For the complete Netlify documentation index, see llms.txt. Markdown versions of this page are available by appending .md to the URL. Learn about pricing for AI features, such as Agent Runners, which you can use to run AI agent tasks in the background or AI Gateway, which you can use to add AI model functionality to your project. For an example project using AI Gateway, check out this gameshow example project, which compares how AI models would compete in a game.
AI inference as a usage meter
Section titled “AI inference as a usage meter”AI inference is a usage meter that measures the costs of using AI models and agents on Netlify. This usage meter calculates costs for using Agent Runners and AI Gateway.
AI inference is one of several usage meters, such as compute, bandwidth, and web requests, that convert usage to Netlify credits.
In your credit usage breakdown, AI inference is broken down into Agent Runners AI inference and AI Gateway AI inference so you can see how each feature contributes to your credit usage.
To check out your AI inference usage, go to Usage & billing Account usage insights. Learn more about this usage graph in our docs on monitoring usage.
Note that the "Why did it fail?" troubleshooting failed deploys feature does not generate AI inference costs. If you use an Agent Runner to fix a failed deploy though, AI inference usage and costs will be calculated.
How costs are calculated
Section titled “How costs are calculated”AI inference costs are calculated based on your AI model usage.
AI inference is measured based on the costs set by AI model providers, which convert AI model usage tokens to USD. Netlify then converts every $1 USD spent on AI model usage to 180 Netlify credits.
This rate is designed to make using AI features like Agent Runners and AI Gateway competitive with using AI providers without Netlify.
AI inference consumes credits at the same rate for both features:
| Metric | Unit | Credits Consumed | What this covers |
|---|---|---|---|
| Agent Runners AI inference | AI model usage in USD (US Dollars) | 180 credits per $1 USD | AI models used by Agent Runners |
| AI Gateway AI inference | AI model usage in USD (US Dollars) | 180 credits per $1 USD | AI models used through AI Gateway |
Pricing for Agent Runners
Section titled “Pricing for Agent Runners”The costs of using Agent Runners are calculated using two usage meters. An agent run consumes credits in two ways: AI inference covers the AI model usage during the run, while compute covers the environment the agent works in, measured in GB-hours.
AI inference costs are determined by the AI model/s used in your agent runs. When you choose an agent for an agent run, the agent you choose picks an AI model based on the task type and complexity. To learn more about how AI models are priced, check out our AI model pricing rates table.
To help you control costs for Agent Runners, you can set an AI Credit Usage Limit. Once the limit is reached, your team can no longer start agent runs and active agent runs stop. The limit applies to AI inference from Agent Runners only, so AI Gateway usage isn't affected. On Enterprise plans, the limit factors in AI inference from both Agent Runners and AI Gateway — though only agent runs are paused when it's reached. Learn more in our docs on Managing AI features.
Pricing for AI Gateway
Section titled “Pricing for AI Gateway”The cost of using AI Gateway is calculated using only the AI inference usage meter.
When you use AI Gateway, you can choose a specific AI model to use for your requests.
How costs are calculated
Section titled “How costs are calculated”For each request to the AI Gateway that ends successfully, the following is calculated:
- Your account is billed for the amount of actual tokens used in that request.
- The count of actual tokens used for each token type (input, output, cache reads, and cache writes) is converted to US dollar amounts, using the rates listed below.
- The exact total dollar value for the request is converted to credits. Each dollar equals 180 credits.
There are no special credits for the AI Gateway. AI Gateway uses the same pool of credits included in your Netlify pricing plan, or any additional credits you purchase.
AI Gateway usage isn't subject to the AI Credit Usage Limit, which applies to AI inference from Agent Runners only. On Enterprise plans, the limit factors in AI inference from both AI Gateway and Agent Runners.
To estimate your costs, you can check the Pricing per AI model table or explore our pricing calculator.
AI providers and models
Section titled “AI providers and models”AI inference supports the following AI providers and models.
If you are using AI Gateway, you can choose a specific AI model to use for your requests.
If you are using Agent Runners, your AI agent will choose which AI models to use on your behalf to optimize performance and cost based on task type and complexity.
| AI Provider | Model |
|---|---|
| Anthropic | claude-fable-5 |
| Anthropic | claude-haiku-4-5 |
| Anthropic | claude-haiku-4-5-20251001 |
| Anthropic | claude-opus-4-1-20250805 |
| Anthropic | claude-opus-4-5 |
| Anthropic | claude-opus-4-5-20251101 |
| Anthropic | claude-opus-4-6 |
| Anthropic | claude-opus-4-7 |
| Anthropic | claude-opus-4-8 |
| Anthropic | claude-sonnet-4-5 |
| Anthropic | claude-sonnet-4-5-20250929 |
| Anthropic | claude-sonnet-4-6 |
| Anthropic | claude-sonnet-5 |
| Gemini | gemini-2.5-flash |
| Gemini | gemini-2.5-flash-image |
| Gemini | gemini-2.5-flash-lite |
| Gemini | gemini-2.5-pro |
| Gemini | gemini-3-flash-preview |
| Gemini | gemini-3-pro-image |
| Gemini | gemini-3.1-flash-image |
| Gemini | gemini-3.1-flash-lite |
| Gemini | gemini-3.1-flash-lite-image |
| Gemini | gemini-3.1-pro-preview |
| Gemini | gemini-3.1-pro-preview-customtools |
| Gemini | gemini-3.5-flash |
| Gemini | gemini-flash-latest |
| Gemini | gemini-flash-lite-latest |
| Openai | chat-latest |
| Openai | gpt-4.1 |
| Openai | gpt-4.1-mini |
| Openai | gpt-4.1-nano |
| Openai | gpt-4o |
| Openai | gpt-4o-mini |
| Openai | gpt-5 |
| Openai | gpt-5-2025-08-07 |
| Openai | gpt-5-codex |
| Openai | gpt-5-mini |
| Openai | gpt-5-mini-2025-08-07 |
| Openai | gpt-5-nano |
| Openai | gpt-5-pro |
| Openai | gpt-5.1 |
| Openai | gpt-5.1-2025-11-13 |
| Openai | gpt-5.1-codex |
| Openai | gpt-5.1-codex-max |
| Openai | gpt-5.1-codex-mini |
| Openai | gpt-5.2 |
| Openai | gpt-5.2-2025-12-11 |
| Openai | gpt-5.2-codex |
| Openai | gpt-5.2-pro |
| Openai | gpt-5.2-pro-2025-12-11 |
| Openai | gpt-5.3-chat-latest |
| Openai | gpt-5.3-codex |
| Openai | gpt-5.4 |
| Openai | gpt-5.4-2026-03-05 |
| Openai | gpt-5.4-mini |
| Openai | gpt-5.4-mini-2026-03-17 |
| Openai | gpt-5.4-nano |
| Openai | gpt-5.4-nano-2026-03-17 |
| Openai | gpt-5.4-pro |
| Openai | gpt-5.4-pro-2026-03-05 |
| Openai | gpt-5.5 |
| Openai | gpt-5.5-2026-04-23 |
| Openai | gpt-5.5-pro |
| Openai | gpt-5.5-pro-2026-04-23 |
| Openai | gpt-5.6-luna |
| Openai | gpt-5.6-sol |
| Openai | gpt-5.6-terra |
| Openai | o3 |
| Openai | o3-mini |
| Openai | o4-mini |
You can also programatically access the up-to-date list in JSON format via a public API endpoint: https://api.netlify.com/api/v1/ai-gateway/providers.
Pricing per AI model
Section titled “Pricing per AI model”The following table shows the current rates for AI tokens in USD (US dollars) for different AI providers before costs are converted to Netlify credits.
AI model cost per 1 million tokens
Section titled “AI model cost per 1 million tokens”| Provider | Model | Input Tokens | Cache read | Output Tokens | Cache write |
|---|---|---|---|---|---|
| Anthropic | claude-fable-5 |
$10.00 | $12.50 | $50.00 | $1.00 |
| Anthropic | claude-haiku-4-5 |
$1.00 | $1.25 | $5.00 | $0.10 |
| Anthropic | claude-haiku-4-5-20251001 |
$1.00 | $1.25 | $5.00 | $0.10 |
| Anthropic | claude-opus-4-1-20250805 |
$15.00 | $18.75 | $75.00 | $1.50 |
| Anthropic | claude-opus-4-5 |
$5.00 | $6.25 | $25.00 | $0.50 |
| Anthropic | claude-opus-4-5-20251101 |
$5.00 | $6.25 | $25.00 | $0.50 |
| Anthropic | claude-opus-4-6 |
$5.00 | $6.25 | $25.00 | $0.50 |
| Anthropic | claude-opus-4-7 |
$5.00 | $6.25 | $25.00 | $0.50 |
| Anthropic | claude-opus-4-8 |
$5.00 | $6.25 | $25.00 | $0.50 |
| Anthropic | claude-sonnet-4-5 |
$3.00 | $3.75 | $15.00 | $0.30 |
| Anthropic | claude-sonnet-4-5-20250929 |
$3.00 | $3.75 | $15.00 | $0.30 |
| Anthropic | claude-sonnet-4-6 |
$3.00 | $3.75 | $15.00 | $0.30 |
| Anthropic | claude-sonnet-5 |
$2.00 | $2.50 | $10.00 | $0.20 |
| Gemini | gemini-2.5-flash |
$0.30 | N/A | $2.50 | $0.03 |
| Gemini | gemini-2.5-flash-image |
$0.30 | N/A | $30.00 | N/A |
| Gemini | gemini-2.5-flash-lite |
$0.10 | N/A | $0.40 | $0.01 |
| Gemini | gemini-2.5-pro |
$1.25 | N/A | $10.00 | $0.13 |
| Gemini | gemini-3-flash-preview |
$0.50 | N/A | $3.00 | $0.05 |
| Gemini | gemini-3-pro-image |
$2.00 | N/A | $120.00 | N/A |
| Gemini | gemini-3.1-flash-image |
$0.50 | N/A | $60.00 | N/A |
| Gemini | gemini-3.1-flash-lite |
$0.25 | N/A | $1.50 | $0.03 |
| Gemini | gemini-3.1-flash-lite-image |
$0.25 | N/A | $30.00 | N/A |
| Gemini | gemini-3.1-pro-preview |
$2.00 | N/A | $12.00 | $0.20 |
| Gemini | gemini-3.1-pro-preview-customtools |
$2.00 | N/A | $12.00 | $0.20 |
| Gemini | gemini-3.5-flash |
$1.50 | N/A | $9.00 | $0.15 |
| Gemini | gemini-flash-latest |
$0.50 | N/A | $3.00 | $0.05 |
| Gemini | gemini-flash-lite-latest |
$0.25 | N/A | $1.50 | $0.03 |
| Openai | chat-latest |
$5.00 | N/A | $30.00 | $0.50 |
| Openai | gpt-4.1 |
$2.00 | N/A | $8.00 | $0.50 |
| Openai | gpt-4.1-mini |
$0.40 | N/A | $1.60 | $0.10 |
| Openai | gpt-4.1-nano |
$0.10 | N/A | $0.40 | $0.02 |
| Openai | gpt-4o |
$2.50 | N/A | $10.00 | $1.25 |
| Openai | gpt-4o-mini |
$0.15 | N/A | $0.60 | $0.07 |
| Openai | gpt-5 |
$1.25 | N/A | $10.00 | $0.12 |
| Openai | gpt-5-2025-08-07 |
$1.25 | N/A | $10.00 | $0.12 |
| Openai | gpt-5-codex |
$1.25 | N/A | $10.00 | $0.12 |
| Openai | gpt-5-mini |
$0.25 | N/A | $2.00 | $0.02 |
| Openai | gpt-5-mini-2025-08-07 |
$0.25 | N/A | $2.00 | $0.02 |
| Openai | gpt-5-nano |
$0.05 | N/A | $0.40 | N/A |
| Openai | gpt-5-pro |
$15.00 | N/A | $120.00 | N/A |
| Openai | gpt-5.1 |
$1.25 | N/A | $10.00 | $0.12 |
| Openai | gpt-5.1-2025-11-13 |
$1.25 | N/A | $10.00 | $0.12 |
| Openai | gpt-5.1-codex |
$1.25 | N/A | $10.00 | $0.12 |
| Openai | gpt-5.1-codex-max |
$1.25 | N/A | $10.00 | $0.12 |
| Openai | gpt-5.1-codex-mini |
$0.25 | N/A | $2.00 | $0.02 |
| Openai | gpt-5.2 |
$1.75 | N/A | $14.00 | $0.17 |
| Openai | gpt-5.2-2025-12-11 |
$1.75 | N/A | $14.00 | $0.17 |
| Openai | gpt-5.2-codex |
$1.75 | N/A | $14.00 | $0.17 |
| Openai | gpt-5.2-pro |
$21.00 | N/A | $168.00 | N/A |
| Openai | gpt-5.2-pro-2025-12-11 |
$21.00 | N/A | $168.00 | N/A |
| Openai | gpt-5.3-chat-latest |
$1.75 | N/A | $14.00 | $0.17 |
| Openai | gpt-5.3-codex |
$1.75 | N/A | $14.00 | $0.17 |
| Openai | gpt-5.4 |
$2.50 | N/A | $15.00 | $0.25 |
| Openai | gpt-5.4-2026-03-05 |
$2.50 | N/A | $15.00 | $0.25 |
| Openai | gpt-5.4-mini |
$0.75 | N/A | $4.50 | $0.07 |
| Openai | gpt-5.4-mini-2026-03-17 |
$0.75 | N/A | $4.50 | $0.07 |
| Openai | gpt-5.4-nano |
$0.20 | N/A | $1.25 | $0.02 |
| Openai | gpt-5.4-nano-2026-03-17 |
$0.20 | N/A | $1.25 | $0.02 |
| Openai | gpt-5.4-pro |
$30.00 | N/A | $180.00 | N/A |
| Openai | gpt-5.4-pro-2026-03-05 |
$30.00 | N/A | $180.00 | N/A |
| Openai | gpt-5.5 |
$5.00 | N/A | $30.00 | $0.50 |
| Openai | gpt-5.5-2026-04-23 |
$5.00 | N/A | $30.00 | $0.50 |
| Openai | gpt-5.5-pro |
$30.00 | N/A | $180.00 | N/A |
| Openai | gpt-5.5-pro-2026-04-23 |
$30.00 | N/A | $180.00 | N/A |
| Openai | gpt-5.6-luna |
$1.00 | $1.25 | $6.00 | $0.10 |
| Openai | gpt-5.6-sol |
$5.00 | $6.25 | $30.00 | $0.50 |
| Openai | gpt-5.6-terra |
$2.50 | $3.12 | $15.00 | $0.25 |
| Openai | o3 |
$2.00 | N/A | $8.00 | $0.50 |
| Openai | o3-mini |
$1.10 | N/A | $4.40 | $0.55 |
| Openai | o4-mini |
$1.10 | N/A | $4.40 | $0.27 |
Did you find this doc useful?
Your feedback helps us improve our docs.