GPT-6.2 Astra API Pricing
- Input / output
- $8.00 / $40.00 per 1M tokens
- Cache read
- $0.40 / 1M
- Context
- 922K tokens
- Max output
- 128K tokens
As of November 17, 2026, GPT-6.2 Astra costs $8.00 per 1M input tokens and $40.00 per 1M output tokens on OpenAI, with cache reads at $0.40 and cache writes at $10.00 per 1M tokens. Across 4 providers on LiteLLM, the input price ranges from $8.00 to $9.60. It has a 922,000-token context window and returns up to 128,000 tokens per response.
GPT-6.2 Astra pricing by provider
9 listings across 4 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-6.2-astra | $8.00 | $40.00 | $0.40 | $10.00 | $4.00 | $20.00 | 922K |
| Amazon Bedrock | openai.gpt-6.2-astra | $8.00 | $40.00 | $0.40 | $10.00 | – | – | 922K |
| Azure OpenAI | azure/gpt-6.2-astra | $8.00 | $40.00 | $0.40 | $10.00 | – | – | 922K |
| ChatGPT Subscription | chatgpt/gpt-6.2-astra | – | – | – | – | – | – | 922K |
| Amazon BedrockGlobal cross-region | global.openai.gpt-6.2-astra | $8.00 | $40.00 | $0.40 | $10.00 | – | – | 922K |
| Amazon BedrockUS cross-region | us.openai.gpt-6.2-astra | $8.80 | $44.00 | $0.44 | $11.00 | – | – | 922K |
| Azure OpenAIapac | azure/apac/gpt-6.2-astra | $9.60 | $48.00 | $0.48 | $12.00 | – | – | 922K |
| Azure OpenAIeu | azure/eu/gpt-6.2-astra | $9.60 | $48.00 | $0.48 | $12.00 | – | – | 922K |
| Azure OpenAIus | azure/us/gpt-6.2-astra | $8.80 | $44.00 | $0.44 | $11.00 | – | – | 922K |
Other GPT-6.2 Astra prices on OpenAI
| Priority input | $16.00 per 1M tokens |
| Priority output | $80.00 per 1M tokens |
| Input above 272K tokens | $16.00 per 1M tokens |
| Output above 272K tokens | $60.00 per 1M tokens |
| Cache read above 272K tokens | $0.80 per 1M tokens |
| Web search | $10.00 per 1K searches |
What GPT-6.2 Astra costs in practice
1,000 requests with 2,000 input and 500 output tokens each
| OpenAI | $36.00 |
| Amazon Bedrock | $36.00 |
| Azure OpenAI | $36.00 |
| OpenAI batch | $18.00 |
100 long-document requests with 100,000 input and 2,000 output tokens each
| OpenAI | $88.00 |
| Amazon Bedrock | $88.00 |
| Azure OpenAI | $88.00 |
GPT-6.2 Astra cost calculator
At OpenAI's price ($8.00 input, $40.00 output per 1M tokens), 10,000 requests a day with 1,000 input and 500 output tokens each cost $280 a day, about $8,400 a month. Change the numbers for your workload, or compare it with other models.
- Per request
- $0.028
- Per day
- $280
- Per month (30 days)
- $8,400
GPT-6.2 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-6.2 Astra with LiteLLM
Call GPT-6.2 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-6.2-astra",
messages=[{"role": "user", "content": "Hello!"}],
)model_list:
- model_name: gpt-6.2-astra
litellm_params:
model: gpt-6.2-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 $LITELLM_API_KEY" \
-d '{
"model": "gpt-6.2-astra",
"messages": [{"role": "user", "content": "Hello!"}]
}'GPT-6.2 Astra FAQ
How much does GPT-6.2 Astra cost?
GPT-6.2 Astra costs $8.00 per 1M input tokens and $40.00 per 1M output tokens on OpenAI, with cache reads at $0.40 and cache writes at $10.00 per 1M tokens. Batch requests cost $4.00 per 1M input tokens and $20.00 per 1M output tokens. Above 272K input tokens, input costs $16.00 and output costs $60.00 per 1M tokens. Across 4 providers on LiteLLM, the input price ranges from $8.00 to $9.60.
What is the context window of GPT-6.2 Astra?
GPT-6.2 Astra has a 922,000-token context window and returns up to 128,000 tokens per response.
Which providers offer GPT-6.2 Astra?
GPT-6.2 Astra is available from 4 providers through LiteLLM: OpenAI, Amazon Bedrock, Azure OpenAI and ChatGPT Subscription. The lowest price is on OpenAI.
How do I call GPT-6.2 Astra with an OpenAI-compatible API?
Use the LiteLLM Python SDK with model="gpt-6.2-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-6.2 Astra support?
GPT-6.2 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-6.2 Astra?
GPT-6.2 Astra was added to LiteLLM's model price file on November 17, 2026.
Compare GPT-6.2 Astra
Sources
Prices come from LiteLLM's open-source model_prices_and_context_window.json, which LiteLLM uses to calculate the cost of every request. Maintainers update it from each provider's published pricing, and this page is usually rebuilt within 20 minutes of every change. Provider pricing pages:
- developers.openai.com/api/docs/pricing
- techcommunity.microsoft.com/t5/microsoft-foundry-blog/gpt-6-2-astra-and-gpt-6-2-sol-now-generally-available-in/ba-p/4574122
LiteLLM docs: OpenAI, Amazon Bedrock, Azure OpenAI, ChatGPT Subscription.
Provider pages: OpenAI, Amazon Bedrock, Azure OpenAI, ChatGPT Subscription.