Skip to content
Sovyron

GPT-6.2 Astra

gpt-astra1.1M context128k max outputreleased Nov 17, 2026ReasoningTool calling2 subscription plans →

As of Nov 22, 2026, the cheapest GPT-6.2 Astra API price is $8 per 1M input tokens (Amazon Bedrock) and $40 per 1M output tokens (Amazon Bedrock). GPT-6.2 Astra is offered by 26 providers in the gpt-astra family, reasoning enabled. OpenAI's own rate is $40 per 1M output tokens. It is also included in 2 flat-rate subscription plans, GitHub Copilot Pro from $10/mo.

Cheapest input
$8
Cheapest output
$40
Official (OpenAI)
$40
output per 1M tokens
Providers
26
offering this model
Spread
1.2×
max / min output
Free offers
0
free-tier offers

API pricing by provider

Metered per-token prices. Cheapest input and output are highlighted; † marks a context-tier surcharge. How prices are ranked. Seeing a wide range? Why the same LLM costs different amounts.

GPT-6.2 Astra API prices by provider in USD per 1M tokens, updated Nov 22, 2026
Amazon Bedrockglobalglobal.openai.gpt-6.2-astraCheapest†$8Cheapest$40$0.4$101.1M—
Azuregpt-6.2-astra†$8$40$0.4$101.1M—
Azure Cognitive Servicesgpt-6.2-astra†$8$40$0.4$101.1M—
Cloudflare AI Gatewayopenai/gpt-6.2-astra†$8$40$0.4$101.1M—
CrossModelopenai/gpt-6.2-astra†$8$40$0.4$101.1M—
DigitalOceanopenai-gpt-6.2-astra†$8$40$0.4—1.1M—
Eden AIopenai/gpt-6.2-astra†$8$40$0.4$101.1M—
Kilo Gatewayopenai/gpt-6.2-astra$8$40$0.4$101.1M3d agoout −33.3%
DevPass (LLM Gateway)gpt-6.2-astra$8$40$0.4$101.1M—
LLM Gatewayazure/gpt-6.2-astra$8$40$0.4$101.1M—
LLM Gatewayopenai/gpt-6.2-astra$8$40$0.4$101.1M—
Merge Gatewayopenai/gpt-6.2-astra†$8$40$0.4$101.1M—
NanoGPTopenai/gpt-6.2-astra$8$40$0.4$10922k—
NEAR AI Cloudopenai/gpt-6.2-astra$8$40$0.4—1.1M—
Novita AIopenai/gpt-6.2-astra†$8$40$0.4—1.1M—
Ofoxopenai/gpt-6.2-astra†$8$40$0.4$101.1M—
OpenAIgpt-6.2-astra†$8$40$0.4$101.1M—
OpenCodegpt-6.2-astra†$8$40$0.4$101.1M—
OpenRouteropenai/gpt-6.2-astra†$8$40$0.4$101.1M—
Prime Inferenceopenai/gpt-6.2-astra$8$40——1.1M—
Requestygpt-6.2-astra†$8$40$0.4$101.1M—
Venice AIopenai-gpt-62-astra†$8$40$0.4$101.1M—
Vercel AI Gatewayopenai/gpt-6.2-astra†$8$40$0.4$101.1M—
Amazon Bedrockopenai.gpt-6.2-astra†$8.8$44$0.44$111.1M—
Amazon Bedrockusus.openai.gpt-6.2-astra†$8.8$44$0.44$111.1M—
Vivgridgpt-6.2-astra†$8.8$44$0.44$111.0M—
Kenarigpt-6-2-astra$9.14$45.71$0.4571$9.141.1M—
Requestyeugpt-6.2-astra@eu†$9.6$48$0.48$121.1M—
Cortecsgpt-6.2-astra$9.925$49.622$0.497$12.4061.1M—

GPT-6.2 Astra price history

Output price per 1M tokens since tracking began on Nov 18, 2026, for the one provider whose rate moved. Each step is a recorded change. All recent price changes.

GPT-6.2 Astra output price per 1M tokens by provider, Nov 18, 2026 to Nov 22, 2026$0$25$50$75$100Nov 18, 2026Nov 20, 2026Nov 22, 2026
Kilo Gateway$40
GPT-6.2 Astra price changes by provider, newest first, USD per 1M tokens
DateProvider1M input1M outputChange
Kilo Gateway$16 → $8$60 → $40−33.3%

Subscription plans (not per-token)

Billed per month, not per token — never counted as the cheapest offer.

GitHub Copilotplan$8$401.1M

GPT-6.2 Astra pricing FAQ

What is the cheapest GPT-6.2 Astra API?

As of Nov 22, 2026, Amazon Bedrock has the lowest GPT-6.2 Astra output price at $40 per 1M tokens, and Amazon Bedrock has the lowest input price at $8 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

How much does GPT-6.2 Astra cost on OpenAI?

OpenAI charges $8 per 1M input tokens and $40 per 1M output tokens for GPT-6.2 Astra.

How many providers offer GPT-6.2 Astra?

26 providers list GPT-6.2 Astra on Sovyron; 29 of them sell it at a metered per-token price.

Is GPT-6.2 Astra free?

No provider in the Sovyron catalog lists a free tier for GPT-6.2 Astra.

Is GPT-6.2 Astra included in a subscription plan?

Yes. 2 flat-rate plans include it; the cheapest is GitHub Copilot Pro at $10/month.

What is the context window of GPT-6.2 Astra?

GPT-6.2 Astra supports a 1.1M-token context window and up to 128k output tokens.

Token cost calculator

What a month costs at one provider's published rates. Enter the tokens you expect to send and receive; cached tokens use the cached-input price where the provider lists one, and count as ordinary input where it does not. See how much prompt caching saves and why output tokens cost more than input tokens.

Estimated

—