GPT-6.2 Astra API pricing

✓ Matches the official page (checked 2026-11-19 01:00 UTC) · Official pricing ↗Synced 2026-11-19 01:00 UTC · Method

GPT-6.2 Astra prices per 1M tokens
FieldPer 1M tokens
Input$8.00
Output$40.00
Cached input$0.40
Cache write$10.00
Batch input$4.00
Batch output$20.00
Batch cached input$0.20
Batch cache write$5.00
Input above 272K$16.00
Output above 272K$60.00
Long-context cached input (>272K)$0.80
Long-context cache write (>272K)$20.00
Long-context batch input (>272K)$8.00
Long-context batch output (>272K)$30.00
Long-context batch cached input (>272K)$0.40

Report a wrong price

OpenAI · Context window 1,050,000 · Max input 922,000 · Max output 128,000
vision · reasoning · tool calling · structured output
Per 1K tokens: $0.008 input, $0.04 output.

Calculate my cost →

Follow this price:
Atom feed ▾
AtomJSON

Get notified in any feed reader.

Billing rules for caching, Batch and long prompts: OpenAI API cost guide.

Price in context

GPT-6.2 Astra ranks 20 of 26 current OpenAI models by output price, cheapest first (GPT-6 Luna is the cheapest at $0.50, GPT-5.4 Pro the most expensive at $180.00). Output tokens cost 5× the input price; the median across all 119 current models is 5×. Against the whole table (median $1.25 input / $4.40 output per 1M), GPT-6.2 Astra is pricier on both input and output.

Cached input costs 5% of the normal input price ($0.40 vs $8.00 per 1M). In the support-chatbot scenario with 60% cache hits the month comes to $3,037 instead of $3,840 without caching (21% less). Writing a prefix to the cache costs 1.25× the input price ($10.00), so caching pays off once a prefix is reused 2 or more times. The Batch API bills $4.00 input / $20.00 output per 1M (50% below the live rates) for jobs that are not time-critical; the batch-processing scenario costs $13,500 per month. Prompts longer than 272K tokens switch to $16.00 input / $60.00 output per 1M (2× / 1.5×).

The context window is 1,050,000 tokens, roughly 2,100 pages of English text; 0% of current models accept more. The closest model from another provider by price is Claude Fable 5.2 ($8.00 / $40.00); the cheapest reasoning model for the chatbot scenario is MiMo V2.6 Flash at $27.18 per month against $3,037 for GPT-6.2 Astra.

What it costs per month

Estimated monthly cost by workload (USD)
Scenario (per month)GPT-6.2 Astra
Customer support chatbot
5,000 req/day · 1,200 in · 400 out · cache 60%
$3,037
RAG over documents
2,000 req/day · 8,000 in · 600 out · cache 30%
$4,234
Coding agent
1,500 req/day · 25,000 in · 2,000 out · cache 80%
$5,985
Deep reasoning
800 req/day · 3,000 in · 6,000 out · cache 20%
$6,227
Batch processing
50,000 req/day · 1,500 in · 150 out · batch
$13,500

Adjust the numbers in the calculator.

Cheaper alternatives

Lowest monthly cost for the chatbot scenario among reasoning models:

Comparisons

Other OpenAI models

GPT-6.2 Sol, GPT-6.1 Sol, GPT-6 Sol, GPT-6 Astra Law, GPT-6 Astra, GPT-5.6 Sol, GPT-5.6 Terra, GPT-5.5, GPT-5.5 Pro, GPT-5.4, GPT-5.4 Pro, GPT-5.3 Codex retiring 2027-04-01, GPT-5.2, GPT-5.2 Pro, GPT-5.1 retiring 2027-04-01, GPT-4.1 retiring 2027-01-14, GPT-4o retiring 2027-01-14, GPT-6.2 Astra Law, GPT-6.1 Terra, GPT-6 Luna, GPT-5.6 Luna, GPT-5.4 mini, GPT-5.4 nano retiring 2027-04-01, GPT-4.1 mini retiring 2027-01-14, GPT-4o mini retiring 2027-01-14 · All OpenAI API prices →

Models at a similar price

Claude Fable 5.2 ($8.00/$40.00), Claude Mythos 5.2 ($8.00/$40.00), GPT-6.2 Astra Law ($8.00/$40.00), GPT-6 Astra Law ($10.00/$50.00), GPT-6 Astra ($10.00/$50.00), Claude Fable 5.1 ($10.00/$50.00)

Price history

No price changes recorded since tracking began on 2026-10-08. See all price changes →

Other changes (1)

Listings, fields a source added or dropped, and limit changes. These are not price moves.

Recorded price changes, USD per 1M tokens
DateChangeOld /1MNew /1MWhat happened
2026-11-17Added———

Source and checks

Source and checks
Data sourceLiteLLM price list (MIT)
Official pricingdevelopers.openai.com ↗
Last synced2026-11-19 01:00 UTC
Last price changeNo price changes recorded since tracking began on 2026-10-08.
Cross-checkMatches models.dev
Official checkVerified against the official page on 2026-11-19 (automatic check)
Price regionNot confirmed by an official check
Field-by-field check against the official page
FieldThis siteOfficialStatus
Input$8.00$8.00✓ official
Output$40.00$40.00✓ official
Cached input$0.40$0.40✓ official
Cache write$10.00$10.00✓ official
Batch input$4.00$4.00✓ official
Batch output$20.00$20.00✓ official
Batch cached input$0.20—– unchecked
Batch cache write$5.00—– unchecked
Context window1,050,000—– unchecked
Max input922,000—– unchecked
Max output128,000—– unchecked

✓ official = the official page's value is in use (other sources' values noted) · ✓ verified = other source equals the official page · ≠ mismatch = differs and is held for confirmation; both shown · … pending = the automatic check could not read the page · – unchecked = not listed on the official page or not checked yet