Gemini 3.8 Flash vs GPT-6 Luna: media inputs & promotional rates
The input you need to send can narrow this pair before any benchmark does. Gemini 3.8 Flash documents more input modalities, while the reviewed text prices also have different validity conditions.
Start with the input modality
The reviewed Gemini entry accepts text, image, audio, video and PDF input; Luna documents text and image input. Both entries produce text. Those capabilities do not make every modality billable at the text rate. This calculator estimates text tokens only and excludes media-specific fees.
Treat the promotion as time-bounded
Gemini 3.8 Flash's reviewed standard text rates are $0.75 input and $3.75 output per million tokens through December 31, 2026. Luna's base rates are $0.10 and $0.50, with long-input conditions. The calculator refuses the expired promotional snapshot until a new price is reviewed.
Compare limits without renaming them
Gemini publishes a 1,048,576-token input limit and 65,536 output limit; the catalogue does not relabel that input limit as a combined context window. Luna publishes combined context plus a separate input ceiling. Use the original definitions when checking whether a request fits.
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.
Paid-tier Standard text pricing. Excludes cache storage/creation, tools, audio/video/image tokens, taxes and other processing tiers. Output includes thinking tokens.
Promotional rates end December 31, 2026. Re-verification required before using subsequent rates.
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.
3 estimated credits / comparison3,000 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.