Extraction estimate · prices checked 2026-11-03
GPT-6.1 Terra vs Levanto Sage 2 for field extraction
List prices
| Model | $ per M input | $ per M output | Source |
|---|---|---|---|
| GPT-6.1 Terra | $1 | $5 | OpenAI pricing |
| GPT-6 Luna | $0.1 | $0.5 | OpenAI pricing |
| Levanto Sage 2 | $0.05 | $1 | Levanto list price |
Checked 2026-11-03. Same table the public prices endpoint serves.
What we measured and what we assumed
- Measured: Levanto Sage 2 used 329 input and 607 output tokens per document on average, over 36 synthetic lead, ticket and invoice documents (228 field values), in our bench run on 2026-11-03. Its output includes per-field probabilities, which is why it is larger than the JSON alone.
- Assumed for GPT-6.1 Terra: 700 input tokens (a ~300-token document plus the audit’s default 400-token prompt with field definitions) and 120 visible output tokens for the JSON.
- Our estimate: 300 reasoning tokens at GPT-6.1 Terra’s API default effort (
medium), billed as output. Extraction gets 2.5× our yes/no estimate.
That gives an estimated $2.80 per 1,000 documents on GPT-6.1 Terra, against $0.624 on Levanto Sage 2.
How accurate was Levanto Sage 2 on our bench?
| Set | Documents | Field values right | Lead / ticket / invoice |
|---|---|---|---|
| Clean templates | 36 | 96.9% of 228 | 98.8% / 90% / 100% |
| Messier wording | 15 | 88.4% of 95 | 82.9% / 88% / 94.3% |
Weakest fields: ticket.amount_paid (58% on clean documents) and lead.budget (20% on the messier set). Money amounts and free-form budgets are where a fallback to GPT-6.1 Terra matters. Levanto Sage 2 left fields empty correctly 84.1% of the time when they were absent. This is a small synthetic bench, not a benchmark of your data.
Effort level changes the bill
Estimated GPT-6.1 Terra cost per 1,000 documents by effort level, with reasoning billed as output:
| Effort | Est. reasoning tokens | Per 1,000 documents |
|---|---|---|
| none | 0 | $1.30 |
| low | 100 | $1.80 |
| medium (API default) | 300 | $2.80 |
| high | 800 | $5.30 |
| xhigh | 2000 | $11.30 |
If the fields are copied straight from the text, a lower effort may give the same JSON; test it on your documents. When lowering effort beats switching models.
Monthly estimate by volume
“Share kept” is a scenario: the share of documents where Levanto Sage 2 is confident on every field. The rest also go to GPT-6.1 Terra.
| Documents / month | All on GPT-6.1 Terra | Hybrid, 50% kept | 70% kept | 90% kept |
|---|---|---|---|---|
| 10,000 | $28.00 | $20.24 | $14.64 | $9.04 |
| 100,000 | $280 | $202 | $146 | $90.36 |
| 1,000,000 | $2,800 | $2,024 | $1,464 | $904 |
Estimates at the assumptions above. The 30% bar needs Levanto Sage 2 to keep at least 52% of documents. For yes/no calls on GPT-6.1 Terra, see GPT-6.1 Terra vs Levanto Sage 2 for classification.
Check it on your own documents
Paste 5 to 25 documents with the JSON GPT-6.1 Terra returned and your field definitions into the free cutover audit. It reports agreement per field, picks the confidence threshold and projects cost with your token counts. How it works · Other models · Is my task too simple for a big model?