Ways to buy 5
| Way to buy | Input | Output | In / out per 1M | Cached | Vs list |
|---|---|---|---|---|---|
 OpenAIflex, cheapest · cached $0.063 | $0.625 | $5 | $0.625 / $5-50% vs list | $0.063 | -50% vs list |
| OpenAI API The lab's own API · cached $0.125 | $1.25 | $10 | $1.25 / $10List price | $0.125 | List price |
 Azure AI FoundryDefault region · cached $0.13 | $1.25 | $10 | $1.25 / $10Same as list | $0.13 | Same as list |
| Azure AI Foundry swedencentral · cached $0.143 | $1.38 | $11 | $1.38 / $11+10% vs list | $0.143 | +10% vs list |
| OpenAI fast · cached $0.25 | $2.5 | $20 | $2.5 / $20+100% vs list | $0.25 | +100% vs list |
USD per 1M tokens; batch $0.625 in, $5 out on the lab's API. Regions are separate routes.
Through a gateway
Your own numbers100M input and 20M output tokens a month: $325.00 direct.
Helicone$325.00+0%
Kong AI Gateway$325.00+0%
LiteLLM$325.00+0%
Vercel AI Gateway$325.00+0%
Cloudflare AI Gateway$341.25+5%
Requesty$341.25+5%
Eden AI$342.88+5.5%
OpenRouter$342.88+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) | · |
 Muse Spark 1.3Meta · 1M | $1.25 | $4.25 | $1.25 / $4.25 | $2 | 1M | Lab list price | · |
 Gemini 3.1 Pro PreviewGoogle · 1MCheapest: $2.25 on Google Vertex AI (global-flex) | $2 | $12 | $2 / $12 | $4.5 | 1M | $2.25 on Google Vertex AI (global-flex) | · |
| Muse Spark 1.1 Meta · 1M | $1.25 | $4.25 | $1.25 / $4.25 | $2 | 1M | Lab list price | · |
 Qwen3.8 Max (0902)Qwen (Alibaba) · 1M | $2 | $6 | $2 / $6 | $3 | 1M | Lab list price | · |
About GPT-5.1
GPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adherence, and a more natural conversational style compared to GPT-5.
Takes image, text, files in and returns text. First listed Nov 14, 2025. Up to 128K output tokens. Blended price $3.44 per 1M tokens at 3 input to 1 output. Overall score 3 on leadersboard.fru.dev (rank 39). Model id gpt-5-1.
Price history
List price since Nov 14, 2025, from Internet Archive snapshots of the OpenRouter catalog, then daily reads.
| Seen | Model | Old price | New price | Change |
|---|---|---|---|---|
| Jul 17, 2026 | GPT-5.1Cached input $0.13 to $0.125 | Cached input $0.13 | Cached input $0.125 | -4% |
| Apr 23, 2026 | GPT-5.1Cached input $0.125 to $0.13 | Cached input $0.125 | Cached input $0.13 | +4% |
Questions
How much does GPT-5.1 cost?
$1.25 per million input tokens and $10 per million output tokens, with cached input at $0.125, or $0.625 and $5 through the Batch API.
What is the context window of GPT-5.1?
400K tokens, with up to 128K tokens of output.
Where is GPT-5.1 cheapest?
Of 5 routes tracked, OpenAI is cheapest at $0.625 input and $5 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.