API price comparison · Updated
GPT-6.1 Terra costs $1.00 per million input tokens and $5.00 per million output tokens; GPT-6 Luna costs $0.10 and $0.50. For an agent task (80,000 input tokens, 60,000 of them cached, and 6,000 output), GPT-6.1 Terra costs $0.053 and GPT-6 Luna $0.0056: GPT-6.1 Terra costs 9.5× as much.
GPT-6 Luna costs 90% less for this workload. Excludes cache writes, tools and taxes.
| Price | GPT-6.1 Terra | GPT-6 Luna |
|---|---|---|
| Model ID | gpt-6.1-terra | gpt-6-luna |
| Input | $1.00 | $0.10 |
| Cache read | $0.05 | $0.01 |
| Cache write | $1.25 | $0.125 |
| Output | $5.00 | $0.50 |
| Batch in / out | $0.50 / $2.50 | $0.05 / $0.25 |
| Long prompts | Over 272,000: $2.00 / $7.50 | Over 272,000: $0.20 / $0.75 |
| Scheduled change | None announced | None announced |
| Status | Available | Available |
Prices for each provider’s own API, from OpenAI’s pricing page. The lower price in each row is highlighted. Ganivra uses these same rates to price GPT-6.1 Terra and GPT-6 Luna calls.
Worked out from the prices above at standard rates, with no Batch discount. Long-prompt rates apply where a model has them.
| Request | GPT-6.1 Terra | GPT-6 Luna | Per 1,000 requests | Difference |
|---|---|---|---|---|
| Chat reply3,000 input tokens, 500 output | $0.0055 | $0.0006 | $5.50 / $0.550 | GPT-6.1 Terra costs 10× as much |
| Document summary30,000 input tokens, 1,500 output | $0.037 | $0.0037 | $37.50 / $3.75 | GPT-6.1 Terra costs 10× as much |
| Agent task80,000 input tokens (60,000 cached), 6,000 output | $0.053 | $0.0056 | $53.00 / $5.60 | GPT-6.1 Terra costs 9.5× as much |
| Long document300,000 input tokens, 2,000 output | $0.615 | $0.061 | $615 / $61.50 | GPT-6.1 Terra costs 10× as much |
Ganivra prices every GPT-6.1 Terra and GPT-6 Luna call you make and adds it up by customer, feature and workflow, next to what each customer pays. Switch a workflow and see what it did to each customer’s margin.
Per million tokens, GPT-6.1 Terra costs $1.00 input and $5.00 output, and GPT-6 Luna $0.10 input and $0.50 output. For an agent task (80,000 input tokens, 60,000 of them cached, and 6,000 output), GPT-6.1 Terra costs 9.5× as much: $53.00 against $5.60 per 1,000 tasks.
$1.00 input and $5.00 output per million tokens on OpenAI's API, with cached input at $0.05 and Batch at $0.50 input and $2.50 output. Prompts over 272,000 tokens cost $2.00 input and $7.50 output.
$0.10 input and $0.50 output per million tokens on OpenAI's API, with cached input at $0.01 and Batch at $0.05 input and $0.25 output. Prompts over 272,000 tokens cost $0.20 input and $0.75 output.
For a 300,000 input tokens, 2,000 output request, GPT-6.1 Terra costs $0.615 and GPT-6 Luna $0.061: GPT-6.1 Terra costs 10× as much. On GPT-6.1 Terra, prompts over 272,000 tokens cost $2.00 input and $7.50 output for the whole request; on GPT-6 Luna, prompts over 272,000 tokens cost $0.20 input and $0.75 output for the whole request.
Record what each call actually used, then price the same usage on both models. Ganivra does this from your recorded calls: it shows what each customer, feature and workflow would cost on GPT-6.1 Terra and on GPT-6 Luna, next to what each customer pays you.
Every model on one page: GPT-6.1 Terra pricing · all model price comparisons · all supported models.