Live survey286 models · 13 providers · 17,592 auditsAudited Using Git Worktrees · SAFE →What changedHow we verifyllms.txt

Model comparison · Updated 10 Oct 2026

Claude Haiku 5.5 vs GPT-6 Luna

Claude Haiku 5.5 and GPT-6 Luna cost the same on input, $0.10 per 1M tokens. GPT-6 Luna has the larger context window (1.05M against 1M tokens). For a support chatbot at 10,000 chats a day, the standard-tier bill is about $90.00 a month for Claude Haiku 5.5 and $90.00 for GPT-6 Luna.

Ask an AI about this pageGChatGPTCClaudePPerplexityGeGeminiXGrok
More
CoCopilotAIGoogle AI Mode
Cite

Cite this page

ModelsAtlas. “Claude Haiku 5.5 vs GPT-6 Luna”. Retrieved 10 Oct 2026. https://modelsatlas.com/compare/anthropic/claude-haiku-5-5/vs/openai/gpt-6-luna

Model A

Claude Haiku 5.5

by Anthropic · weights not marked open · GRIDC5

Input / 1M
$0.10
observed We measured
Source
Our catalogue
Retrieved
10 Oct 2026
Output / 1M$0.50
Context1M
vs

Model B

GPT-6 Luna

by OpenAI · weights not marked open · GRIDC6

Input / 1M
$0.10
observed We measured
Source
Our catalogue
Retrieved
10 Oct 2026
Output / 1M$0.50
Context1.05M

Key numbers

Standard tier · highlighted = better

Claude Haiku 5.5
GPT-6 Luna
Input / 1M tokens
$0.10
$0.10
Output / 1M tokens
$0.50
$0.50
Batch input / output
$0.05 / $0.25
$0.05 / $0.25
Context window
1,000,000
1,050,000
Input types
Not disclosed
Not disclosed
Weights
Not marked open
Not marked open
Tiers listed
batch, standard
batch, standard
Prices checked
2026-10-10
2026-10-10

What it costs for real workloads

Monthly, standard tier, 30 days

Support chatbot10k chats/day · 1.5k in, 300 out
$90.00/mo
$90.00/mo
RAG over documents2k queries/day · 12k in, 500 out
$87.00/mo
$87.00/mo
Coding agent300 tasks/day · 60k in, 8k out
$90.00/mo
$90.00/mo

Claude Haiku 5.5   GPT-6 Luna · Derived from the standard-tier prices above, input and output tokens per request as stated, 30 days. Excludes caching discounts and batch. Try your own numbers.

On the atlas

Price band (A–H) × context band (1–6)

1 square apart. GPT-6 Luna (C6) sits 1 context band larger than Claude Haiku 5.5 (C5).

Same square as Claude Haiku 5.5: Muse Spark 1.2 Contributor ($0.10), Muse Spark 1.3 Contributor ($0.10), Qwen3.8 Flash ($0.15). Same square as GPT-6 Luna: Llama 4 Scout ($0.10), GPT-5.6 Luna ($0.20). Open C5 · Open C6

AFreeB<$0.10C$0.10–0.30D$0.30–1E$1–3F$3–10G$10–30H$30+1<32K232–128K3128–256K4256K–1M51M6>1MINPUT PRICE PER 1M TOKENS →CONTEXT WINDOW ↑ · position within a square follows the real valueMuse Spark 1.2 Contributor · C5Muse Spark 1.3 Contributor · C5Qwen3.8 Flash · C5Qwen3.8 Omni Flash · C5Llama 4 Maverick · C5Qwen3.6 Flash · C5Llama 4 Scout · C6GPT-5.6 Luna · C6Claude Haiku 5.5Claude Haiku 5.5GPT-6 LunaGPT-6 Luna
Claude Haiku 5.5GPT-6 LunaNearest neighboursOpen weights
View the map as a table (2 squares)
SquarePrice bandContext bandModels
GRIDC5$0.10–0.301MClaude Haiku 5.5, Muse Spark 1.2 Contributor, Muse Spark 1.3 Contributor, Qwen3.8 Flash, Qwen3.8 Omni Flash, Llama 4 Maverick, Qwen3.6 Flash
GRIDC6$0.10–0.30>1MGPT-6 Luna, Llama 4 Scout, GPT-5.6 Luna

Capabilities side by side

Only what our records list

Claude Haiku 5.5
GPT-6 Luna
Vision input
Not disclosed
Not disclosed
Audio input
Not disclosed
Not disclosed
Open weights
Not marked open
Not marked open
Batch tier
Supported
Supported
Free tier
Not listed
Not listed
Thinking tier
Not listed
Not listed

Neither record lists input types, so we do not claim any.

Which should you choose?

Editorial

Choose Claude Haiku 5.5 if…

Nothing in the recorded numbers favours Claude Haiku 5.5 over GPT-6 Luna. Pick it for what our records do not cover — your own tests, or an account you already have with Anthropic.

Choose GPT-6 Luna if…

  • your prompts are long: it takes 1,050,000 tokens against 1,000,000

Each reason is a fact from the tables above. Picking between them is our judgement, and we do not benchmark quality: price and context are what we can measure, so test both on your own prompts before you commit.

Questions

Is Claude Haiku 5.5 better than GPT-6 Luna?
We do not benchmark quality, so we cannot say. On the recorded numbers: Claude Haiku 5.5 and GPT-6 Luna cost the same on input, $0.10 per 1M tokens. GPT-6 Luna has the larger context window (1.05M against 1M tokens). For a support chatbot at 10,000 chats a day, the standard-tier bill is about $90.00 a month for Claude Haiku 5.5 and $90.00 for GPT-6 Luna. Which is better for you depends on your task; test both on your own prompts.
Which is cheaper, Claude Haiku 5.5 or GPT-6 Luna?
They cost the same on input, $0.10 per 1M tokens. Output is $0.50 for Claude Haiku 5.5 and $0.50 for GPT-6 Luna.
How much does each cost per 1M tokens?
Claude Haiku 5.5: $0.10 input and $0.50 output. GPT-6 Luna: $0.10 input and $0.50 output. Standard tier, USD.
Which has the larger context window?
GPT-6 Luna, with 1,050,000 tokens. Claude Haiku 5.5 has 1,000,000 tokens.
Do both offer batch pricing?
Claude Haiku 5.5 lists a batch tier, at 50% of its standard price. GPT-6 Luna lists a batch tier, at 50% of its standard price.
Can both read images or audio?
Input types recorded for Claude Haiku 5.5: none recorded. For GPT-6 Luna: none recorded. Where a record lists none we say so rather than guess; check each vendor's documentation before relying on a capability.
Is either model open-weight?
Claude Haiku 5.5: not marked open-weight in our records. GPT-6 Luna: not marked open-weight in our records.
What would each cost for a support chatbot?
At 10,000 chats a day, 1,500 input and 300 output tokens each, 30 days, standard tier: about $90.00 a month for Claude Haiku 5.5 and $90.00 for GPT-6 Luna. This is our calculation from the listed prices, not a quote.

About the two models

Claude Haiku 5.5

By Anthropic. $0.10 input and $0.50 output per 1M tokens, 1M context, atlas square C5. Tiers listed: batch, standard.

Full specs & pricing →

GPT-6 Luna

By OpenAI. $0.10 input and $0.50 output per 1M tokens, 1.05M context, atlas square C6. Tiers listed: batch, standard.

Full specs & pricing →

Keep going in your AI

Opens with this page as the source. We add nothing else to the prompt.