Models / GPT pricing
GPT API pricing
13 GPT models from OpenAI on one key, per million tokens. Input 37% to 70% under OpenAI's list price, output 40% to 70%. Lowest price: GPT-6 Luna, $0.0625 in and $0.15 out.
Prices · per million tokens, USD, next to OpenAI's list price
| Model | Input | Cached input | Output | Under list |
|---|---|---|---|---|
| GPT-6.1 Solgpt-6.1-sol | $0.60list $2.00 | $0.06list $0.10 | $3.00list $10.00 | 70% in · 70% out |
| GPT-6 Solgpt-6-sol | $0.60list $2.00 | $0.12list $0.20 | $3.00list $10.00 | 70% in · 70% out |
| GPT-5.5gpt-5.5 | $1.50list $5.00 | $0.15list $0.50 | $9.00list $30.00 | 70% in · 70% out |
| GPT-6 Astragpt-6-astra | $3.00list $10.00 | $0.30list $1.00 | $15.00list $50.00 | 70% in · 70% out |
| GPT-6 Lunagpt-6-luna | $0.0625list $0.10 | $0.0125list $0.01 | $0.15list $0.50 | 37% in · 70% out |
| GPT-5.6 Lunagpt-5.6-luna | $0.12list $0.20 | $0.012list $0.02 | $0.72list $1.20 | 40% in · 40% out |
| GPT-5.6 Solgpt-5.6-sol | $1.20list $2.00 | $0.12list $0.20 | $3.00list $10.00 | 40% in · 70% out |
| GPT-5.6 Terragpt-5.6-terra | $1.20list $2.00 | $0.12list $0.20 | $3.60list $12.00 | 40% in · 70% out |
| GPT-5.4gpt-5.4 | $1.50list $2.50 | $0.15list $0.25 | $9.00list $15.00 | 40% in · 40% out |
| GPT-5.4 Minigpt-5.4-mini | $0.45list $0.75 | $0.045list $0.075 | $2.70list $4.50 | 40% in · 40% out |
| GPT-5.3-Codexgpt-5.3-codex | $1.05list $1.75 | $0.105list $0.175 | $8.40list $14.00 | 40% in · 40% out |
| GPT-4ogpt-4o | $1.50list $2.50 | input rate | $6.00list $10.00 | 40% in · 40% out |
| GPT-4o minigpt-4o-mini | $0.09list $0.15 | input rate | $0.36list $0.60 | 40% in · 40% out |
List price: OpenAI's published rate, read October 2026. Live from GET https://api.uplinkswitch.com/v1/catalog.
Call them · same base URL and key for every model
Python · OpenAI SDK
from openai import OpenAI
client = OpenAI(
base_url="https://api.uplinkswitch.com/v1",
api_key="sk-uplink-live-...",
)
completion = client.chat.completions.create(
model="gpt-6.1-sol",
messages=[{"role": "user", "content": "Summarize this in one line."}],
)
print(completion.choices[0].message.content)TypeScript · OpenAI SDK
import OpenAI from 'openai';
const client = new OpenAI({
baseURL: 'https://api.uplinkswitch.com/v1',
apiKey: 'sk-uplink-live-...',
});
const completion = await client.chat.completions.create({
model: 'gpt-6.1-sol',
messages: [{ role: 'user', content: 'Summarize this in one line.' }],
});
console.log(completion.choices[0].message.content);Questions
- Which GPT model costs the least?
- GPT-6 Luna (gpt-6-luna): $0.0625 per million input tokens and $0.15 per million output tokens.
- How far under OpenAI's list price is it?
- Input runs 37% to 70% under OpenAI's list price, output 40% to 70%, depending on the model. Each row above shows both prices.
- Is there a subscription?
- No. Prepaid credit from $10, with no subscription or monthly fee. Each top-up locks your prices for 30 days.
- How is cached input billed?
- At the cached rate in the table. A model with no cached rate bills cached tokens at its input rate.
- Are there rate limits?
- Every key carries a request-per-minute limit and a concurrency limit.