Claude Haiku 5.5 vs GPT-6 Luna

As of November 12, 2026, Claude Haiku 5.5 and GPT-6 Luna cost the same: $0.10 per 1M input tokens and $0.50 per 1M output tokens. Claude Haiku 5.5 has the larger context window: 1M tokens versus 922K.

Prices from LiteLLM's price fileChecked November 12, 2026

Claude Haiku 5.5 vs GPT-6 Luna side by side

Headline prices in US dollars per 1M tokens: each model's own lab where it sells it, otherwise its cheapest provider. Source: LiteLLM model price file, as of November 12, 2026.
	Claude Haiku 5.5	GPT-6 Luna
Input, per 1M tokens	$0.10	$0.10
Output, per 1M tokens	$0.50	$0.50
Cache read, per 1M tokens	$0.01	$0.01
Cache write, per 1M tokens	$0.125	$0.125
Context window	1,000,000 tokens	922,000 tokens
Max output	128,000 tokens	128,000 tokens
Image input	Yes	Yes
Tool calling	Yes	Yes
Structured output (JSON)	Yes	Yes
Prompt caching	Yes	Yes
Reasoning	Yes	Yes
Providers on LiteLLM	10	13
Price shown is from	Anthropic	OpenAI
Added to LiteLLM	–	September 22, 2026

Cheapest provider for each

Claude Haiku 5.5: Anthropic at $0.10 input and $0.50 output per 1M tokens (claude-haiku-5-5)
GPT-6 Luna: OpenAI at $0.10 input and $0.50 output per 1M tokens (gpt-6-luna)

Benchmark scores

From the Epoch AI Benchmarking Hub (CC BY 4.0), data as of October 9, 2026. Some results were run by Epoch and others collected by Epoch from each benchmark's own leaderboard, linked in the first column. Each model's best reported reasoning setting is shown in brackets. Higher is better. Only benchmarks with a score for both models are shown.
Benchmark	Claude Haiku 5.5	GPT-6 Luna
Overall
Epoch Capabilities Index	160.4	156.4
Coding and agents
FrontierCode	46.4% (max)	42.4% (max)
APEX-Agents	56.1% (max)	44.3% (max)
Reasoning and knowledge
GPQA Diamond	89.6% (max)	90.5% (max)
ARC-AGI-2	61.3% (xhigh)	59.3% (max)
SimpleQA Verified	23.8% (max)	41.4% (max)
Math
FrontierMath (tiers 1-3)	75.1% (max)	78.9% (max)
FrontierMath (tier 4)	46.3% (max)	56.1% (max)
OTIS Mock AIME 2024-2025	98.9% (xhigh)	98.9% (max)

Call Claude Haiku 5.5 or GPT-6 Luna with LiteLLM

Both use the OpenAI format through LiteLLM, so switching is a model name change. Set each provider's API key in the environment first.

Python SDK

from litellm import completion

messages = [{"role": "user", "content": "Hello!"}]

# Claude Haiku 5.5
response = completion(model="claude-haiku-5-5", messages=messages)

# GPT-6 Luna
response = completion(model="gpt-6-luna", messages=messages)

# Claude Haiku 5.5, falling back to GPT-6 Luna if the call fails
response = completion(model="claude-haiku-5-5", messages=messages, fallbacks=["gpt-6-luna"])

FAQ

Which is cheaper, Claude Haiku 5.5 or GPT-6 Luna?

They cost the same: $0.10 per 1M input tokens and $0.50 per 1M output tokens, as of November 12, 2026.

Which has the larger context window, Claude Haiku 5.5 or GPT-6 Luna?

Claude Haiku 5.5 has the larger context window: 1,000,000 tokens, versus 922,000 for GPT-6 Luna.

Can I switch from Claude Haiku 5.5 to GPT-6 Luna without changing my code?

Yes. Through LiteLLM both use the OpenAI format, so switching means changing the model name from "claude-haiku-5-5" to "gpt-6-luna", or pointing a LiteLLM gateway model alias at the other model. You can also use one as a fallback for the other.