GPT-6 Astra
-50% vs listOpenAI · 400K context · 128K max output. Half the vendor list price on Halfbill, through the same API you already use.
gpt-6-astraSpecifications
- Model id
- gpt-6-astra
- Vendor
- OpenAI
- Tier
- Standard
- Context window
- 400K tokens
- Max output
- 128K tokens
- Capabilities
- Streaming, Tool calls, Reasoning, Structured outputs, Prompt caching
- Endpoints
- /v1/chat/completions, /v1/responses, /v1/messages
Pricing
USD per 1M tokens, excl. VAT. Identical for API and chat.
| Tokens | List | Halfbill |
|---|---|---|
| Input | $10.00 | $5.00 |
| Output | $50.00 | $25.00 |
| Cached input | — | $0.50 |
List price is the vendor's published rate at the time the catalog was generated. Cached-input rates are not compared.
Call it
Both endpoint families, with this model id filled in. Set HALFBILL_API_KEY and run.
curl https://api.halfbill.uk/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $HALFBILL_API_KEY" \
-d '{
"model": "gpt-6-astra",
"messages": [{"role": "user", "content": "Say hello in one line."}]
}'Frequently asked questions
Is this the same GPT-6 Astra as OpenAI's?
Yes. Requests to "gpt-6-astra" are served by the same model. Halfbill is an independent service and is not affiliated with OpenAI; we bill at our own prices.
What does GPT-6 Astra cost on Halfbill?
$5.00 per 1M input tokens and $25.00 per 1M output tokens, 50% below the list price of $10.00 / $50.00. Cached input tokens cost $0.50 per 1M. USD, excl. VAT.
Which endpoints can I use?
The OpenAI-compatible /v1/chat/completions and /v1/responses endpoints and the Anthropic-compatible /v1/messages endpoint at https://api.halfbill.uk, with the model id "gpt-6-astra".
How large is the context window?
400K tokens of context and up to 128K output tokens per request, as listed in the catalog.
Does it work in Claude Code and Cursor?
Yes. Set ANTHROPIC_BASE_URL=https://api.halfbill.uk and ANTHROPIC_AUTH_TOKEN to your Halfbill key for Claude Code, or override the OpenAI base URL to https://api.halfbill.uk/v1 in Cursor and add "gpt-6-astra" as a custom model.
Other OpenAI models
GPT-5.6 Sol
- Vendor
- OpenAI
- Context
- 400K
- Max output
- 128K
- Streaming
- Tool calls
- Reasoning
- Structured outputs
- Prompt caching
GPT-5.6 Terra
- Vendor
- OpenAI
- Context
- 400K
- Max output
- 128K
- Streaming
- Tool calls
- Reasoning
- Structured outputs
- Prompt caching
GPT-5.5
- Vendor
- OpenAI
- Context
- 400K
- Max output
- 128K
- Streaming
- Tool calls
- Reasoning
- Structured outputs
- Prompt caching
Halfbill is an independent service and is not affiliated with, endorsed by, or sponsored by OpenAI or Anthropic. Model names are trademarks of their respective owners.