# GPT-5.6 Terra vs GPT-6.1 Terra

As of October 27, 2026, GPT-5.6 Terra costs 100% more per input token than GPT-6.1 Terra ($2.00 vs $1.00 per 1M), and both have a 922K-token context window.

- Page: https://models.litellm.ai/compare/gpt-5.6-terra-vs-gpt-6.1-terra
- GPT-5.6 Terra: https://models.litellm.ai/models/gpt-5.6-terra
- GPT-6.1 Terra: https://models.litellm.ai/models/gpt-6.1-terra

## Side by side

| | GPT-5.6 Terra | GPT-6.1 Terra |
|---|---|---|
| Input, per 1M tokens | $2.00 | $1.00 |
| Output, per 1M tokens | $12.00 | $5.00 |
| Cache read, per 1M tokens | $0.20 | $0.05 |
| Cache write, per 1M tokens | $2.50 | $1.25 |
| Context window | 922,000 tokens | 922,000 tokens |
| Max output | 128,000 tokens | 128,000 tokens |
| Image input | Yes | Yes |
| Tool calling | Yes | Yes |
| Structured output (JSON) | Yes | Yes |
| Prompt caching | Yes | Yes |
| Reasoning | Yes | Yes |
| Providers on LiteLLM | 9 | 4 |
| Price shown is from | OpenAI | OpenAI |
| Added to LiteLLM | July 9, 2026 | October 26, 2026 |

Headline prices in USD per 1M tokens, from LiteLLM's model price file.

## Cheapest provider for each

- GPT-5.6 Terra: OpenAI at $2.00 input per 1M tokens (`gpt-5.6-terra`)
- GPT-6.1 Terra: OpenAI at $1.00 input per 1M tokens (`gpt-6.1-terra`)

## When to pick which

- GPT-5.6 Terra: Available from 9 providers through LiteLLM, vs 4.
- GPT-6.1 Terra: Costs 50% less per input token: $1.00 vs $2.00 per 1M.

## FAQ

### Which is cheaper, GPT-5.6 Terra or GPT-6.1 Terra?

GPT-6.1 Terra is cheaper at 3 input tokens per output token: $2.00 per 1M tokens blended ($1.00 input, $5.00 output), versus $4.50 ($2.00 and $12.00) for GPT-5.6 Terra, as of October 27, 2026.

### Which has the larger context window, GPT-5.6 Terra or GPT-6.1 Terra?

Both have a 922,000-token context window.

### Can I switch from GPT-5.6 Terra to GPT-6.1 Terra without changing my code?

Yes. Through LiteLLM both use the OpenAI format, so switching means changing the model name from "gpt-5.6-terra" to "gpt-6.1-terra", or pointing a LiteLLM gateway model alias at the other model. You can also use one as a fallback for the other.