As of August 20, 2026, GPT-5.6 Luna is 89% cheaper per million tokens than GPT-4o. GPT-4o is $2.50 / $10.00 per million input/output tokens versus GPT-5.6 Luna at $0.20 / $1.20. Source: https://developers.openai.com/api/docs/pricing
Source: OpenAI API pricing (https://developers.openai.com/api/docs/pricing)
GPT-4o
OpenAI
Input
$2.50
Output
$10.00
GPT-5.6 Luna
OpenAI
Input
$0.20
Output
$1.20
Token pricing, specs, and benchmarks side by side
GPT-4oGPT-5.6 LunaVerdict
GPT-5.6 Luna offers both lower pricing and stronger benchmark performance across the board, making it the clear value leader in this comparison.
As of August 20, 2026, GPT-5.6 Luna is 89% cheaper on blended LLM API pricing. GPT-5.6 Luna costs $0.20 per million input tokens and $1.20 per million output tokens ($1.40 blended 1M-in + 1M-out). GPT-4o costs $2.50 / $10.00 per million tokens ($12.50 blended). Sources: https://developers.openai.com/api/docs/pricing and https://developers.openai.com/api/docs/pricing. The cheapest LLM for your app still depends on how many output tokens you generate.
GPT-4o OpenAI API pricing is $2.50 input and $10.00 output per million tokens via OpenAI. GPT-5.6 Luna OpenAI API pricing is $0.20 input and $1.20 output per million tokens via OpenAI. Use those four numbers, not ChatGPT Plus or Claude Pro subscription prices, when you are comparing APIs.
GPT-5.6 Luna leads on SWE-bench Verified: GPT-4o at 33.2% vs GPT-5.6 Luna at 93%. SWE-bench measures real GitHub fixes; LiveCodeBench measures contest programming.
GPT-4o supports a 128K token context window, while GPT-5.6 Luna supports 1M tokens. GPT-5.6 Luna offers a larger context window. Filling a larger window bills more input tokens, so the cheaper-per-million model can still cost more on long documents.
GPT-5.6 Luna leads on 13 of 13 shared benchmarks versus GPT-4o's 0 wins. Check the comparison table for GPQA Diamond, SWE-bench, MMLU, HLE, and the other evals we track. Token price and benchmark score together are the usual LLM comparison, not either number alone.
Both GPT-4o and GPT-5.6 Luna are production API models. For cost-sensitive production traffic, GPT-5.6 Luna has better economics on the blended 1M-in + 1M-out scale. For maximum capability, weight the benchmark table for your domain. Many production stacks route cheap models for drafts and a frontier model for the hard turn, which is usually cheaper than sending everything to the expensive API.
Yes. Call GPT-4o through OpenAI and GPT-5.6 Luna through OpenAI with separate API keys, or through a gateway that already wraps both. Keep prompts in tokens, not characters, when you estimate the invoice. AnotherWrapper templates can swap providers without rewriting auth and billing.
List rates are the latest published OpenAI API pricing and OpenAI API pricing, quoted per million tokens. Official rate sheets: https://developers.openai.com/api/docs/pricing and https://developers.openai.com/api/docs/pricing. Prompt caching, batch APIs, and committed-use discounts can change the invoice. Benchmark scores are from official publications and independent evals, updated as new numbers land.
GPT-4o supports up to 16K output tokens per request, while GPT-5.6 Luna supports up to 128K output tokens. Output tokens are usually the expensive half of API pricing, so a higher max output cap is a capability, not a discount.
GPT-4o runs at approximately 99 tokens/second while GPT-5.6 Luna runs at 48.45216448188169 tokens/second. GPT-4o is faster in raw throughput. Throughput (tokens per second) and time-to-first-token are why two models with the same per-million-token price can still feel different in chat and agents.
Use the model pickers at the top of this LLM comparison. Search any model in the index and the URL updates. Open GPT-4o or GPT-5.6 Luna from the sidebar for the single-model API pricing page, or go back to the LLM pricing table to sort by cheapest blended cost.
This comparison covers API pricing, context window, throughput, and benchmark scores. GPT-4o costs $2.50/M input and $10.00/M output. GPT-5.6 Luna costs $0.20/M input and $1.20/M output.
Rank both on the LLM leaderboard, SWE-bench, and Humanity's Last Exam.
The index
280 models across 33 providers. Search or jump to a lab — every model page stays linked here.
Next step
Auth, billing, and the API layer are already decided. Fork 8 finished AI apps, or have us build the first version with you.
