Loading

gpt-6-luna-decisions pricing and usage · CheaperInference

Model record / OpenAI

gpt-6-luna-decisions

Access gpt-6-luna-decisions from OpenAI through one OpenAI-compatible API with live market-linked pricing and usage-based billing.

DecisionText inputStandard generationNon-streaming35% below list

Input / 1M tokens~~$0.10 list~~$0.065

Cached input / 1M tokens$0.065

Current discount35%

Observed reliability

100

Successful provider-reaching requests

Output speed

—

Median tokens per second over sustained generations

TTFT

—

p50 · p90 not available · n 0

Latency

1.3 s

p50 · p90 1.4 s · n 2

Evidence strength

—

Provider: OpenAI
Model ID: gpt-6-luna-decisions
Type: Decision
Endpoint: /v1/decisions
Input: text
Output: text
Vision input: Not supported
Image editing: Not supported
Video input: Not supported
Reasoning: Not supported
Streaming: Not supported
Context window: 1,050,000 tokens

Pricing history

See how much this model saves and when its recorded price has been lowest.

Time zone

gpt-6-luna-decisions

Early data

Savings are visible now, but a best-time recommendation needs at least 12 observations across 6 different hours.

Last 30 days

Average saved

35.0%

Last 30 days

Cheapest time

Collecting data

Too early

Hourly coverage

5/24

5 total observations

Signal quality

Early

More history needed

Typical unit savings$0.04 / 1M input tokens$0.00 / 1M output tokens

Hover a bar for savings per token and observation counts.

Source buckets are UTC; labels are converted to UTC.

Last 24 hours

#208

of 251 ranked models

Last 7 days

#209

of 251 ranked models

Last 30 days

#210

of 252 ranked models

Ready when you are

Stop paying list price for tokens.

Marketplace pricing, capped at list, optimized further.

Start saving Talk to sales

POST /v1/decisions

1curl https://api.cheaperinference.com/v1/decisions \2  -H "Authorization: Bearer ci_live_YOUR_API_KEY" \3  -H "Content-Type: application/json" \4  -d '{5    "input": "I was charged twice.",6    "model": "gpt-6-luna-decisions",7    "questions": [8      {9        "name": "refund",10        "type": "predicate",11        "instructions": "Does the customer ask for a refund?"12      }13    ]14  }'