Claude Haiku 5.5 vs GPT-6 Luna: prices & input tiers
A low base token rate is only the beginning of this comparison. Haiku 5.5 and GPT-6 Luna share the same standard base text rates, but the size of the input changes the bill at different thresholds.
The base-rate tie has a boundary
Both list $0.10 input and $0.50 output per million text tokens. Haiku's full-request higher tier begins above 100,000 input tokens; Luna's begins above 272,000. Use the calculator with your actual input, cached input and billable output rather than treating the base-rate tie as a fixed total cost.
An API choice as well as a budget choice
The documented API IDs are claude-haiku-5-5 and gpt-6-luna. Haiku uses Anthropic Messages; Luna uses OpenAI Responses. Provider-specific request formats and tokenizers need separate integration work. A shared prompt does not imply identical token counts.
What this comparison cannot establish
The documented shared context windows are 1,000,000 and 1,050,000 tokens respectively. Those limits describe capacity, not answer quality. No comparable licensed benchmark or measured throughput is available here; validate extraction or routing quality on your own representative examples before choosing.
Documented specifications and standard direct API rates, manually checked 2026-10-09. Evaluation suggestions are editorial guidance; no measured comparative quality or speed is claimed.
Unknown fields are not evidence of equal capabilities. Specifications describe support, not comparative answer quality.
BENCHMARK EVIDENCE
No reliable data available
Comparable results with confirmed reuse permission have not been published here yet.
A published result must include the exact model version, benchmark version, original value and unit, test date, conditions and source. No scores or overall rankings are inferred.
Text tokens only. Billable output includes reasoning tokens where applicable. Excludes cache creation, tools, media and regional or processing-tier uplifts.
Default 30-minute cache writes use 1.25× uncached input pricing as a replacement rate. V1 live trials request explicit-only caching with no breakpoints.
KNOW YOUR API COST
A small prompt. A clearer budget.
Same token counts for both models. Standard paid text rates in USD. Output must include all billable reasoning tokens.
Cached input is included in total input. No cache creation/storage, tools, media, taxes or regional/priority/Batch fees. Tokenizers differ; equal token counts do not imply equal text length.
1 estimated credits / comparison1,000 credits across 1,000 comparisons.Reference estimate only. Playground uses verified OpenRouter charges; 1,000 credits = $1. A + B round up together once for each comparison.
See how your prompt behaves.
Choose an enabled official model pair in the Playground. Your maximum reservation is shown before running; confirmed usage determines the final charge.