GPT-6.1 Terra (released October 26, 2026) looks simple at $1 in / $5 out per million tokens — until the cache-write tiers, the 272K long-context surcharge and the Batch/Flex/Fast modes get involved. This calculator prices all of it, and compares Terra against GPT-5.6 Terra, GPT-6.1 Sol and GPT-6 Luna on the same workload. Rates checked November 4, 2026.
GPT-6.1 Terra monthly cost
| Model | Input /1M | Cached /1M | Output /1M | Monthly cost |
|---|
Sol and Luna publish no separate cached-input rate, so their cached tokens are billed at the full input rate in this comparison. Cache writes and the long-context surcharge are Terra-specific rows and are excluded from the comparison table.
| Item | Rate per 1M tokens |
|---|---|
| Input | $1.00 |
| Cached input | $0.05 |
| Cache write, 30-minute retention | $1.25 |
| Cache write, 12-hour retention | $2.50 |
| Output | $5.00 |
| Prompts over 272K tokens | input & cache ×2, output ×1.5 (whole request) |
| Batch / Flex mode | all rates ×0.5 |
| Fast mode | all rates ×2 |
Context window 1.05M tokens, up to 128K output. The predecessor GPT-5.6 Terra cost $2 / $0.20 / $12 — Terra halves input and output and cuts cached reads by 75%.
Terra Cost Planner Pack — $9.99
25 pre-built workload scenarios (support agents, invoice processing, RAG chatbots, computer-use RPA, batch pipelines…) with the monthly Terra budget already calculated, a four-model monthly planner, and a usage-CSV estimator with the formulas written out. Download, plug in your numbers, get a budget.
One-time payment. Not affiliated with OpenAI; rates verified November 4, 2026.
$1.00 input, $0.05 cached input, $5.00 output. Cache writes are $1.25 (30-minute retention) or $2.50 (12-hour) per million tokens.
Any single request whose prompt exceeds 272,000 input tokens is billed at 2× input and cache rates and 1.5× output — for the entire request, not just the excess.
Usually by a lot: cached reads fell from $0.20 to $0.05 per million. On a 10M-input session at 97% cache hit with 200K output, Terra costs about $1.79 versus $4.94 on GPT-5.6 Terra.
Yes — every rate halves ($0.50 input, $2.50 output). If your workload tolerates asynchronous processing, it is the single biggest saving available.
Multiply your monthly input tokens by $1.00 and your output tokens by $5.00, per million, then adjust for caching and mode. The calculator above does this in one click; the $9.99 planner pack adds 25 ready-made workload budgets.
Cached input reads cost $0.05 per million tokens — 20 times cheaper than fresh input at $1.00. Writing the cache costs $1.25 per million tokens for 30-minute retention or $2.50 for 12-hour retention.
Yes, exactly half. Terra is $1.00 input and $5.00 output per million tokens; Sol is $2.00 input and $10.00 output per million.
Luna is the budget tier at $0.10 input and $0.50 output per million tokens — one tenth of Terra's price — aimed at high-volume, simpler tasks. Terra is the mid tier for work that needs stronger reasoning.
Fast mode costs double the standard rates: $2.00 per million input tokens and $10.00 per million output tokens. Batch and Flex modes go the other way at half price.
Yes. When one request's prompt exceeds 272K tokens, input and cache rates double for the whole request and output rises 1.5 times, from $5.00 to $7.50 per million tokens.
Most support chatbots fit Terra: strong answers at $1/$5 per million with cheap cached reads for repeated system prompts. Luna suits simple FAQ replies at one tenth of the price; Sol is for the hardest reasoning steps.
Independent tool, not affiliated with OpenAI. Prices as published by OpenAI and checked on November 4, 2026 — verify before committing a budget.