GPT-5.6 Terra
A balanced GPT-5.6 model for strong reasoning and coding performance at a lower price point.
- Input price
- $1.80–$3.60list $2.0010% off
- Output price
- $10.80–$16.20list $12.0010% off
- Context
- 1.1M
- Max output
- 128K
- Capability
- 161 (#19 of 82)
- Human preference
- 1449
- 30-day uptime
- —
- Released
- 2026-07-09
- Knowledge cutoff
- 2026-02-16
Providers
This model is served by the dedicated providers below. We pick the provider for each request, so provider preferences don’t apply, including a provider named in your request. Prices in USD per 1M tokens. Need a custom setup? Contact [email protected].
- SuccessTTFT
- Azure AI FoundryGlobal——
- OpenAIUnited States——
Pricing
Prices for this model. Each request is billed at these prices, whichever provider serves it.
| Item | Standard | Standard Discount | Flex | Flex Discount | Batch | Batch Discount | Priority | Priority Discount | Price | Price Discount | |||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Prompt ≤ 272K tokens | |||||||||||||||
| Inputper 1M tokens | $1.80 | list $2.00 | 10% off | $0.90 | list $1.00 | 10% off | $0.90 | list $1.00 | 10% off | $3.60 | list $4.00 | 10% off | — | ||
| Outputper 1M tokens | $10.80 | list $12.00 | 10% off | $5.40 | list $6.00 | 10% off | $5.40 | list $6.00 | 10% off | $21.60 | list $24.00 | 10% off | — | ||
| Cache readper 1M tokens | $0.18 | list $0.20 | 10% off | $0.09 | list $0.10 | 10% off | $0.09 | list $0.10 | 10% off | $0.36 | list $0.40 | 10% off | — | ||
| Cache write (5 min)per 1M tokens | $2.25 | list $2.50 | 10% off | $1.125 | list $1.25 | 10% off | $1.125 | list $1.25 | 10% off | $4.50 | list $5.00 | 10% off | — | ||
| Prompt > 272K tokens | |||||||||||||||
| Inputper 1M tokens | $3.60 | list $4.00 | 10% off | $1.80 | list $2.00 | 10% off | $1.80 | list $2.00 | 10% off | $7.20 | list $8.00 | 10% off | — | ||
| Outputper 1M tokens | $16.20 | list $18.00 | 10% off | $8.10 | list $9.00 | 10% off | $8.10 | list $9.00 | 10% off | $32.40 | list $36.00 | 10% off | — | ||
| Cache readper 1M tokens | $0.36 | list $0.40 | 10% off | $0.18 | list $0.20 | 10% off | $0.18 | list $0.20 | 10% off | $0.72 | list $0.80 | 10% off | — | ||
| Cache write (5 min)per 1M tokens | $4.50 | list $5.00 | 10% off | $2.25 | list $2.50 | 10% off | $2.25 | list $2.50 | 10% off | $9.00 | list $10.00 | 10% off | — | ||
| Web searchper request | — | — | — | — | $0.0126 | list $0.014 | 10% off | ||||||||
| Estimated cost of common use (500 output tokens each) | |||||||||||||||
| One chat message3K input tokens | $0.0108 | $0.0054 | — | $0.0216 | — | ||||||||||
| Agent first turn100K tokens of context, none cached | $0.23 | $0.115 | — | $0.461 | — | ||||||||||
| Each later agent turncontext read from cache, plus 2K new tokens | $0.0279 | $0.014 | — | $0.0558 | — | ||||||||||
| 20-turn agent taskfirst turn plus 19 more | $0.76 | $0.38 | — | $1.52 | — | ||||||||||
Try it
Runs on your balance and is billed like any API request.
Similar models
Other models with the same output types at a similar price.
Human preference ratings are from the LMArena Text Arena (CC BY 4.0, as of 2026-11-18): Elo ratings from blind votes, on a different scale from capability scores. lmarena.ai/leaderboard/text