GPT Luna Latest vs Claude Haiku 4.5
Side-by-side API pricing and Artificial Analysis performance for GPT Luna Latest (~openai) and Claude Haiku 4.5 (Anthropic). Green cells mark the better value in each row.
Prices updated Sep 20, 2026, 12:27 AM UTC · refreshed hourly
| GPT Luna Latest ~openai | Claude Haiku 4.5 Anthropic | |
|---|---|---|
| Pricing | ||
| Input $/1M | $0.20 | $1.00 |
| Output $/1M | $1.20 | $5.00 |
| Blended $/1M (3:1) | $0.45 | $2.00 |
| RAG example (30K in / 2K out) | $0.0084 | $0.04 |
| Quality & speed | ||
| Intelligence Index | — | 17.6 |
| Coding Index | — | 43.9 |
| Agentic Index | — | 10.3 |
| Output speed (tok/s) | — | — |
| Time to first token | — | — |
| Specs | ||
| Context window | 1.05M | 200K |
| Input modalities | file, image, text | text, image, file |
FAQ
Which is cheaper, GPT Luna Latest or Claude Haiku 4.5?
GPT Luna Latest has the lower blended API price at $0.45 per 1M tokens (3:1 input:output mix), versus $2.00 for the other model. Prices are live from OpenRouter and refresh about hourly.
Which is better for RAG workloads?
For a typical RAG request (30K input / 2K output tokens), GPT Luna Latest costs about $0.0084 per request versus $0.04. Also compare context windows: GPT Luna Latest offers 1.05M and Claude Haiku 4.5 offers 200K.
Which scores higher on Artificial Analysis benchmarks?
Claude Haiku 4.5 leads on the Artificial Analysis Intelligence Index (17.6 vs —). Check coding and agentic indices on this page for workload-specific tradeoffs.