A side-by-side comparison of GPT-6.1 Terra and GPT-6.2 Astra: input/output pricing, capabilities and available endpoints, served live from 370.AI. Both are reachable with the same API key.
| Item | GPT-6.1 Terra | GPT-6.2 Astra |
|---|---|---|
| Input (per 1M tokens) | $0.65 | $5.2 |
| Output (per 1M tokens) | $3.25 | $26 |
| Cache read explicit (per 1M tokens) | $0.0325 | $0.26 |
| Cache write 5m (per 1M tokens) | $0.8125 | $6.5 |
| Item | GPT-6.1 Terra | GPT-6.2 Astra |
|---|---|---|
| Context window | 922,000 | — |
| Max output | 128,000 | — |
| Item | GPT-6.1 Terra | GPT-6.2 Astra |
|---|---|---|
| function_calling | Yes | — |
| prompt_caching | Yes | — |
| vision | Yes | — |
On input, GPT-6.1 Terra is cheaper ($0.65 vs $5.2 per 1M tokens). On output, GPT-6.1 Terra is cheaper ($3.25 vs $26 per 1M tokens). All prices are per million tokens in USD.
only GPT-6.1 Terra supports function_calling, prompt_caching, vision.
Yes. Both are available on 370.AI through one API key and the same OpenAI-compatible endpoint — switching means changing the model field from "gpt-6.1-terra" to "gpt-6.2-astra", nothing else.
Both are available on 370.AI under one API key — switching between them means changing the model field and nothing else, so you can use each where it fits rather than picking one.