# 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.

- Page: https://models.litellm.ai/compare/claude-haiku-5-5-vs-gpt-6-luna
- Claude Haiku 5.5: https://models.litellm.ai/models/claude-haiku-5-5
- GPT-6 Luna: https://models.litellm.ai/models/gpt-6-luna

## Side by side

| | 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 |

Headline prices in USD per 1M tokens, from LiteLLM's model price file.

## Cheapest provider for each

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

## Benchmark scores

| Benchmark | Claude Haiku 5.5 | GPT-6 Luna |
|---|---|---|
| Epoch Capabilities Index (Overall) | 160.4 | 156.4 |
| FrontierCode (Coding and agents) | 46.4% (max) | 42.4% (max) |
| APEX-Agents (Coding and agents) | 56.1% (max) | 44.3% (max) |
| GPQA Diamond (Reasoning and knowledge) | 89.6% (max) | 90.5% (max) |
| ARC-AGI-2 (Reasoning and knowledge) | 61.3% (xhigh) | 59.3% (max) |
| SimpleQA Verified (Reasoning and knowledge) | 23.8% (max) | 41.4% (max) |
| FrontierMath (tiers 1-3) (Math) | 75.1% (max) | 78.9% (max) |
| FrontierMath (tier 4) (Math) | 46.3% (max) | 56.1% (max) |
| OTIS Mock AIME 2024-2025 (Math) | 98.9% (xhigh) | 98.9% (max) |

From the Epoch AI Benchmarking Hub (https://epoch.ai/benchmarks), CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/), data as of October 9, 2026: Epoch's own runs and results it collects from each benchmark's leaderboard. Higher is better.

## 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.