Ways to buy 6
| Way to buy | Input | Output | In / out per 1M | Cached | Vs list |
|---|---|---|---|---|---|
 OpenAIflex, cheapest · cached $0.5 | $5 | $25 | $5 / $25-50% vs list | $0.5 | -50% vs list |
| OpenAI API The lab's own API · cached $1 | $10 | $50 | $10 / $50List price | $1 | List price |
 Azure AI FoundryDefault region · cached $1 | $10 | $50 | $10 / $50Same as list | $1 | Same as list |
 AWS Bedrockus-west-2 · cached $1.1 | $11 | $55 | $11 / $55+10% vs list | $1.1 | +10% vs list |
| Azure AI Foundry us · cached $1.1 | $11 | $55 | $11 / $55+10% vs list | $1.1 | +10% vs list |
| OpenAI fast · cached $2 | $20 | $100 | $20 / $100+100% vs list | $2 | +100% vs list |
USD per 1M tokens; batch $5 in, $25 out on the lab's API. Regions are separate routes.
Through a gateway
Your own numbers100M input and 20M output tokens a month: $2,000 direct.
Helicone$2,000+0%
Kong AI Gateway$2,000+0%
LiteLLM$2,000+0%
Vercel AI Gateway$2,000+0%
Cloudflare AI Gateway$2,100+5%
Requesty$2,100+5%
Eden AI$2,110+5.5%
OpenRouter$2,110+5.5%
No published token fee: Martian Gateway, Portkey, TrueFoundry AI Gateway.
Related models
| In / out per 1M | Cheapest route | ||||||
|---|---|---|---|---|---|---|---|
| GPT-6 Luna OpenAI · 1.05MCheapest: $0.1 on OpenAI (flex) | $0.1 | $0.5 | $0.1 / $0.5 | $0.2 | 1.05M | $0.1 on OpenAI (flex) | · |
| GPT-6 Luna Pro OpenAI · 1.05MCheapest: $0.1 on OpenAI (flex) | $0.1 | $0.5 | $0.1 / $0.5 | $0.2 | 1.05M | $0.1 on OpenAI (flex) | · |
| GPT-6 Sol OpenAI · 1.05MCheapest: $2 on OpenAI (flex) | $2 | $10 | $2 / $10 | $4 | 1.05M | $2 on OpenAI (flex) | · |
| GPT-6 Sol Pro OpenAI · 1.05MCheapest: $2 on OpenAI (flex) | $2 | $10 | $2 / $10 | $4 | 1.05M | $2 on OpenAI (flex) | · |
 Claude Fable 5.1Anthropic · 1M | $10 | $50 | $10 / $50 | $20 | 1M | Lab list price | · |
| Claude Opus 5 Anthropic · 1M | $5 | $25 | $5 / $25 | $10 | 1M | Lab list price | · |
| Claude Fable 5 Anthropic · 1M | $10 | $50 | $10 / $50 | $20 | 1M | Lab list price | · |
| Claude Opus 4.6 Anthropic · 1M | $5 | $25 | $5 / $25 | $10 | 1M | Lab list price | · |
About GPT-6 Astra
GPT-6 Astra is OpenAI's flagship model for demanding end-to-end work.
Takes files, image, text in and returns text. First listed Sep 5, 2026. Up to 128K output tokens. Blended price $20 per 1M tokens at 3 input to 1 output. Overall score 48 on leadersboard.fru.dev (rank 2). Model id gpt-6-astra.
Price history
List price since Sep 5, 2026, from Internet Archive snapshots of the OpenRouter catalog, then daily reads.
Questions
How much does GPT-6 Astra cost?
$10 per million input tokens and $50 per million output tokens, with cached input at $1, or $5 and $25 through the Batch API.
What is the context window of GPT-6 Astra?
1.05M tokens, with up to 128K tokens of output.
Where is GPT-6 Astra cheapest?
Of 6 routes tracked, OpenAI is cheapest at $5 input and $25 output per million tokens.
Sources: OpenRouter's public model catalog and each provider's own pricing page, read every morning at 05:00 UTC; gateway fees re-read every Monday. List prices: your contract may differ. Logos via logo.dev; trademarks belong to their owners.