gpt-6-luna
gpt-6-lunaSamples: 16
OpenAI GPT-6 Luna: fast, cost-efficient tier for high-volume and latency-sensitive work, 1.05M context with tiered long-context pricing above 272K tokens.
- Input / 1M tokens
- $0.1–$0.2
- Output / 1M tokens
- $0.5–$0.75
- Context window
- 1,050,000
- Route
- Default
DefaultVariable pricing
Roleplay combines public evaluations of emotional understanding, creative writing and story-related skills. It is a comparative reference, not a direct roleplay test.
Each benchmark is rescaled to 1–10 within its own leaderboard. We average results from the same publisher first, then give each publisher equal weight. Only verified model matches are included.
LiveBench · Story constraint following
gpt-6-luna-max: 63.28
71 Models · 2026-10-25
LiveBench · Theory of mind
gpt-6-luna-max: 73.08
71 Models · 2026-10-25
Routes
Ability score divided by token cost, ranked across measured model routes. Cost uses equal input and output token counts; higher is better value.
| Use this model | ||||||
|---|---|---|---|---|---|---|
| Default | $0.1–$0.2 | $0.5–$0.75 | $0.01–$0.02 | 5.1/10 | Not measured | Use this model |
| devin | $0.05–$0.1 | $0.25–$0.375 | $0.005–$0.01 | 5.1/10 | Not measured | Plans and tiers |
| openai_enterprise | $0.01–$0.02 | $0.05–$0.075 | $0.001–$0.002 | 5.1/10 | Not measured | Plans and tiers |
| openai_pro | $0.01–$0.02 | $0.05–$0.075 | $0.001–$0.002 | 5.1/10 | Not measured | Plans and tiers |
devinQuick start
Access and billingcurl --fail-with-body 'https://api.tokenreply.com/v1/chat/completions' \
-H "Authorization: Bearer $TOKENREPLY_API_KEY" \
-H 'Content-Type: application/json' \
--data '{
"model": "gpt-6-luna",
"messages": [
{
"role": "user",
"content": "Reply with hello."
}
]
}'