GPT API
Use OpenAI GPT-6.1, GPT-6 and GPT-5.6 through SandBase. Each generation has a large flagship tier, a balanced middle tier and a small fast tier, plus Pro reasoning modes.
Explore the model lineup
Preview the output style, compare capabilities, then open any model for full specs, pricing, and a live Playground.
GPT-6.1 Sol
GPT-6.1 Sol is OpenAI's upgrade to GPT-6 Sol, introduced at DevDay 2026 and positioned between GPT-6 Astra and GPT-6 Luna, with text and image input. OpenAI says it delivers near-Astra performance for...
GPT-6 Sol
GPT-6 Sol is the middle tier of OpenAI's GPT-6 reasoning family, released in September 2026 alongside GPT-6 Luna and built, according to OpenAI, for complex coding and agentic workflows, with text and...
GPT-6 Luna
GPT-6 Luna is the smallest, fastest tier of OpenAI's GPT-6 reasoning family, described by OpenAI as its most efficient model for focused, high-volume tasks, with text and image input. It was trained w...
GPT-6 Astra
GPT-6 Astra is OpenAI's flagship GPT-6 reasoning model, described by OpenAI as its most capable model for the most demanding work, with text and image input. OpenAI recommends it for complex reasoning...
GPT-5.6 Sol
GPT-5.6 Sol is the flagship tier of OpenAI's GPT-5.6 reasoning family, accepting text and image input; OpenAI says it roughly corresponds to the unsuffixed tier of earlier GPT-5 families, and the plai...
GPT-5.6 Terra
GPT-5.6 Terra is the middle tier of OpenAI's GPT-5.6 reasoning family, with text and image input, and is described by OpenAI as a balanced model for everyday work; it roughly corresponds to the mini t...
GPT-5.6 Luna
GPT-5.6 Luna is the smallest, fastest tier of OpenAI's GPT-5.6 reasoning family, with text and image input; OpenAI says it roughly corresponds to the nano tier of earlier GPT-5 families. It is designe...
GPT-6 Luna Pro
GPT-6 Luna Pro is the same GPT-6 Luna model, OpenAI's most efficient GPT-6 tier, served in OpenAI's pro reasoning mode instead of standard mode. Pro mode spends more model work per request and returns...
GPT-5.6 Luna Pro
GPT-5.6 Luna Pro is the same GPT-5.6 Luna model, OpenAI's smallest GPT-5.6 tier, served in OpenAI's pro reasoning mode rather than as different weights. In pro mode the model performs more work on eac...
GPT-6 Astra Pro
GPT-6 Astra Pro is the same GPT-6 Astra model, OpenAI's most capable GPT-6 tier, served in OpenAI's pro reasoning mode rather than as different weights. In pro mode the model does more work on each re...
GPT-6.1 Sol Pro
GPT-6.1 Sol Pro is the same GPT-6.1 Sol model, OpenAI's near-Astra GPT-6 tier, served in OpenAI's pro reasoning mode rather than as different weights. Pro mode spends more model work on each request b...
GPT-5.6 Sol Pro
GPT-5.6 Sol Pro is the same GPT-5.6 Sol model, the flagship of OpenAI's GPT-5.6 family, served in OpenAI's pro reasoning mode rather than as a separate model. Pro mode spends more model work on each r...
GPT-6 Sol Pro
GPT-6 Sol Pro is the same GPT-6 Sol model, the middle tier of OpenAI's GPT-6 family, served in OpenAI's pro reasoning mode rather than as a separate model. Pro mode does more model work on each reques...
GPT-5.6 Terra Pro
GPT-5.6 Terra Pro is the same GPT-5.6 Terra model, the balanced middle tier of OpenAI's GPT-5.6 family, served in OpenAI's pro reasoning mode instead of standard mode. Pro mode applies more model work...
GPT-6.1 Terra
GPT-6.1 Terra is the middle tier of OpenAI's GPT-6.1 family and the replacement for GPT-5.6 Terra, with text and image input. OpenAI positions it for everyday agentic, coding and writing work, with pa...
GPT-6.1 Terra Pro
GPT-6.1 Terra Pro is the same GPT-6.1 Terra model, the balanced middle tier of OpenAI's GPT-6.1 family, served in OpenAI's pro reasoning mode instead of standard mode. Pro mode applies more model work...
Model lineup
Context window and positioning from each provider.
| Model | Context | Positioning |
|---|---|---|
| GPT-5.6 Luna | 1050K | GPT-5.6 Luna is the smallest, fastest tier of OpenAI's GPT-5.6 reasoning family, with text and image input; OpenAI says it roughly corresponds to… |
| GPT-5.6 Sol | 1050K | GPT-5.6 Sol is the flagship tier of OpenAI's GPT-5.6 reasoning family, accepting text and image input; OpenAI says it roughly corresponds to the… |
| GPT-5.6 Terra | 1050K | GPT-5.6 Terra is the middle tier of OpenAI's GPT-5.6 reasoning family, with text and image input, and is described by OpenAI as a balanced model for… |
| GPT-6 Astra | 1050K | GPT-6 Astra is OpenAI's flagship GPT-6 reasoning model, described by OpenAI as its most capable model for the most demanding work, with text and… |
| GPT-6.1 Sol | 1050K | GPT-6.1 Sol is OpenAI's upgrade to GPT-6 Sol, introduced at DevDay 2026 and positioned between GPT-6 Astra and GPT-6 Luna, with text and image input |
| GPT-6 Luna | 1050K | GPT-6 Luna is the smallest, fastest tier of OpenAI's GPT-6 reasoning family, described by OpenAI as its most efficient model for focused,… |
| GPT-5.6 Luna Pro | 1050K | GPT-5.6 Luna Pro is the same GPT-5.6 Luna model, OpenAI's smallest GPT-5.6 tier, served in OpenAI's pro reasoning mode rather than as different… |
| GPT-6 Sol | 1050K | GPT-6 Sol is the middle tier of OpenAI's GPT-6 reasoning family, released in September 2026 alongside GPT-6 Luna and built, according to OpenAI, for… |
| GPT-5.6 Sol Pro | 1050K | GPT-5.6 Sol Pro is the same GPT-5.6 Sol model, the flagship of OpenAI's GPT-5.6 family, served in OpenAI's pro reasoning mode rather than as a… |
| GPT-6.1 Sol Pro | 1050K | GPT-6.1 Sol Pro is the same GPT-6.1 Sol model, OpenAI's near-Astra GPT-6 tier, served in OpenAI's pro reasoning mode rather than as different weights |
| GPT-5.6 Terra Pro | 1050K | GPT-5.6 Terra Pro is the same GPT-5.6 Terra model, the balanced middle tier of OpenAI's GPT-5.6 family, served in OpenAI's pro reasoning mode… |
| GPT-6 Luna Pro | 1050K | GPT-6 Luna Pro is the same GPT-6 Luna model, OpenAI's most efficient GPT-6 tier, served in OpenAI's pro reasoning mode instead of standard mode |
Current OpenAI GPT models
SandBase serves OpenAI GPT models on the OpenAI-compatible POST /v1/chat/completions, with Responses API support where the model offers it.
Generations and tiers
- GPT-6.1: Sol, positioned between GPT-6 Astra and Luna, and Terra, the balanced tier that replaces GPT-5.6 Terra.
- GPT-6: Astra (flagship), Sol (middle) and Luna (smallest and fastest).
- GPT-5.6: Sol (flagship), Terra (balanced) and Luna. GPT-5.6 Luna is the most used LLM on SandBase.
Pro variants run the same weights in OpenAI's pro reasoning mode. All current GPT models accept text and image input with a context of about 1M tokens. For OpenAI image models, see GPT Image.
Start using GPT API on SandBase
Switch models by changing one field.
- 01
Create an API key
Sign in to the SandBase Console and create a key on the API Keys page. Keep it in an environment variable and never commit it to source control.
TERMINALexport SANDBASE_API_KEY="YOUR_SANDBASE_API_KEY" - 02
Send a chat request
Call the OpenAI-compatible Chat Completions API with model openai/gpt-6.1-sol. Any OpenAI SDK works with base URL https://api.sandbase.ai/v1.
TERMINALcurl https://api.sandbase.ai/v1/chat/completions \ -H "Authorization: Bearer $SANDBASE_API_KEY" \ -H "Content-Type: application/json" \ -d '{"model": "openai/gpt-6.1-sol", "messages": [{"role": "user", "content": "Explain vector databases in two sentences."}]}' - 03
Connect your AI tools
Use the same key in Claude Code, Codex, Cursor and other clients. See Use in AI tools for setup.
Questions, answered
What do Sol, Terra, Luna and Astra mean?
They are OpenAI’s tier names. Astra is the GPT-6 flagship, Sol and Terra are middle tiers, and Luna is the smallest and fastest.
What is a Pro model?
The same model served in OpenAI’s pro reasoning mode, not different weights. It reasons longer on hard problems.
Can I use the OpenAI SDK?
Yes. Set the base URL to https://api.sandbase.ai/v1 and use your SandBase key.
Where are older GPT models?
GPT-5.5 and earlier, GPT-4.1 and GPT-4o are on the OpenAI vendor page.
Build with GPT API.
One key, consistent APIs, and usage-based pricing across every model on this page.