Models
Five models, one endpoint. Each converts tokens to credits at its own published rate per class, so the model you pick is the price you pay.
Which model should I use?
The number in a name is the GPT generation it runs on: sol-6.1 runs GPT-6.1, and sol-6 and luna-6 run GPT-6. Pick by the work, then read its rate across the row.
sol and luna still work as model names for existing integrations: they now run sol-6.1 and luna-6, billed at those models' rates. Requests that name GPT-5.6 Terra are served by terra, which runs GPT-6.1.
| MODEL | GENERATION | CREDITS PER 1M TOKENS | BEST FOR | |
|---|---|---|---|---|
| INPUT | OUTPUT + REASONING | |||
| astra | GPT-6 | 5,500,000 | 27,500,000 | Frontier reasoning on a 1M-token window, for the hardest work of all. |
| sol-6.1 | GPT-6.1 | 1,100,000 | 5,500,000 | Deep reasoning, hard coding, agentic tasks and research. |
| sol-6 | GPT-6 | 1,100,000 | 5,500,000 | Deep reasoning, hard coding, agentic tasks and research. |
| terra | GPT-6.1 | 550,000 | 2,750,000 | Fast, efficient everyday work — agents, tools, coding, computer use and visual tasks. |
| luna-6 | GPT-6 | 55,000 | 275,000 | Fast drafts, classification, summaries and high-volume chat. |
The five models
astra
GENERATION · GPT-6
Frontier reasoning on a 1M-token window, for the hardest work of all.
BEST FOR
- Our deepest reasoning tier for the hardest work
- A 1M-token context window
- Every rate published: 5.5× input, 27.5× output
sol-6.1
GENERATION · GPT-6.1
Sol's GPT-6.1 model, the newest in the family, at 1.1 AI credits per input token.
BEST FOR
- The GPT-6.1 model in the Sol family
- The anchor rate: 1.1× input, 5.5× output
- Switch by naming sol-6.1; nothing else changes
sol-6
GENERATION · GPT-6
The GPT-6 generation of Sol, at 1.1 AI credits per input token.
BEST FOR
- The GPT-6 generation of the Sol family
- The anchor rate: 1.1× input, 5.5× output
- Switch by naming sol-6; nothing else changes
terra
GENERATION · GPT-6.1
Fast, efficient everyday work — agents, tools, coding, computer use and visual tasks.
BEST FOR
- Agents, tools & everyday coding
- Computer use & visual tasks
- Half the anchor rate: 0.55× input, 2.75× output
luna-6
GENERATION · GPT-6
The GPT-6 generation of Luna, at the lowest rates published here.
BEST FOR
- The GPT-6 generation of the Luna family
- The lowest rates: 0.055× input, 0.275× output
- Switch by naming luna-6; nothing else changes
Credit weights
Short context
| MODEL | INPUT | CACHE READ | CACHE WRITE | OUTPUT + REASONING |
|---|---|---|---|---|
| astra | 5.5 | 2.75 | 5.5 | 27.5 |
| sol-6.1 | 1.1 | 0.55 | 1.1 | 5.5 |
| sol-6 | 1.1 | 0.55 | 1.1 | 5.5 |
| terra | 0.55 | 0.275 | 0.55 | 2.75 |
| luna-6 | 0.055 | 0.0275 | 0.055 | 0.275 |
Long context
| MODEL | INPUT | CACHE READ | CACHE WRITE | OUTPUT + REASONING |
|---|---|---|---|---|
| astra | 5.5 | 2.75 | 5.5 | 27.5 |
| sol-6.1 | 1.1 | 0.55 | 1.1 | 5.5 |
| sol-6 | 1.1 | 0.55 | 1.1 | 5.5 |
| terra | 0.55 | 0.275 | 0.55 | 2.75 |
| luna-6 | 0.055 | 0.0275 | 0.055 | 0.275 |
A request with more than 272,000 input tokens converts at the long-context rate. Plans and pricing · Your first request