GPT-6 Luna

images

Model id

openai/gpt-6-luna

Provider list price

Pricing

USD / 1M tokens

Input$0.1 / M tokens
Output$0.5 / M tokens
Cache read$0.01 / M tokens
Cache write$0.125 / M tokens
Past 272K prompt tokens$0.2 in / $0.75 out per M$0.02 cache read$0.25 cache write
RoutingFree

Provider list price. BYOK bills your provider; managed credits draw down at these rates. No markup or request fee. Every request is metered per engineer and joined to shipped work.

Registry 2026-09-27.4 · effective 9/17/2026 · OpenAI API pricing

Input
$0.1
per M · $0.2 past 272K context
Output
$0.5
per M · $0.75 past 272K context
Cache read
$0.01
per M tokens
Context
1,050K
tokens

Registry contract

Capabilities

Protocols
3
Chat · Responses · Messages · streaming
Tools
None
Not supported
JSON Schema
None
Not supported
Vision
Yes
Chat · Responses · Messages
Reasoning
2
Chat · Responses
Output limit
128,000
tokens
Input limit
922,000
tokens

canonical openai/gpt-6-luna · revision openai/gpt-6-luna · aliases gpt-6-luna

First request

Run it

Python · TokenSpend SDK

from tokenspend import TokenSpend

client = TokenSpend()
resp = client.chat.completions.create(
    model="openai/gpt-6-luna",
    messages=[{"role": "user", "content": "hello"}],
)

TypeScript · TokenSpend SDK

import { TokenSpend } from "@tokenspend/sdk";

const client = new TokenSpend();
const resp = await client.chat.completions.create({
  model: "openai/gpt-6-luna",
  messages: [{ role: "user", content: "hello" }]
});

curl

curl https://api.tokenspend.dev/v1/chat/completions \
  -H "content-type: application/json" \
  -H "Authorization: Bearer $TOKENSPEND_API_KEY" \
  -d '{"model":"openai/gpt-6-luna","messages":[{"role":"user","content":"hello"}]}'

Claude Code integration

export ANTHROPIC_BASE_URL=https://api.tokenspend.dev
export ANTHROPIC_API_KEY=$TOKENSPEND_API_KEY
export ANTHROPIC_MODEL=openai/gpt-6-luna

One request shape reaches every model. Claude Code connects as an integration with two environment variables. Prompts are not stored unless you enable request logging.