GPT-5.1 API Pricing

OpenAI · released Nov 13, 2025 · 400K context · API model ID gpt-5.1

GPT-5.1 by OpenAI API pricing: $1.25 per 1M input tokens and $10.00 per 1M output tokens (verified against the official pricing page, Oct 9, 2026).

Prices

GPT-5.1 prices, USD per 1M tokens
PriceUSD per 1M tokens
Input$1.25
Output$10.00
Cache read$0.125
Cache writeNot published
Batch input$0.625
Batch output$5.00

Verified against the provider's official pricing page on Oct 9, 2026. Official pricing page

Estimated monthly cost

$1,875

per month

per day
$62.50
per request
$0.00625

Cost = input tokens × input price + output tokens × output price, 30 days a month. Cached input uses the cache read price. Cache write fees are not included.

Compare this workload across models

Monthly cost by workload

WorkloadPer month
Chatbot1,000 in / 500 out tokens, 10,000 requests a day$1,875/mo
RAG8,000 in / 500 out tokens, 5,000 requests a day$2,250/mo
Coding agent50,000 in / 2,000 out tokens, 1,000 requests a day, 80% cached input$1,125/mo

Context and capabilities

Context
400,000 tokens
Max output
128,000 tokens
Input
text, image
Output
text
Knowledge cutoff
Sep 30, 2024
Open weights
No
Tool calling
Yes
Reasoning
Yes
Structured outputs
Yes

Capabilities and limits as listed by models.dev.

Similarly priced models

Price history

No price changes since we started tracking on Oct 8, 2026.

Questions

How much does GPT-5.1 cost per month?
For a chatbot handling 10,000 requests a day with 1,000 input and 500 output tokens each, GPT-5.1 costs about $1,875 per month at the provider's official prices (verified) ($1.25 per 1M input tokens, $10.00 per 1M output tokens).
Does GPT-5.1 support prompt caching?
Yes. Cached input costs $0.125 per 1M tokens, compared with $1.25 for regular input.
How long is GPT-5.1's context window?
GPT-5.1 accepts up to 400,000 tokens (400K) of context and returns up to 128,000 tokens per response.
Does GPT-5.1 have a batch price?
Yes. Asynchronous batch requests cost $0.625 per 1M input tokens and $5.00 per 1M output tokens.