openai / text-generation API-only released 2026-09-22

GPT-6 Luna

GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive workloads such as chat, classification, and lightweight agentic...

Input / 1M
$0.10
Output / 1M
$0.50
Context
1.0M
AA Intelligence
38.1
Closed weights — available only as a hosted API file + image + text → text View on OpenRouter ↗

Pricing

via OpenRouter · USD per 1M tokens · synced 2026-10-24
$0.10
input / 1M
$0.50
output / 1M
$0.01
cached input / 1M
$0.60
1M in + 1M out
:batch variant $0.05 in · $0.25 out
Price tiers
  • Above 272K prompt tokens: input $0.20/M, output $0.75/M (2× base)
Context window
1,050,000 tokens
Max output
128,000 tokens
Providers
3
Cheapest provider
OpenAI · $0.05 / $0.25
Best throughput
—
AA Intelligence / Coding / Agentic
38.1 / — / —
✓ Tool calling ✓ Reasoning ✓ Structured outputs ✓ Image input ✓ File input ✗ Audio input ✓ Prompt caching

Price history

tracking started — chart appears after 7 days of snapshots (6 recorded)
Current: $0.10 input · $0.50 output per 1M tokens

Benchmarks

Third-party indices as published through OpenRouter — Artificial Analysis and Design Arena. Not measured by us.

AA Intelligence Index
38.1
AA Coding Index
—
AA Agentic Index
—

Providers

3 providers · per 1M tokens · last 30 min metrics
ProviderQuantContextInputOutputUptimeTok/s
OpenAI unknown 1.0M $0.05 $0.25 100% —
Azure unknown 1.0M $0.10 $0.50 100% —
OpenAI unknown 1.0M $0.10 $0.50 100% —
Amazon Bedrock unknown 1.0M $0.11 $0.55 100% —
Azure unknown 1.0M $0.11 $0.55 100% —
Azure unknown 1.0M $0.11 $0.55 100% —
OpenAI unknown 1.0M $0.20 $1.00 100% —
Provider data from OpenRouter's endpoint listing, refreshed daily.

Specifications

Organisation
openai
Released on OpenRouter
2026-09-22
Context window
1,050,000 tokens
Max output
128,000 tokens
Input
file, image, text
Output
text
Tokenizer
GPT
Moderated by provider
Yes
OpenRouter id
openai/gpt-6-luna
Compare with
Prices, context and providers from the public OpenRouter API, snapshotted daily; benchmark indices from Artificial Analysis. See /methodology.