GPT API pricing. Up to 75% below list.
GPT is OpenAI's family of models. GPT-6 comes in three tiers: Astra, the most capable; Sol, for complex coding and agentic workflows; and Luna, the fastest and lowest-cost. GPT-6.1 Sol is the newest Sol. Zurelay serves them in OpenAI's API format, so the OpenAI SDKs and any OpenAI-compatible tool work once you change the base URL and key.
- GPT models
- 7
- Below OpenAI's list
- 59–75%
- From, per 1M input
- $0.025
Pricing
Every GPT model. Live prices, one key.
Each GPT model on Zurelay, with OpenAI's list price beside ours.
| Model | Context | Input / 1M | Output / 1M | 10K requests | You save |
|---|---|---|---|---|---|
| GPT-6 Astragpt-6-astra | 1.05M | $2.50 | $12.50 | $112.50 | 75%off |
| GPT-6.1 Solgpt-6.1-sol | 1.05M | $0.50 | $2.50 | $22.50 | 75%off |
| GPT-6 Solgpt-6-sol | 1.05M | $0.50 | $2.50 | $22.50 | 75%off |
| GPT-6 Lunagpt-6-luna | 1.05M | $0.025 | $0.125 | $1.125 | 75%off |
| GPT-5.6 Solgpt-5.6-sol | 1.05M | $1.14 | $5.70 | $51.30 | 72%off |
| GPT-5.6 Terragpt-5.6-terra | 1.05M | $0.54 | $3.26 | $27.10 | 73%off |
| GPT-5.6 Lunagpt-5.6-luna | 1.05M | $0.08 | $0.49 | $4.05 | 59%off |
Prices in US dollars per 1M tokens, live from the catalog, with OpenAI's list price struck through. 10K requests is 10,000 requests of 2,000 tokens in and 500 out, at each price. You save is on output tokens.
Which model
Which GPT model to use. Same key for all of them.
The hardest tasks
GPT-6 Astra
$2.50 / $12.50 per 1M tokens
OpenAI's most capable model, for complex reasoning, coding, research and document work.
GPT-6 Astra APICoding and agents
GPT-6.1 Sol
$0.50 / $2.50 per 1M tokens
OpenAI says it nearly matches GPT-6 Astra on agentic coding, computer use and professional work, at one-fifth of Astra's list price per token.
GPT-6.1 Sol APIFast, high-volume calls
GPT-6 Luna
$0.025 / $0.125 per 1M tokens
The fastest, lowest-cost GPT-6 model, for summaries, extraction and quick answers.
GPT-6 Luna APIAlso on Zurelay, for prompts, evals and agents tuned on them: GPT-6 Sol, GPT-5.6 Sol, GPT-5.6 Terra and GPT-5.6 Luna.
Quickstart
Change two lines. Keep your code.
Point the OpenAI SDK, or any OpenAI-compatible tool, at https://api.zurelay.com/v1 and use your Zurelay key. Streaming, tool calling and structured output work as documented.
Add credit from $10, with no subscription. The quickstart has the rest.
from openai import OpenAIclient = OpenAI( base_url="https://api.zurelay.com/v1", api_key="YOUR_ZURELAY_KEY",)stream = client.chat.completions.create( model="gpt-6-astra", messages=[{"role": "user", "content": "Explain quicksort in two sentences."}], stream=True,)for chunk in stream: if chunk.choices: print(chunk.choices[0].delta.content or "", end="")Verified
The GPT you asked for. Checked every day.
Model capacity is often bought ahead, through prepaid credits, committed-spend contracts and volume tiers, and not all of it gets used. Sellers offer it below list price. Zurelay tests each route, pools several per model and sends every request to one that is available and verified.
Before a route serves requests, and every day after, it has to pass identity, dated-knowledge and reasoning checks that catch a different or older model sold under a newer name. Failed attempts move to another route, and you aren’t billed for them. How models are verified.
Live health for every model is on the status page.
How much does the GPT API cost?
On Zurelay, GPT models cost from $0.025 input and $0.125 output per 1M tokens (GPT-6 Luna) to $2.50 and $12.50 (GPT-6 Astra), 59–75% below OpenAI's list prices. There's no subscription or minimum spend: you add prepaid credit from $10 and pay for the tokens you use.
Is it the real GPT?
Yes. Each model is served over several routes run by independent sellers. Every route is tested before it serves requests and every day after, with identity, dated-knowledge and reasoning checks that catch a different or older model sold under the name you asked for. If an answer doesn't look right, send its x-request-id to support and we check the route that served it.
Why is it cheaper than OpenAI's own API?
Sellers offer model capacity they bought ahead, through prepaid credits, committed-spend contracts and volume tiers, below list price. Zurelay tests it, pools several routes per model and sends each request to one that is available and verified. Requests aren't served under OpenAI's own terms for its customers; our Terms explain how they are served.
How do I start calling GPT through Zurelay?
Create a key, then point the OpenAI SDK, or any OpenAI-compatible tool, at https://api.zurelay.com/v1 with a model ID such as gpt-6-astra. Code that already uses the OpenAI SDK only needs the base URL, the key and the model name changed.
What's the difference between GPT-6 Sol and GPT-6.1 Sol?
GPT-6.1 Sol is OpenAI's newer Sol model, released on September 29, 2026, a week after GPT-6 Sol. OpenAI says it nearly matches GPT-6 Astra on agentic coding, computer use and professional work. Both are on Zurelay, so code tuned on GPT-6 Sol keeps working while you test 6.1.
Stop paying list price.
Start saving today.
Create a key in seconds, point the SDK you already use at Zurelay, and every request costs up to 90% less from the first token.