- 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-6-astra API Pricing and Package Multipliers
GPT-6-astra
Model
gpt-6-astra GPT-6-astra API Pricing
Official base: Input 10 / Output 50 / Cache read 1 / Cache write 12.5
| Channel | SU8 price | Billing unit | Quota multiplier | Effective multiplier |
|---|---|---|---|---|
| Azure | Input $9.5 Output $47.5 Cache read $0.95 Cache write $11.875 | USD / 1M | 6.384x | 0.95x |
| Codex | Input $0.744 Output $3.7202 Cache read $0.0744 Cache write $0.9301 | 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-6-astra available packages and multipliers
| Package | Channel | SU8 price | Billing unit | Quota multiplier | Effective multiplier |
|---|---|---|---|---|---|
| Super Ultra | Azure | Input $8.9725 Output $44.8627 Cache read $0.8973 Cache write $11.2157 | USD / 1M | 63.479x | 0.8973x |
| Ultra | Azure | Input $9.1706 Output $45.853 Cache read $0.9171 Cache write $11.4632 | USD / 1M | 63.479x | 0.9171x |
| SU500 | Azure | Input $8.4639 Output $42.3193 Cache read $0.8464 Cache write $10.5798 | USD / 1M | 63.479x | 0.8464x |
| SU750 | Azure | Input $8.3525 Output $41.7625 Cache read $0.8353 Cache write $10.4406 | USD / 1M | 63.479x | 0.8353x |
| SU1000 | Azure | Input $8.4639 Output $42.3193 Cache read $0.8464 Cache write $10.5798 | USD / 1M | 63.479x | 0.8464x |
| Max | Azure | Input $11.0051 Output $55.0257 Cache read $1.1005 Cache write $13.7564 | USD / 1M | 63.479x | 1.1005x |
| Super Ultra | Codex | Input $0.3816 Output $1.9082 Cache read $0.0382 Cache write $0.477 | USD / 1M | 2.7x | 0.0382x |
| Lite | Codex | Input $0.6503 Output $3.2513 Cache read $0.065 Cache write $0.8128 | USD / 1M | 2.7x | 0.065x |
| Plus | Codex | Input $0.585 Output $2.925 Cache read $0.0585 Cache write $0.7313 | USD / 1M | 2.7x | 0.0585x |
| Pro | Codex | Input $0.546 Output $2.7302 Cache read $0.0546 Cache write $0.6826 | USD / 1M | 2.7x | 0.0546x |
| Max | Codex | Input $0.4681 Output $2.3405 Cache read $0.0468 Cache write $0.5851 | USD / 1M | 2.7x | 0.0468x |
| Ultra | Codex | Input $0.3901 Output $1.9503 Cache read $0.039 Cache write $0.4876 | USD / 1M | 2.7x | 0.039x |
| SU500 | Codex | Input $0.36 Output $1.8 Cache read $0.036 Cache write $0.45 | USD / 1M | 2.7x | 0.036x |
| SU750 | Codex | Input $0.3553 Output $1.7763 Cache read $0.0355 Cache write $0.4441 | USD / 1M | 2.7x | 0.0355x |
| SU1000 | Codex | Input $0.36 Output $1.8 Cache read $0.036 Cache write $0.45 | USD / 1M | 2.7x | 0.036x |
GPT-6-astra OpenAI-compatible API access
After creating a key in the console, call this model with the unified model name gpt-6-astra. When package and pay-as-you-go balance are both available, package quota is used first.
model: "gpt-6-astra"
- 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-5.3 Codex Spark
Lightweight Codex-oriented GPT model for quick code Q&A, small edits, and lower-cost development tasks.
GPT-5.4 Mini
OpenAI lightweight model balancing speed and cost for daily Q&A, batch jobs, and low-latency use cases.
GPT-5.5
OpenAI flagship model for complex reasoning, coding, architecture design, and demanding tasks.