Comparison · Anthropic and OpenAI
Claude Haiku 5.5 vs GPT-6 Luna
Listed API prices of Claude Haiku 5.5 and GPT-6 Luna turned into the cost of the same three standard tasks, with speed from our own test requests in the United States and what each provider’s API documentation says about features that break on a switch. Output quality and answer length are not compared.
Calculated impact cost per task and per month
For an L2 task (deep analysis over a 50,000-token document, 3 steps), Claude Haiku 5.5 and GPT-6 Luna both cost $0.017 at the prices listed in the United States on , the same amount, counting visible output only, without cache discounts or hidden reasoning.
| Task | Claude Haiku 5.5, per task | GPT-6 Luna, per task | Claude Haiku 5.5, per month | GPT-6 Luna, per month | Claude Haiku 5.5 vs GPT-6 Luna, per task |
|---|---|---|---|---|---|
| L1Micro-task (classification or strict JSON extraction) | $0.0003per L1 task | $0.0003per L1 task | $3.65per month | $3.65per month | same |
| L2Deep analysis over a 50,000-token document | $0.017per L2 task | $0.017per L2 task | $254.04per month | $254.04per month | same |
| L3Agentic coding loop, 15 steps | $0.424per L3 task | $0.136per L3 task | $6,189.38per month | $1,986.33per month | +211.6 % |
Calculated Per month: 20 tasks an hour around the clock, 730 hours.
Prices USD per 1M tokens
| Price | Claude Haiku 5.5 | GPT-6 Luna |
|---|---|---|
| Input, per 1M tokens | $0.100 | $0.100 |
| Output, per 1M tokens | $0.500 | $0.500 |
| Price from | Provider's price list · source page Published | Provider's price list · source page Published |
| Read | · the United States | · the United States |
| Context window | 1,000,000 tokens | 1,050,000 tokens |
What can I use it for? six common tasks, our data checks
Quality on your task: not measured by Measured Lab yet.
| Task | Claude Haiku 5.5 | GPT-6 Luna |
|---|---|---|
| Answer customer messages | Fits on price and context | Fits on price and context |
| Pull data from invoices and documents with strict JSON and page images | Fits on price and context | Fits on price and context |
| Summarize documents and meetings | Fits on price and context | Fits on price and context |
| Translate content | Fits on price and context | Fits on price and context |
| Chat assistant on your website | Fits on price and context | Fits on price and context |
| Write and review code with tool calls | Fits on price and context | Fits on price and context |
| Tasks it fits | 6 of 6 | 6 of 6 |
Checks of our data for six common tasks: a published price, a context window and answer length for the task and, where the task needs them, strict JSON output, page images and tool calls; prices, cost a month and terms for each model on its model card. Compare models for your own task in the model picker.
Speed in the US Observed our test requests
In our test requests from the United States, the median time to the first answer token was 528 ms for Claude Haiku 5.5 (Direct API · Anthropic) and 2,938 ms for GPT-6 Luna (Direct API · OpenAI).
| Model and route | Time to first answer token, median | Output speed, median | Answers |
|---|---|---|---|
| Claude Haiku 5.5Direct API · Anthropic | 528 ms range 290 ms–7,547 ms | 221 tokens/s range 87.6 tokens/s–430 tokens/s | 115 answers on 23 dates |
| GPT-6 LunaDirect API · OpenAI | 2,938 ms range 1,981 ms–7,571 ms | 159 tokens/s range 95.1 tokens/s–239 tokens/s | 70 answers on 14 dates |
The same short request to every model, sent from a measurement point in the United States; medians of successful answers on at least 2 different dates, latest on . How we measure
What breaks when you switch Published provider documentation
Moving from Anthropic to OpenAI: every feature that Anthropic’s documentation lists as supported is also listed as supported by OpenAI.
Moving from OpenAI to Anthropic: every feature that OpenAI’s documentation lists as supported is also listed as supported by Anthropic.
| Feature of the API | Anthropic | OpenAI |
|---|---|---|
| Strict JSON schemas | Yes | Yes |
| Parallel tool calls | Yes | Yes |
| Streamed tool arguments | Yes | Yes |
| Reasoning with tools | Yes | Yes |
| Cache covers tool definitions | Yes | Yes |
What each provider’s own API documentation says, read ; “not stated” is not the same as “no”. Quotes and sources: what breaks when you switch AI APIs.