Claude Haiku 5.5 vs GPT-6 Luna
Claude Haiku 5.5 and GPT-6 Luna share a list price, $0.10 input and $0.50 output per 1M tokens, and Haiku scores higher: 39.2% against 16.4% on Terminal-Bench 4.0. The catch is long prompts. The Haiku rate rises to $0.50 and $2.50 past 100K prompt tokens; Luna's rises only to $0.20 and $0.75, and only past 272K.
Short prompts: the same price
Below 100K prompt tokens the two cost the same, cached input included ($0.01 per 1M). Our quick fix costs $0.03 on both and the feature session $0.54, or $0.15 with 90% of prompts cached.
Long prompts: Luna is far cheaper
A coding agent's prompt grows as the conversation does. Our long agent day sends 150K-token prompts, which is over the Haiku threshold and under Luna's, so it costs $24.38 on Haiku 5.5 and $4.88 on Luna, or $6.15 against $1.23 with the cache. Filling the whole window once costs $0.50 on Haiku and $0.21 on Luna.
Scores and dates
Terminal-Bench 4.0: Haiku 39.2%, Luna 16.4%. FrontierCode 1.1: Haiku 46.4%, Luna 42.4%. Both Luna scores are as Anthropic quoted them. Haiku also has 57.4% on Humanity's Last Exam with tools; we have no Luna score there.
GPT-6 Luna was first listed on the API on 22 September 2026, and Anthropic released Haiku 5.5 two weeks later, on 7 October. Luna reads up to 1.05M tokens, Haiku up to 1M, and both write up to 128K.
Side by side
| Claude Haiku 5.5 | GPT-6 Luna | |
|---|---|---|
| Maker | Anthropic | OpenAI |
| Released | 7 October 2026[1] | 22 September 2026[2] first API listing |
| Context window | 1M tokens[1] | 1.05M tokens[3] |
| Max output | 128K tokens[1] | 128K tokens[3] |
| Input price | $0.10 per 1M tokens[1] | $0.10 per 1M tokens[3] |
| Output price | $0.50 per 1M tokens[1] | $0.50 per 1M tokens[3] |
| Cached input | $0.01 per 1M tokens[4] | $0.01 per 1M tokens[3] |
| Long prompts | Over 100K: $0.50 in, $2.50 out[1] Prompts over 100,000 tokens are billed at the higher rate. | Over 272K: $0.20 in, $0.75 out[3] Prompts over 272K input tokens: 2x input and 1.5x output for the whole request. |
| Price change | None announced | None announced |
| Open weights | No[1] Offered through the Claude API and cloud platforms; no weights are published. | No[5] Listed as an API model, not in OpenAI's open-weight section. |
| Reads | text, image[1] | text, image[3] |
Benchmarks
Scores as the makers published them, each with its source and date. Makers run these at different settings, so read a gap of a few points as a tie.
| Benchmark | Claude Haiku 5.5 | GPT-6 Luna |
|---|---|---|
| Terminal-Bench 4.0Agentic coding tasks in a real terminal. | 39.2%[6] | 16.4%[6] Quoted by Anthropic. |
| FrontierCode 1.1 (Main)Hard software engineering tasks. | 46.4%[6] | 42.4%[6] Quoted by Anthropic. |
| Humanity's Last Exam (with tools)Expert-level questions across many fields, tools allowed. | 57.4%[6] | Not published |
What a coding session costs
Our own estimate from the list prices above, for three sessions we define: a coding agent resends the conversation with every call, so prompts are large and grow. "Cached" assumes 90% of prompt tokens are read from the prompt cache and leaves out cache write fees. A long-prompt price applies when a call's prompt is over its threshold. Work out your own mix with the token cost calculator.
| Session | Claude Haiku 5.5 | Claude Haiku 5.5 cached | GPT-6 Luna | GPT-6 Luna cached |
|---|---|---|---|---|
| Quick fix10 calls of 25K prompt and 1.5K output tokens | $0.03 | $0.01 | $0.03 | $0.01 |
| Feature session60 calls of 80K prompt and 2K output tokens | $0.54 | $0.15 | $0.54 | $0.15 |
| Long agent day300 calls of 150K prompt and 2.5K output tokens | $24.38 | $6.15 | $4.88 | $1.23 |
Value for money and release gap
Claude Haiku 5.5 is dated 2 weeks later (15 days; GPT-6 Luna: first API listing). Price per point divides our feature-session cost by a published score: lower means more score for the money. It is a rough lens, not a ranking.
| Measure | Claude Haiku 5.5 | GPT-6 Luna |
|---|---|---|
| Input tokens per $1 | 10M | 10M |
| Filling the whole context window once | $0.50 | $0.21 |
| Feature session per point of Terminal-Bench 4.0 | $0.01 | $0.03 |
| Feature session per point of FrontierCode 1.1 (Main) | $0.01 | $0.01 |
Questions
Do Haiku 5.5 and GPT-6 Luna cost the same?
For short prompts, yes: $0.10 per 1M input tokens and $0.50 per 1M output. Past 100K prompt tokens Haiku 5.5 charges $0.50 and $2.50; Luna keeps its base rate up to 272K and then charges $0.20 and $0.75.
Which is better at coding, Haiku 5.5 or GPT-6 Luna?
Haiku 5.5 on both shared benchmarks: 39.2% against 16.4% on Terminal-Bench 4.0 and 46.4% against 42.4% on FrontierCode 1.1.
Which is cheaper for a long agent session?
GPT-6 Luna. Our long agent day, with 150K-token prompts, costs $4.88 on Luna and $24.38 on Haiku 5.5 at list prices, because the Haiku long-prompt rate applies.
Most compared
Any other two models: pick them in the lists at the top of the page.
- Claude Haiku 5.5 vs Claude Sonnet 5.5
- Claude Haiku 4.5 vs Claude Haiku 5.5
- Claude Haiku 5.5 vs Gemini 3.8 Flash
- Claude Opus 5.5 vs Claude Sonnet 5.5
- Claude Fable 5.1 vs Claude Opus 5.5
- Claude Opus 5 vs Claude Opus 5.5
- Claude Sonnet 5 vs Claude Sonnet 5.5
- Claude Fable 5 vs Claude Fable 5.1
- Claude Opus 5.5 vs GPT-6.1 Sol
- Claude Sonnet 5.5 vs GPT-6.1 Sol
- Claude Opus 5.5 vs GPT-5.6 Sol
- Claude Fable 5.1 vs GPT-6 Astra
- Claude Opus 5.5 vs GPT-6 Astra
- GPT-6.1 Sol vs GPT-6 Sol
- GPT-6.1 Sol vs GPT-6 Astra
- Claude Opus 5.5 vs Gemini 4 Argon
- Claude Sonnet 5.5 vs Gemini 4 Argon
- Claude Opus 5.5 vs Gemini 3.1 Pro Preview
- Gemini 4 Argon vs GPT-6.1 Sol
- Gemini 3.1 Pro Preview vs Gemini 4 Argon
- Claude Opus 5.5 vs Grok 4.7
- Claude Opus 5.5 vs DeepSeek V4 Pro
- Claude Sonnet 5.5 vs Kimi K3
- Claude Sonnet 5.5 vs GLM-5.3
More tools
Sources
Numbers from the makers' own pages, checked by hand, last read . List prices in US dollars before tax. Spotted a mistake? office@shuriken.sh.
Made by Shuriken, the harness for coding agents. Its hot swapping moves your chats to another of your accounts or API keys when one nears its limit. Use only accounts you own and are entitled to use.
Try Shuriken on your own computerYou're signed in
Add your Claude, Codex and Gemini accounts once. Shuriken switches between them so your agents keep working.Your accounts, projects and chats are in the app.
Coming soon