GPT-6 Astra
everyais/gpt-6-astra
GPT-6 Astra (everyais/gpt-6-astra) availability, capabilities, context limits, and public reference pricing on everyais.
Method
The page starts with current public catalog metadata and reference costs; operational metrics are added only when measured samples are available.
Source and update
GET /models/catalogUpdated
- Model type
- Chat
- Released
- 2026-09-08
- Context window
- 8K
- Price unit
- Per 1M tokens
- Maximum output
- 4,096
- Model reference price (USD)
Standard (≤272K)
- Input / 1M tokens
- $10
- Output / 1M tokens
- $50
- Cache read / 1M tokens
- $1
- Cache write / 1M tokens
- $12.5
Long context (>272K, full request)
- Input / 1M tokens
- $20
- Output / 1M tokens
- $75
- Cache read / 1M tokens
- $2
Capabilities
- ✓ Streaming
- ✓ Tool use
- ✓ JSON
- ✓ Reasoning
- ✓ Structured outputs
- ✓ Parallel tools
Supported endpoints
- /v1/chat/completions
Benchmarks
Evaluation results published by external sources. Only mappings approved by a human administrator are shown.
| Benchmark | Score | Source |
|---|---|---|
| eci | 169.23 (source-specific scale) | Epoch AI Benchmarking HubCC-BY |
Scores are reproduced as published; everyais does not re-measure them. Scores using different units cannot be compared. See benchmark sources and licenses.
Code example
Use the OpenAI SDK by changing only base_url.
from openai import OpenAI
client = OpenAI(
api_key="everyais_...",
base_url="https://api.everyais.com/v1",
)
response = client.chat.completions.create(
model="everyais/gpt-6-astra",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Compare models side by side
Compare capabilities, context windows, and reference prices to find a model for your use case. Your actual billed rate can differ by account.