec-to-plan workflows, and customer-facing workflows where execution quality and response polish are critical.
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.
Prices are per million tokens. Latency and throughput are rolling averages measured on AIHubMix.
Promotional prices show the discounted rate; see each model page for promotion windows.
Daily traffic served through AIHubMix — how demand for each model is trending.
Measured on real AIHubMix traffic, hourly buckets. Gaps mean no traffic in that hour.
Estimate your monthly bill for the same workload on each model.
Monthly = daily × 30. Discounted rates applied where a promotion is active.
gpt-5.6-luna: $1.20/M output tokens; gpt-5.5: $30.00/M. Use the cost calculator above to estimate your own workload.
gpt-5.6-luna: 3.1s first-token latency measured on AIHubMix; see the live performance charts above for how each model behaves across the day.
gpt-5.5 accepts 1,050,000 and gpt-5.6-luna accepts 1,050,000 input tokens. Maximum output per request is 128,000 tokens on gpt-5.5 and 128,000 tokens on gpt-5.6-luna.
gpt-5.6-luna at 93.6 tokens/s and gpt-5.5 at 49.1 tokens/s, measured as output throughput on AIHubMix — a separate metric from first-token latency.
gpt-5.5 accepts text and image input and supports thinking, function calling, structured outputs, web search and tool calling; gpt-5.6-luna accepts text and image input and supports tool calling, thinking and structured outputs.
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.
Related model match-ups readers also look at.
AIHubMix