GPT-5.6 Luna (Non-reasoning) API Provider Benchmarking & Analysis

GPT-5.6 Luna (Non-reasoning) is available through 2 API providers: OpenAI and Amazon. Each provider offers different performance characteristics and pricing.

GPT-5.6 Luna (Non-reasoning) is currently available through 2 API providers that we benchmark and track.

The fastest providers for GPT-5.6 Luna (Non-reasoning) by output speed are Amazon (210.8 t/s) and OpenAI (118.8 t/s). Output speed measures how quickly tokens are generated after the model starts responding.

The providers with the lowest time to first token for GPT-5.6 Luna (Non-reasoning) are OpenAI (0.70s) and Amazon (0.72s). Lower latency means faster initial response time.

The most affordable providers for GPT-5.6 Luna (Non-reasoning) by blended price are OpenAI ($0.17 per 1M tokens) and Amazon ($0.96 per 1M tokens). Blended price uses a 7:2:1 cache hit/input/output token ratio.

The providers with the lowest input token pricing for GPT-5.6 Luna (Non-reasoning) are OpenAI ($0.20 per 1M input tokens) and Amazon ($1.10 per 1M input tokens).

The providers with the lowest output token pricing for GPT-5.6 Luna (Non-reasoning) are OpenAI ($1.20 per 1M output tokens) and Amazon ($6.60 per 1M output tokens).

Prices for GPT-5.6 Luna (Non-reasoning) vary up to 5.5x across providers. The most affordable is OpenAI at $0.17 per 1M tokens, while Amazon charges $0.96 per 1M tokens.

Output speed for GPT-5.6 Luna (Non-reasoning) varies significantly across providers. Amazon is the fastest at 210.8 t/s, which is 1.8x faster than OpenAI at 118.8 t/s.

All 2 providers of GPT-5.6 Luna (Non-reasoning) support JSON mode for structured output.

All 2 providers of GPT-5.6 Luna (Non-reasoning) support function calling (tool use).

The best provider for GPT-5.6 Luna (Non-reasoning) depends on your priorities: Amazon offers the highest output speed, OpenAI has the lowest latency, and OpenAI provides the most competitive pricing.

When choosing a provider for GPT-5.6 Luna (Non-reasoning), consider: output speed (for throughput-intensive tasks), latency (for interactive applications requiring quick first responses), pricing (for cost-sensitive workloads), and API features like JSON mode or function calling.

Yes, provider performance can vary over time due to infrastructure changes, load balancing, and updates. We continuously benchmark all providers and display historical performance trends in the "Over Time" charts.

For information about GPT-5.6 Luna (Non-reasoning)'s intelligence, capabilities, modalities, and how it compares to other models, see the model overview page. View model overview