GPT-6 Astra API Pricing
As of October 10, 2026, GPT-6 Astra costs $10.00 per 1M input tokens and $50.00 per 1M output tokens on OpenAI, with cache reads at $1.00 and cache writes at $12.50 per 1M tokens. Across 8 providers on LiteLLM, the input price ranges from $10.00 to $11.00. It has a 922,000-token context window and returns up to 128,000 tokens per response.
- Input
- $10.00 / 1M tokens
- Output
- $50.00 / 1M tokens
- Cache read
- $1.00 / 1M tokens
- Context window
- 922,000 tokens
- Max output
- 128,000 tokens
- Providers
- 8
- Added to LiteLLM
- September 3, 2026
GPT-6 Astra pricing by provider
12 listings across 8 providers. Token prices are in US dollars per 1M tokens. The highlighted row is the price quoted above.
| Provider | Model name in LiteLLM | Input | Output | Cache read | Cache write | Batch in | Batch out | Context |
|---|---|---|---|---|---|---|---|---|
| OpenAI | gpt-6-astra | $10.00 | $50.00 | $1.00 | $12.50 | $5.00 | $25.00 | 922K |
| Amazon Bedrock Mantle | bedrock_mantle/openai.gpt-6-astra | $11.00 | $55.00 | $1.10 | $13.75 | – | – | 1M |
| Azure AI Foundry | azure_ai/gpt-6-astra | $10.00 | $50.00 | $1.00 | $12.50 | – | – | 922K |
| Azure OpenAI | azure/gpt-6-astra | $10.00 | $50.00 | $1.00 | $12.50 | – | – | 922K |
| Azure OpenAIsnapshot 2026-09-03 | azure/gpt-6-astra-2026-09-03 | $10.00 | $50.00 | $1.00 | $12.50 | – | – | 922K |
| ChatGPT Subscription | chatgpt/gpt-6-astra | – | – | – | – | – | – | 922K |
| GitHub Copilot | github_copilot/gpt-6-astra | – | – | – | – | – | – | 272K |
| Perplexity | perplexity/openai/gpt-6-astra | $10.00 | $50.00 | $1.00 | $12.50 | – | – | – |
| Amazon BedrockGlobal cross-region | global.openai.gpt-6-astra | $10.00 | $50.00 | $1.00 | $12.50 | – | – | 1M |
| Amazon BedrockUS cross-region | us.openai.gpt-6-astra | $11.00 | $55.00 | $1.10 | $13.75 | – | – | 1M |
| Azure OpenAIeu | azure/eu/gpt-6-astra | $12.00 | $60.00 | $1.20 | $15.00 | – | – | 922K |
| Azure OpenAIus | azure/us/gpt-6-astra | $11.00 | $55.00 | $1.10 | $13.75 | – | – | 922K |
Other GPT-6 Astra prices on OpenAI
| Priority input | $20.00 per 1M tokens |
| Priority output | $100.00 per 1M tokens |
| Flex input | $5.00 per 1M tokens |
| Flex output | $25.00 per 1M tokens |
| Input above 272K tokens | $20.00 per 1M tokens |
| Output above 272K tokens | $75.00 per 1M tokens |
| Cache read above 272K tokens | $2.00 per 1M tokens |
| Web search | $10.00 per 1K searches |
What GPT-6 Astra costs in practice
1,000 requests with 2,000 input and 500 output tokens each
| OpenAI | $45.00 |
| Azure AI Foundry | $45.00 |
| Azure OpenAI | $45.00 |
| Perplexity | $45.00 |
| OpenAI batch | $22.50 |
100 long-document requests with 100,000 input and 2,000 output tokens each
| OpenAI | $110.00 |
| Azure AI Foundry | $110.00 |
| Azure OpenAI | $110.00 |
| Perplexity | $110.00 |
GPT-6 Astra features
Input: text, image. Output: text.
- Function calling
- Parallel tool calls
- Structured output
- Image input
- PDF input
- Reasoning
- Prompt caching
- Web search
- Computer use
Use GPT-6 Astra with LiteLLM
Call GPT-6 Astra through the LiteLLM Python SDK, or put it behind the LiteLLM proxy and send OpenAI-format requests to /v1/chat/completions. LiteLLM tracks the cost of every request at these prices.
from litellm import completion
response = completion(
model="gpt-6-astra",
messages=[{"role": "user", "content": "Hello!"}],
)model_list:
- model_name: gpt-6-astra
litellm_params:
model: gpt-6-astra
api_key: os.environ/OPENAI_API_KEYcurl http://0.0.0.0:4000/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer sk-1234" \
-d '{
"model": "gpt-6-astra",
"messages": [{"role": "user", "content": "Hello!"}]
}'GPT-6 Astra FAQ
How much does GPT-6 Astra cost?
GPT-6 Astra costs $10.00 per 1M input tokens and $50.00 per 1M output tokens on OpenAI, with cache reads at $1.00 and cache writes at $12.50 per 1M tokens. Batch requests cost $5.00 per 1M input tokens and $25.00 per 1M output tokens. Above 272K input tokens, input costs $20.00 and output costs $75.00 per 1M tokens. Across 8 providers on LiteLLM, the input price ranges from $10.00 to $11.00.
What is the context window of GPT-6 Astra?
GPT-6 Astra has a 922,000-token context window and returns up to 128,000 tokens per response.
Which providers offer GPT-6 Astra?
GPT-6 Astra is available from 8 providers through LiteLLM: OpenAI, Amazon Bedrock Mantle, Azure AI Foundry, Azure OpenAI, ChatGPT Subscription, GitHub Copilot, Perplexity and Amazon Bedrock. The lowest price is on OpenAI.
How do I call GPT-6 Astra with an OpenAI-compatible API?
Use the LiteLLM Python SDK with model="gpt-6-astra", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/chat/completions from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.
What features does GPT-6 Astra support?
GPT-6 Astra supports function calling, parallel tool calls, structured output, image input, PDF input, reasoning, prompt caching, web search and computer use.
When did LiteLLM add GPT-6 Astra?
GPT-6 Astra was added to LiteLLM's model price file on September 3, 2026.
Sources
Prices come from LiteLLM's open-source model_prices_and_context_window.json, which LiteLLM uses to calculate the cost of every request. Provider pricing pages:
- developers.openai.com/api/docs/pricing
- docs.aws.amazon.com/bedrock/latest/userguide/model-card-openai-gpt-6-astra.html
- ai.azure.com/catalog/models/gpt-6-astra
- prices.azure.com/api/retail/prices?$filter=serviceName%20eq%20'Foundry%20Models'%20and%20armRegionName%20eq%20'eastus'%20and%20priceType%20eq%20'Consumption'
LiteLLM docs: OpenAI, Amazon Bedrock Mantle, Azure AI Foundry, Azure OpenAI, ChatGPT Subscription, GitHub Copilot.
Provider pages: OpenAI, Amazon Bedrock Mantle, Azure AI Foundry, Azure OpenAI, ChatGPT Subscription, GitHub Copilot, Perplexity, Amazon Bedrock.
