- Good as a general-purpose model for text generation and everyday reasoning.
- Good when you want package quota first, with pay-as-you-go enabled by key configuration.
OpenAI active
GPT-5.6 Terra API Pricing and Package Multipliers
Balanced GPT-5.6 model for high-quality agent and long-context workloads.
Model
gpt-5.6-terra chat.completionsresponses
GPT-5.6 Terra API Pricing
Official base: Input 2 / Output 12 / Cache read 0.2 / Cache write 2.5
| Channel | SU8 price | Billing unit | Quota multiplier | Effective multiplier |
|---|---|---|---|---|
| Azure | Input $1.9 Output $11.4 Cache read $0.19 Cache write $2.375 | USD / 1M | 6.384x | 0.95x |
| Codex | Input $0.1488 Output $0.8929 Cache read $0.0149 Cache write $0.186 | USD / 1M | 0.5x | 0.0744x |
Cache hits are billed at the cache read price. Cache writes use the cache write price, and the Console usage detail shows the final cost breakdown.
GPT-5.6 Terra available packages and multipliers
| Package | Channel | SU8 price | Billing unit | Quota multiplier | Effective multiplier |
|---|---|---|---|---|---|
| Super Ultra | Azure | Input $1.7945 Output $10.7671 Cache read $0.1795 Cache write $2.2431 | USD / 1M | 63.479x | 0.8973x |
| Ultra | Azure | Input $1.8341 Output $11.0047 Cache read $0.1834 Cache write $2.2926 | USD / 1M | 63.479x | 0.9171x |
| SU500 | Azure | Input $1.6928 Output $10.1566 Cache read $0.1693 Cache write $2.116 | USD / 1M | 63.479x | 0.8464x |
| SU750 | Azure | Input $1.6705 Output $10.023 Cache read $0.1671 Cache write $2.0881 | USD / 1M | 63.479x | 0.8353x |
| SU1000 | Azure | Input $1.6928 Output $10.1566 Cache read $0.1693 Cache write $2.116 | USD / 1M | 63.479x | 0.8464x |
| Max | Azure | Input $2.201 Output $13.2062 Cache read $0.2201 Cache write $2.7513 | USD / 1M | 63.479x | 1.1005x |
| Super Ultra | Codex | Input $0.0424 Output $0.2544 Cache read $0.0042 Cache write $0.053 | USD / 1M | 1.5x | 0.0212x |
| Lite | Codex | Input $0.0723 Output $0.4335 Cache read $0.0072 Cache write $0.0903 | USD / 1M | 1.5x | 0.0361x |
| Plus | Codex | Input $0.065 Output $0.39 Cache read $0.0065 Cache write $0.0813 | USD / 1M | 1.5x | 0.0325x |
| Pro | Codex | Input $0.0607 Output $0.364 Cache read $0.0061 Cache write $0.0758 | USD / 1M | 1.5x | 0.0303x |
| Max | Codex | Input $0.052 Output $0.3121 Cache read $0.0052 Cache write $0.065 | USD / 1M | 1.5x | 0.026x |
| Ultra | Codex | Input $0.0433 Output $0.26 Cache read $0.0043 Cache write $0.0542 | USD / 1M | 1.5x | 0.0217x |
| SU500 | Codex | Input $0.04 Output $0.24 Cache read $0.004 Cache write $0.05 | USD / 1M | 1.5x | 0.02x |
| SU750 | Codex | Input $0.0395 Output $0.2368 Cache read $0.0039 Cache write $0.0493 | USD / 1M | 1.5x | 0.0197x |
| SU1000 | Codex | Input $0.04 Output $0.24 Cache read $0.004 Cache write $0.05 | USD / 1M | 1.5x | 0.02x |
GPT-5.6 Terra OpenAI-compatible API access
After creating a key in the console, call this model with the unified model name gpt-5.6-terra. When package and pay-as-you-go balance are both available, package quota is used first.
model: "gpt-5.6-terra"
- Not ideal for legacy integrations that only accept OpenAI-compatible APIs.
- Not ideal when you need dedicated SLA terms, private capacity, or a fixed-cost enterprise commitment.
This model is available through the public catalog and unified gateway pricing configuration.
Open this model in the console
The public model page is for discovery and comparison. Actual API access, key creation, and model scopes are managed after sign-in.
Models worth comparing
GPT-5.6 Luna
Efficient GPT-5.6 model for cost-sensitive agent and long-context workloads.
GPT-5.6 Sol
GPT-5.6 flagship model for frontier reasoning, coding agents, and long-context production workloads.
GPT-5.3 Codex Spark
Lightweight Codex-oriented GPT model for quick code Q&A, small edits, and lower-cost development tasks.