OpenAI · Model
GPT-6.2 Astra API pricing, cost and context window
GPT-6.2 Astra costs $8 per million input tokens and $40 per million output tokens, rising to $16 and $60 once a prompt passes 272,000 tokens. Cached input costs $0.40. It reads up to 1,050,000 tokens and writes up to 128,000 per reply. Prices checked 2026-11-22. By blended price it is number 10 of OpenAI’s 11 current models here, counting from the cheapest.
- Input / 1M
- $8
- Output / 1M
- $40
- Cached / 1M
- $0.40
- Context
- 1,050,000
- Max output
- 128,000
- Released
- 2026-11-17
Estimate your cost with GPT-6.2 AstraCompare all OpenAI modelsCount tokens for GPT-6.2 Astra
Pricing
How much does GPT-6.2 Astra cost per million tokens?
| Price per 1M tokens | Input | Output |
|---|---|---|
| Standard | $8 | $40 |
| Cached input (read) | $0.40 | – |
| Cache write | $10 | – |
| Batch API | $4 | $20 |
| Prompts of 272,000+ tokens | $16 | $60 |
Output costs 5.0× the input price, so long replies drive the bill more than long prompts. If your requests share a long fixed prefix, such as a system prompt or tool definitions, caching cuts that part to 5% of the normal input price. Once a single prompt reaches 272,000 tokens, the whole request is billed at the higher long-context rate shown above.
Work out your monthly GPT-6.2 Astra bill in the cost calculatorSee what prompt caching savesSee what the Batch API saves
Examples
How much does a typical GPT-6.2 Astra request cost?
| Workload | Tokens in / out | Requests/day | Per request | Per month |
|---|---|---|---|---|
| Support chatbot50% cached | 1,500 / 400 | 1,000 | $0.0223 | $678.29 |
| RAG app20% cached | 6,000 / 500 | 500 | $0.0589 | $895.47 |
| Coding agent80% cached | 40,000 / 2,000 | 200 | $0.16 | $953.87 |
| Document summariserbatch | 8,000 / 600 | 300 | $0.044 | $401.50 |
Change any number in the cost calculator.
Context
What is GPT-6.2 Astra’s context window and max output?
GPT-6.2 Astra accepts up to 1,050,000 tokens per request, roughly 787,500 English words or 1,575 pages. That budget is shared between your prompt and the reply, and a single reply is capped at 128,000 tokens.
Filling the whole window with one prompt costs about $16.80 at list price, so for repeated long-document work, retrieval (sending only the relevant parts) or prompt caching is usually much cheaper.
Features
What can GPT-6.2 Astra do?
- Image input
- Yes
- Tool / function calling
- Yes
- Reasoning mode
- Yes
- Prompt caching
- Yes
- Structured output
- Yes
- Open weights
- No
- Accepts
- file, image, text
- Knowledge cutoff
- Not published
As declared by the provider’s API. It shows a feature exists, not how well it works.
API
What is the GPT-6.2 Astra API model ID?
- OpenRouter
openai/gpt-6.2-astra
Use the OpenRouter ID when calling it through OpenRouter; OpenAI’s own API may name it differently. See the model ID reference for the providers we document.
OpenAI
Where does GPT-6.2 Astra sit in OpenAI’s line-up?
Ranked by blended price (three parts input to one part output, $16 per 1M for GPT-6.2 Astra), it is number 10 of OpenAI’s 11 current models here, counting from the cheapest. One step down, GPT-5.5 costs $11.25 blended (30% less). It has the same published limits and features as GPT-6.2 Astra. One step up, GPT-5.5 Pro costs $67.50 (4.2× as much). It has the same published limits and features as GPT-6.2 Astra. See every OpenAI model and price
| Model | Input / 1M | Output / 1M | Context | Released |
|---|---|---|---|---|
| gpt-oss-120b | $0.09 | $0.36 | 131,072 | 2025-08-05 |
| GPT-6 Luna | $0.10 | $0.50 | 1,050,000 | 2026-09-22 |
| GPT-4o-mini | $0.15 | $0.60 | 128,000 | 2024-07-18 |
| GPT-5.4 Mini | $0.75 | $4.50 | 400,000 | 2026-03-17 |
| GPT-6.1 Terra | $1 | $5 | 1,050,000 | 2026-10-26 |
| GPT-6.1 Sol | $2 | $10 | 1,050,000 | 2026-09-29 |
| GPT-6.2 Sol | $2 | $10 | 1,050,000 | 2026-11-17 |
| GPT-4o | $2.50 | $10 | 128,000 | 2024-05-13 |
| GPT-5.5 | $5 | $30 | 1,050,000 | 2026-04-24 |
| GPT-6.2 Astra (this page) | $8 | $40 | 1,050,000 | 2026-11-17 |
| GPT-5.5 Pro | $30 | $180 | 1,050,000 | 2026-04-24 |
OpenAI’s current models with a page here, cheapest first. Older and superseded models are listed on the provider page and in the comparison table.
History
Is GPT-6.2 Astra cheaper than GPT-6 Astra?
The previous model in this line is GPT-6 Astra, first listed on 2026-09-04. Compared with it, GPT-6.2 Astra’s input price is 20% lower and its output price is 20% lower.
| Model | Input / 1M | Output / 1M | Context | Released |
|---|---|---|---|---|
| GPT-6 Astra | $10 | $50 | 1,050,000 | 2026-09-04 |
Earlier releases with the same name and size in our data, newest first. Dates are when our source first listed each model.
Save
What are cheaper alternatives to GPT-6.2 Astra?
- Gemini 3.8 FlashGoogle90% cheaper
- GPT-5.4 MiniOpenAI89% cheaper
- GLM 5V TurboZ.ai88% cheaper
- Qwen4 MaxQwen87% cheaper
- Claude Sonnet 5.5Anthropic75% cheaper
Current models from major providers, one per provider, that keep image input, tool calling, a reasoning mode, a usable context window and output limit. Compared by blended price.
Compare
Which models cost about the same?
- Claude Fable 5.2Anthropic$8 / $40
- Muse WonderMeta$4 / $20
- Gemini 4 NeonGoogle$3 / $15
- Qwen3.8 Max PrimeQwen$4 / $12
- Kimi K3Moonshot AI$3 / $15
Current models from other major providers, closest blended price.
FAQ
GPT-6.2 Astra questions
How much does GPT-6.2 Astra cost?
GPT-6.2 Astra costs $8 per million input tokens and $40 per million output tokens, with cached input at $0.40. A typical chatbot reply (1,500 tokens in, 400 out) costs about $0.028. Use the LLM cost calculator for your own workload.
What is GPT-6.2 Astra’s context window?
1,050,000 tokens, about 787,500 English words or 1,575 printed pages, shared between your prompt and the reply. A single reply can be up to 128,000 tokens.
Does GPT-6.2 Astra support prompt caching and batch requests?
Yes, cached input is billed at $0.40 per million tokens (5% of the normal input price), and writing a prompt to the cache costs $10 per million tokens. A batch API is available at $4 input and $20 output per million tokens.
What are cheaper alternatives to GPT-6.2 Astra?
With the same essentials (image input and tool calling), the cheapest options are Gemini 3.8 Flash (90% cheaper), GPT-5.4 Mini (89% cheaper), GLM 5V Turbo (88% cheaper). Cheaper doesn’t mean equivalent, so test them on your own prompts.
What is the API model ID for GPT-6.2 Astra?
On OpenRouter it is openai/gpt-6.2-astra. OpenAI’s own API may use a different name, so check its model list before you deploy. Pass the ID as the model value in each request.
When was GPT-6.2 Astra released?
GPT-6.2 Astra was first listed on 2026-11-17. It follows GPT-6 Astra, first listed on 2026-09-04. Release dates here are when our price source first listed each model.
Is GPT-6.2 Astra cheaper than GPT-6 Astra?
The previous OpenAI model in the same line is GPT-6 Astra, first listed on 2026-09-04. Compared with it, GPT-6.2 Astra’s input price is 20% lower and its output price is 20% lower. Prices are only part of the picture, so test the newer model on your own prompts before switching.
Is GPT-6.2 Astra open source?
No, GPT-6.2 Astra is only available through OpenAI’s API and partners; its weights aren’t published.
Keep exploring