# GPT-6 Astra API

GPT-6 Astra is OpenAI's flagship model for demanding work, with text and image input, a 1.05M-token context window (922K maximum input) and up to 128K output tokens; list price $10.00 in / $50.00 out per 1M tokens, provider list as at 1 November 2026.

- Provider: OpenAI
- Model ID: gpt-6-astra
- Type: Chat
- Region: Global (provider global routing)
- Context window: 1,050,000 tokens
- Max output: 128,000 tokens
- Modalities: text, vision, tools, reasoning
- Endpoints: OpenAI Chat Completions https://api.seedrise.ai/v1
- Prices checked: 1 November 2026

## Provider list price

Provider list price as at 1 November 2026, per 1M tokens. AUD at a reference rate of 1 USD = 1.53 AUD; invoices use the rate on the day.

| Token type | USD | AUD |
|---|---:|---:|
| Input | 10.00 | 15.30 |
| Output | 50.00 | 76.50 |
| Cached input | 1.00 | 1.53 |

Your Seedrise rate is quoted per account against this list price. Request a rate card: https://seedrise.ai/contact?model=gpt-6-astra

Global: runs on the provider's global routing; no Australian-region option as at 1 November 2026. Prompts over 272K input tokens are billed by OpenAI at $20.00 in / $75.00 out and $2.00 cached per 1M tokens for the whole request.

## Strengths

- Reasoning effort from low up to max, set per request
- 922K-token maximum input with up to 128K output tokens
- Function calling and structured outputs
- Knowledge cutoff of 30 April 2026

## Typical use cases

- Complex analysis and planning where accuracy outweighs cost
- Long-document review and synthesis
- Hard coding and debugging tasks
- Quality baselines for evaluating lower-cost models

## Quickstart

A first request with curl. Replace sk-... with your Seedrise key.

```bash
curl https://api.seedrise.ai/v1/chat/completions \
  -H "Authorization: Bearer sk-..." \
  -H "Content-Type: application/json" \
  -d '{"model":"gpt-6-astra","messages":[{"role":"user","content":"Hello"}]}'
```

OpenAI SDK, Python:

```python
from openai import OpenAI

client = OpenAI(base_url="https://api.seedrise.ai/v1", api_key="sk-...")

r = client.chat.completions.create(
    model="gpt-6-astra",
    messages=[{"role": "user", "content": "Summarise this contract in three bullets."}],
)
print(r.choices[0].message.content)
```

## Where it runs

Global: Served on the provider's global routing.

## Related models

- [GPT-6.1 Sol](https://seedrise.ai/models/gpt-6.1-sol): US$2.00 input · US$10.00 output per 1M tokens, Global
- [GPT-6.1 Terra](https://seedrise.ai/models/gpt-6.1-terra): US$1.00 input · US$5.00 output per 1M tokens, Global
- [GPT-6 Luna](https://seedrise.ai/models/gpt-6-luna): US$0.10 input · US$0.50 output per 1M tokens, Global
- [GPT Image 2.5](https://seedrise.ai/models/gpt-image-2.5): US$30.00 per 1M image output tokens, Global
- [Claude Fable 5.1](https://seedrise.ai/models/claude-fable-5-1): US$10.00 input · US$50.00 output per 1M tokens, Global
- [Claude Opus 5.5](https://seedrise.ai/models/claude-opus-5-5): US$4.00 input · US$20.00 output per 1M tokens, AU
- [Claude Sonnet 5.5](https://seedrise.ai/models/claude-sonnet-5-5): US$2.00 input · US$10.00 output per 1M tokens, AU

## FAQ

### What is the model ID for GPT-6 Astra?

Use gpt-6-astra as the model field, with no vendor prefix, on the OpenAI-compatible endpoint at https://api.seedrise.ai/v1. GET /v1/models returns the IDs your key can call.

### How does the Seedrise rate for GPT-6 Astra compare to the list price?

OpenAI's list price as at 1 November 2026 is US$10.00 per 1M input tokens and US$50.00 per 1M output tokens. Seedrise quotes rates per account against the provider's published list price for the same routing. Volume and committed tiers sit below list.

### What is the context window and max output of GPT-6 Astra?

GPT-6 Astra has a context window of 1,050,000 tokens and a maximum output of 128,000 tokens, per the provider documentation checked on 1 November 2026.

### Can GPT-6 Astra run in Australia?

Not at present. GPT-6 Astra is served on the provider's global routing. Models marked AU in the model library can be pinned to Sydney or Melbourne on request.

### Can I turn reasoning off on GPT-6 Astra?

No. OpenAI lists low, medium, high, xhigh and max as its effort levels, so low is the lightest setting. For calls without reasoning, GPT-6.1 Terra and GPT-6 Luna accept an effort of none.

### What does a prompt over 272K tokens cost on GPT-6 Astra?

OpenAI bills the whole request at the long-context rate: $20.00 in / $75.00 out and $2.00 cached per 1M tokens at list as at 1 November 2026, against $10.00 / $50.00 for shorter prompts.

Model names are trademarks of their respective providers.

Source: https://seedrise.ai/models/gpt-6-astra