A side-by-side comparison of Claude Sonnet 5 and GPT-5.6 Terra: input/output pricing, capabilities and available endpoints, served live from 370.AI. Both are reachable with the same API key.
| Item | Claude Sonnet 5 | GPT-5.6 Terra |
|---|---|---|
| Input (per 1M tokens) | $1.8 | $1.625 |
| Output (per 1M tokens) | $9 | $9.75 |
| Cache read (per 1M tokens) | $0.18 | $0.1625 |
| Cache write 5m (per 1M tokens) | $2.25 | $2.03125 |
| Item | Claude Sonnet 5 | GPT-5.6 Terra |
|---|---|---|
| Context window | 1,000,000 | 922,000 |
| Max output | — | 128,000 |
| Item | Claude Sonnet 5 | GPT-5.6 Terra |
|---|---|---|
| function_calling | Yes | Yes |
| prompt_caching | Yes | Yes |
| vision | Yes | Yes |
On input, GPT-5.6 Terra is cheaper ($1.8 vs $1.625 per 1M tokens). On output, Claude Sonnet 5 is cheaper ($9 vs $9.75 per 1M tokens). All prices are per million tokens in USD.
Claude Sonnet 5 does — Claude Sonnet 5 accepts 1,000,000 input tokens and GPT-5.6 Terra accepts 922,000.
both support 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 "claude-sonnet-5" to "gpt-5.6-terra", 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.