Home/OpenAI/GPT-6.2 Astra
OpenAI pricing

GPT-6.2 Astra API Pricing & Cost Calculator

GPT-6.2 Astra is priced at $8.00 input / $40.00 output per 1M tokens, with a 922K context window and 128K max output. Cached input $0.40/1M. That is 20% cheaper per call than GPT-6 Astra ($10.00/$50.00). A 1,000-in / 500-out call costs $0.02800.

Listed automatically on 2026-11-18

Prices and limits come straight from the LiteLLM registry and are verified daily. The description is generated from those numbers and has not yet been reviewed by a person, so it may miss context about how this model relates to others in its family.

Input
$8.00
per 1M tokens
Output
$40.00
per 1M tokens
Context window
922K
tokens
Listed here
2026-11
✓ Exact tokenizer·$8.00 in·$40.00 out (per 1M)
Quick start with a use case
Total cost per call$0.0280
Input$0.008000
Output$0.0200
Cost comparison
Standard
$0.0280
With Caching
$0.0242
Save 14% ↓
With Batch
$0.0140
Save 50% ↓
Cutting costs? Open models start at $0.28/1M

DeepSeek, Kimi & 200+ open models on Novita AI — often 5–20x cheaper than proprietary APIs for comparable tasks.

Try Novita AI

Affiliate link — we may earn a commission at no extra cost to you.

Detailed pricing

GPT-6.2 Astra pricing breakdown

All pricing dimensions including caching and batch discounts.

TypePrice (per 1M tokens)
Input$8.0000
Output$40.0000
Cached input$0.4000
Cache write$10.0000
Batch input$4.0000
Batch output$20.0000
Cutting costs? Open models start at $0.28/1M

DeepSeek, Kimi & 200+ open models on Novita AI — often 5–20x cheaper than proprietary APIs for comparable tasks.

Try Novita AI

Affiliate link — we may earn a commission at no extra cost to you.

Last verified 2026-11-18 · OpenAI official pricing · ⚠️ Spotted a wrong price? Report in 30s →

How it compares

GPT-6.2 Astra vs alternatives

Single-call cost (1000 input + 500 output tokens) ranked from cheapest.

ModelPer call
GPT-6.2 Astra
OpenAI · this page
$0.0280
GPT-6 Luna
OpenAI
$0.000350
Claude Haiku 5.5
Anthropic
$0.000350
DeepSeek V3.2
DeepSeek
$0.000480
GPT-5.6 Luna
OpenAI
$0.000800
DeepSeek V4-Flash
DeepSeek
$0.000900
Recommended use

When to choose GPT-6.2 Astra

GPT-6.2 Astra shines for general-purpose tasks, complex multi-step reasoning, image and document understanding, and long documents and large codebases. Token counts on this page are exact via the official tokenizer.

✓Context window of 922K tokens handles long conversations and large documents.
✓Prompt caching available — significant savings for repeated system prompts.
✓Batch API support for non-realtime workloads at ~50% discount.
✓Tool / function calling supported.
FAQ

Frequently asked questions

GPT-6.2 Astra costs $8.00 per 1M input tokens and $40.00 per 1M output tokens. A typical chat call (1000 input + 500 output tokens) costs approximately $0.0280. Use the calculator above to estimate your specific use case.
GPT-6.2 Astra supports a 922K token context window with a max output of 128,000 tokens.
Yes. Cached input is priced at $0.40 per 1M tokens — 95% cheaper than uncached input. This is especially valuable for repeated system prompts, long-context retrieval, and chat threads with shared history.
Yes. GPT-6.2 Astra supports the Batch API at $4.00 input / $20.00 output per 1M tokens — typically 50% off standard pricing. Batch jobs complete within ~24 hours, ideal for non-realtime workloads like overnight data processing or content generation pipelines.
Yes, GPT-6.2 Astra accepts image input. Vision token pricing is generally calculated based on image dimensions and folded into the input token count. Specific image-specific pricing varies — refer to OpenAI's official documentation.
Token counts for GPT-6.2 Astra use the official o200k_base tokenizer (exact). Cost calculations use the prices verified on 2026-11-18. For final billing accuracy, always verify with OpenAI's usage dashboard.
GPT-6.2 Astra does not currently support fine-tuning. Consider another model in the OpenAI family if fine-tuning is required.