$1.00/M input · $5.00/M output. List prices from provider data; in idapt, chat is metered per token with transparent, usage-based pricing at the prices shown in the app.
| Rate | Price | Unit |
|---|---|---|
| Input | 1 | /M tokens |
| Output | 5 | /M tokens |
| Cache read | 0.049999999999999996 | /M tokens |
| Cache write | 1.25 | /M tokens |
| Web search | 0.01 | /search |
| Workload | Tokens | List price |
|---|---|---|
| Quick question | 1K tokens in, 500 out | $0.0035 |
| Long-document summary | 60K tokens in, 2K out | $0.07 |
| Agent working session | 400K tokens in, 40K out across a day | $0.60 |
Compare up to four models at once in the cost calculator.
GPT 6.1 Terra lists at $1.00 per 1M input tokens and $5.00 per 1M output tokens.
Yes. Cached input tokens are billed at $0.05 per 1M, versus $1.00 for fresh input. Prompts that repeat a long prefix (a system prompt, attached files) benefit the most.
A message with about 1,000 input tokens and a 500-token reply costs roughly $0.0035 at list price. Long documents and long replies scale that linearly with token counts.
GPT 6.1 Terra has the lower blended price at a 3:1 input:output mix. GPT 6.1 Terra: $1.00 in / $5.00 out per 1M. GPT 6.1 Sol: $2.00 in / $10.00 out per 1M.
Chat with GPT 6.1 Terra in idapt is metered per token with transparent, usage-based pricing at the prices shown in the app. Subscriptions include a weekly usage allowance before any balance is touched.
Part of the GPT 6.1 Terra model page · cheapest models board · price changes