Ways to buy 4
| Way to buy | Input | Output | In / out per 1M | Cached | Vs list |
|---|---|---|---|---|---|
 OpenAIflex, cheapest · cached $0.087 | $0.875 | $7 | $0.875 / $7-50% vs list | $0.087 | -50% vs list |
| OpenAI API The lab's own API · cached $0.175 | $1.75 | $14 | $1.75 / $14List price | $0.175 | List price |
 Azure AI FoundryDefault region · cached $0.175 | $1.75 | $14 | $1.75 / $14Same as list | $0.175 | Same as list |
| OpenAI fast · cached $0.35 | $3.5 | $28 | $3.5 / $28+100% vs list | $0.35 | +100% vs list |
USD per 1M tokens; batch $0.875 in, $7 out on the lab's API. Regions are separate routes.
Through a gateway
Your own numbers100M input and 20M output tokens a month: $455.00 direct.
Helicone$455.00+0%
Kong AI Gateway$455.00+0%
LiteLLM$455.00+0%
Vercel AI Gateway$455.00+0%
Cloudflare AI Gateway$477.75+5%
Requesty$477.75+5%
Eden AI$480.02+5.5%
OpenRouter$480.02+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 Opus 5Anthropic · 1M | $5 | $25 | $5 / $25 | $10 | 1M | Lab list price | · |
| Claude Opus 5.5 Anthropic · 1M | $4 | $20 | $4 / $20 | $8 | 1M | Lab list price | · |
| Claude Opus 4.6 Anthropic · 1M | $5 | $25 | $5 / $25 | $10 | 1M | Lab list price | · |
| Claude Opus 4.7 Anthropic · 1M | $5 | $25 | $5 / $25 | $10 | 1M | Lab list price | · |
About GPT-5.2
GPT-5.2 is the latest frontier-grade model in the GPT-5 series, offering stronger agentic and long context perfomance compared to GPT-5.1.
Takes files, image, text in and returns text. First listed Dec 15, 2025. Up to 128K output tokens. Blended price $4.81 per 1M tokens at 3 input to 1 output. Model id gpt-5-2.
Price history
List price since Dec 15, 2025, from Internet Archive snapshots of the OpenRouter catalog, then daily reads.
Questions
How much does GPT-5.2 cost?
$1.75 per million input tokens and $14 per million output tokens, with cached input at $0.175, or $0.875 and $7 through the Batch API.
What is the context window of GPT-5.2?
400K tokens, with up to 128K tokens of output.
Where is GPT-5.2 cheapest?
Of 4 routes tracked, OpenAI is cheapest at $0.875 input and $7 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.