Generate text, stream responses, and make structured decisions through managed AI models. Use your Nutrient account for API access, usage, and billing.
SUBSCRIPTION PRICING
Each plan includes monthly usage in USD, billed per token at each model’s rate. Enable pay-as-you-go for usage beyond your allowance, subject to your account’s billing and spending controls.
—
/MO
—
included usage/month
Pay-as-you-go: — per $1 of usage
—
/MO
—
included usage/month
Pay-as-you-go: — per $1 of usage
—
/MO
—
included usage/month
Pay-as-you-go: — per $1 of usage
—
/MO
—
included usage/month
Pay-as-you-go: — per $1 of usage
—
/MO
—
included usage/month
Pay-as-you-go: — per $1 of usage
—
/MO
—
included usage/month
Pay-as-you-go: — per $1 of usage
—
/MO
—
included usage/month
Pay-as-you-go: — per $1 of usage
—
/MO
—
included usage/month
Pay-as-you-go: — per $1 of usage
Built for teams already running business-critical document workflows on Nutrient.
FLEXIBLE API ACCESS
Use the OpenAI Responses API for generation and reasoning with function tools, keep existing Chat Completions integrations, or use the decision API for structured questions and probabilities. Start with an API key enabled for AI Gateway and the OpenAI SDK. Account access is required.
import OpenAI from "openai";
const client = new OpenAI({ apiKey: process.env.NUTRIENT_API_KEY, baseURL: "https://api.nutrient.io/ai/v1"});
try { const response = await client.responses.create({ model: "nutrient-s", input: "Summarize this obligation: The supplier must deliver the report by 30 November and notify the customer of delays within two business days." }); console.log(response.output_text);} catch (error) { console.error("AI Gateway request failed:", error.message); process.exitCode = 1;}WHY AI GATEWAY
AI Gateway connects your applications to supported AI providers while keeping usage controls and billing in your existing Nutrient DWS account.
Use Responses or Chat Completions for generation, streaming, and application-executed function tools. Use the decision API for decisions with probabilities when enabled for your account.
Manage access, usage limits, and pay-as-you-go billing through your Nutrient account.
Summarize extracted text, answer questions over content you provide, or route work using decision probabilities. Pair with Data Extraction when you need document parsing and citations.
DEVELOPER GUIDES
Set up access and an API key, then use curl, JavaScript, or Python to generate a response.
Pick a model, and Responses, Chat Completions, or the decision API.
Review plans, how token usage is billed, test keys, and pay-as-you-go usage.
FAQ
AI Gateway supports OpenAI-compatible Responses and Chat Completions, plus a decision API for structured questions and probabilities. The Models endpoint lists available aliases, capabilities, limits, and rates for your key. The decision API requires additional account access.
The Free plan includes $5 of usage per month. Live requests are billed by token usage, with separate input, cached-input, and output rates per model. See current token rates on the dashboard pricing page. Test keys make real text-only requests without consuming your allowance and have separate usage controls. See the pricing guide for how charges are calculated and pay-as-you-go details.
Data Extraction parses documents into spatial elements, Markdown, or schema-shaped data with citations and charges per page. AI Gateway calls models for generation and decisions and charges by token usage. Combine them by passing extracted content to a model; each product is billed separately.
Yes. You can continue using your existing provider accounts. AI Gateway is an additional option for managing model access, usage, and billing through Nutrient.
Nutrient records the request details needed to operate and bill the service, including request IDs, model and rate information, token counts, costs, and errors. Data handling and retention depend on the model provider. OpenAI-backed requests may be processed globally and retained for abuse monitoring for up to 30 days. Zero Data Retention and regional processing aren’t currently available for OpenAI-backed requests.
For generative tasks, nutrient-s is the fast, lower-cost tier, nutrient-m is the default balance, and nutrient-l is for complex workloads. For structured questions with probabilities, use the decision API.
Talk to Nutrient about model access, usage, pricing, and the right plan for your application.