Claude Sonnet 5.5
- Input / 1M tokens
- $2.00
- Output / 1M tokens
- $10.00
API models · Side by side
Claude Sonnet 5.5 vs GPT-6 Luna
Claude Sonnet 5.5 is a mid-priced all-rounder. GPT-6 Luna is OpenAI's budget model at a twentieth of the price. Both read text, images and files. The question is whether Luna is good enough for your feature.
GPT-6 Luna
- Input / 1M tokens
- $0.10
- Output / 1M tokens
- $0.50
The short answer
Sonnet charges $2 per million input tokens and $10 per million output tokens. Luna charges $0.10 and $0.50, rising to $0.20 and $0.75 above 272,000 tokens. Both write up to 128,000 tokens per reply. Luna reads slightly more: 1.05 million tokens vs 1 million.
Compare the details
Compare context, supported inputs and usage costs. Highlighted rows show a difference.
| Feature | Claude Sonnet 5.5 | GPT-6 Luna |
|---|---|---|
| Input formats | file, image, text | file, image, text |
| Output formats | text | text |
| Context / position limit | 1,000,000 | 1,050,000 |
| Maximum output tokens | 128,000 | 128,000 |
| Developer features | Reasoning output, Completion limit, Output limit, Reasoning controls, Thinking effort, Response format, Stop sequences, Structured output, Tool selection, Tool calling, Response length | Reasoning output, Completion limit, Output limit, Reasoning controls, Thinking effort, Response format, Seed, Structured output, Tool selection, Tool calling, Response length |
| Cached input / 1M tokens | $0.10 | $0.01 |
| Cache write / 1M tokens | $2.50 | $0.13 |
| USD input / 1M tokens | $2.00 | $0.10 |
| USD output / 1M tokens | $10.00 | $0.50 |
| Model identifier | anthropic/claude-sonnet-5.5 | openai/gpt-6-luna |
API pricing
Prices are in USD per million tokens. Input is what you send; output is what the model generates. Claude and ChatGPT subscriptions are billed separately.
GPT-6 Luna: long-prompt rates
- Long-prompt threshold: 272,000 prompt tokens. Input: $0.20 / 1M. Output: $0.75 / 1M.
Tools, images and additional reasoning can add charges. The examples below cover input and output tokens only.
Compare local modelsWhat those prices mean in practice
Each example uses the same token budget for both models. These are calculations, not measured workloads. Cache discounts, media, tools and extra reasoning are excluded.
| Workload | Claude Sonnet 5.5 | GPT-6 Luna |
|---|---|---|
| 1,000 short requestsPer request: 2,000 input + 500 output tokens | $9.00 | $0.45 |
| 100 document summariesPer request: 20,000 input + 1,000 output tokens | $5.00 | $0.25 |
| 10 long-document requestsPer request: 300,000 input + 2,000 output tokens | $6.20 | $0.61 |
Estimate = requests × (input tokens × input price + output tokens × output price) ÷ 1,000,000. Long-prompt rates are applied where the pricing data provides them. Real requests can use different amounts of output.
Beyond the price tag
Customer replies
For support answers, set clear rules: answer the question, follow your policy, no promises you can't keep. Then compare how much editing each model's replies need. If Luna's are good enough, you save about 95% on every reply.
Summaries that keep the facts
A good summary keeps the dates, decisions and next steps, not just the topic. Both models read files directly. Check a sample of summaries against the original documents before going live.
Long documents
Luna's rates rise above 272,000 tokens but stay far below Sonnet's. Even for long documents, Luna remains the much cheaper option.
Which one should you pick?
Choose GPT-6 Luna for repetitive, high-volume features where its answers pass your checks. Keep Claude Sonnet 5.5 for work where its results need clearly less editing, or where you already have a reliable Claude setup.
Common questions
Is Luna only good for short answers?
No. Both can write up to 128,000 tokens in one reply. The price is lower, not the limit.
Can I judge writing quality from the table?
No. The table shows prices and limits. Read real outputs to judge quality.