GPT-6 Astra

openai/gpt-6-astra is OpenAI's most capable model, built for end-to-end work that runs long: hard reasoning, agentic coding, computer use, research, and document production.

Model	Context	Output	Inputs
openai/gpt-6-astra	1,050,000	128,000	Text, image, PDF

Audio input is not supported; a request carrying audio is refused upstream.

Pricing

Prices are per million tokens and are OpenAI's list rates. No margin is added to model prices.

Model	Input / Cache read / Output ($/1M)
openai/gpt-6-astra	10.00 / 1.00 / 50.00

Cache writes are billed separately

This model charges for prompt cache writes. That is true of the whole GPT-6 family, Sol and Luna included; on GPT-5.6 and earlier OpenAI models, writing to the cache is free.

Metric	Standard	Requests above 272K tokens
Input	10.00	20.00
Cache read	1.00	2.00
Cache write	12.50	25.00
Output	50.00	75.00

The cache-write rate is 1.25x the input rate. Cache-write tokens are a subset of input tokens, not an addition to them: on a cold request the cacheable prefix of the prompt is written to the cache, and that portion bills at the cache-write rate instead of the input rate. On a second request with the same prefix those same tokens move to the cache-read rate, one tenth of input.

In practice this means an agent loop that resends the same system prompt pays roughly 25% more on its first call and roughly 90% less on every call after it. Cache writes and cache reads appear as separate line items in your usage records.

When a request's input exceeds 272,000 tokens, the entire request is billed from the long-context column above: input and cache rates double, and the output rate rises by half.

The free card is closed

openai/gpt-6-astra-free served the same model free of charge. LLMTR stopped offering it on 7 September 2026, and the identifier no longer accepts requests.

Closed on 7 September 2026

Requests to openai/gpt-6-astra-free return 410 model_retired, and the error names openai/gpt-6-astra as the model to use instead.

Nothing is forwarded to the metered row and nothing is charged without your knowledge: changing the model id is your decision, and until you make it no request is billed.

This card had previously announced 10 September 2026 as its closing date. The closure was brought forward by three days.

The model itself is unaffected: openai/gpt-6-astra serves it with a wider context window, PDF input, no enforced output ceiling, and the Responses endpoint in addition to chat completions. Its page section above covers pricing and usage.

The free card's page stays online as a reference with the same details, so an existing link does not break.

Text request

curl "$LLMTR_BASE_URL/v1/responses" \
  -H "Authorization: Bearer llmtr-your_key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-6-astra",
    "input": "List the irreversible steps in this migration plan.",
    "max_output_tokens": 1024
  }'

The same model can be called through /v1/chat/completions; the gateway translates the request into the Responses format and returns the answer in OpenAI chat format.

curl "$LLMTR_BASE_URL/v1/chat/completions" \
  -H "Authorization: Bearer llmtr-your_key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-6-astra",
    "messages": [
      { "role": "user", "content": "List the irreversible steps in this migration plan." }
    ],
    "max_tokens": 1024
  }'

Reasoning effort levels

The model accepts five levels: low, medium, high, xhigh, and max. none and minimal are not accepted; sending either returns 400.

{
  "model": "openai/gpt-6-astra",
  "reasoning_effort": "max",
  "input": "Explain why this race condition only shows up under load.",
  "max_output_tokens": 4096
}

The level can be set three ways, in priority order reasoning_effort > reasoning.effort > slug suffix. See Reasoning Effort for details.

On this model the :max suffix resolves to a real max level rather than falling back to xhigh:

openai/gpt-6-astra:max     -> reasoning effort = max
openai/gpt-6-astra:xhigh   -> reasoning effort = xhigh

Higher levels spend more reasoning tokens, and those tokens bill at the output rate. At max, a low max_output_tokens can be consumed entirely by reasoning, leaving the answer text empty.

Sampling parameters

temperature and top_p are not supported on this model. Rather than rejecting the request, the gateway removes these fields and reports which ones were dropped, so clients that send them by default keep working.

Image and document input

Images and PDFs are sent in the content array:

{
  "model": "openai/gpt-6-astra",
  "input": [
    {
      "role": "user",
      "content": [
        { "type": "input_text", "text": "Find the inconsistencies in this table." },
        { "type": "input_image", "image_url": "data:image/png;base64,..." }
      ]
    }
  ],
  "max_output_tokens": 2048
}

Image tokens bill at the input rate.

Tool calling and structured output

Function calling, parallel calls, tool_choice: "required", and json_schema with strict: true are all supported. See Tool Calling for the shared request format.

Streaming

The model supports streaming. The final frame of the stream carries the complete usage block, so streamed requests are billed from real token counts as well. See Streaming.

GPT-6 Astra free plan: what changed in September 2026

The free openai/gpt-6-astra-free card closed on 7 September 2026, three days before its announced 10 September date; requests now return an error naming openai/gpt-6-astra, with no automatic switch and no charge to the account. The same model remains available through metered openai/gpt-6-astra at $10 input, $50 output, and $1 cache read per 1M tokens, with a 1,050,000-token context on the chat completions and Responses endpoints.