# Infron ## Document - [Quickstart](https://infronai.gitbook.io/docs/overview/quickstart.md): Get started with Infron - [Text](https://infronai.gitbook.io/docs/overview/quickstart/text.md): Text Generation Quickstart - [Image](https://infronai.gitbook.io/docs/overview/quickstart/image.md): Image Generation Quickstart - [Video](https://infronai.gitbook.io/docs/overview/quickstart/video.md): Video Generation Quickstart - [Audio](https://infronai.gitbook.io/docs/overview/quickstart/audio.md): Audio Generation Quickstart - [Search](https://infronai.gitbook.io/docs/overview/quickstart/search.md): Search, Deepsearch & Extract Quickstart - [Embedding](https://infronai.gitbook.io/docs/overview/quickstart/embedding.md): Embedding & Reranker Quickstart - [Batch](https://infronai.gitbook.io/docs/overview/quickstart/batch.md): Batch API Quickstart - [Platform Overview](https://infronai.gitbook.io/docs/overview/introduction.md): Infron - The world’s first AI Model Marketplace and Inference Provider Routing Platform - [FAQ](https://infronai.gitbook.io/docs/overview/faq.md): Common questions about Infron AI. - [Pricing and Fee Structure](https://infronai.gitbook.io/docs/overview/pricing-and-fee-structure.md): Understanding Infron’s usage-based pricing model. - [Inference Provider Routing](https://infronai.gitbook.io/docs/routing-and-gateway/inference-provider-routing.md): Route requests to the best inference provider - [BYOK](https://infronai.gitbook.io/docs/routing-and-gateway/byok.md): Bring your own provider API keys - [Available Providers](https://infronai.gitbook.io/docs/routing-and-gateway/available-providers.md) - [Zero Completion Insurance](https://infronai.gitbook.io/docs/features/zero-completion-insurance.md): Infron will not charge you for zero token responses - [Zero Data Retention](https://infronai.gitbook.io/docs/features/zero-data-retention.md): How Infron gives you control over your data - [Structured Outputs](https://infronai.gitbook.io/docs/features/structured-outputs.md): Return structured data from your models. - [Tool Calling](https://infronai.gitbook.io/docs/features/tool-calling.md): Tool & Function Calling - Use tools in your prompts - [Prompt Caching](https://infronai.gitbook.io/docs/features/prompt-caching.md): Prompt Cache in Infron - [Multimodal Input](https://infronai.gitbook.io/docs/features/multimodal-input.md): Send images, PDFs, and audio to Infron AI models - [Images Inputs](https://infronai.gitbook.io/docs/features/multimodal-input/images-inputs.md): How to send images and PDFs to Infron AI - [PDF Inputs](https://infronai.gitbook.io/docs/features/multimodal-input/pdf-inputs.md): How to send PDFs to Infron AI models - [Audio Inputs](https://infronai.gitbook.io/docs/features/multimodal-input/audio-inputs.md): How to send audio files to Infron AI models - [Video Inputs](https://infronai.gitbook.io/docs/features/multimodal-input/video-inputs.md) - [Reasoning & Thinking](https://infronai.gitbook.io/docs/features/reasoning-and-thinking.md) - [1M Token Long Context Window](https://infronai.gitbook.io/docs/features/1m-token-long-context-window.md) - [Web Search](https://infronai.gitbook.io/docs/features/web-search.md): This document explains how to use the Web Search feature on the Infron platform. - [Plugins](https://infronai.gitbook.io/docs/features/plugins.md): Extend model capabilities with Infron plugins - [Web Search](https://infronai.gitbook.io/docs/features/plugins/web-search.md): Model-agnostic grounding - [Overview](https://infronai.gitbook.io/docs/frameworks-and-integrations/overview.md): Using Infron AI with Popular Frameworks and Integrations - [OpenAI SDK](https://infronai.gitbook.io/docs/frameworks-and-integrations/openai-sdk.md): Using Infron AI with OpenAI SDK - [LangChain](https://infronai.gitbook.io/docs/frameworks-and-integrations/langchain.md): Using Infron AI with LangChain - [PydanticAI](https://infronai.gitbook.io/docs/frameworks-and-integrations/pydanticai.md): Using Infron AI with PydanticAI - [Langfuse](https://infronai.gitbook.io/docs/frameworks-and-integrations/langfuse.md): Using Infron AI with Langfuse - [n8n](https://infronai.gitbook.io/docs/frameworks-and-integrations/n8n.md): Build AI automations with Infron AI & n8n - [Claude Code Integration Guide](https://infronai.gitbook.io/docs/frameworks-and-integrations/claude-code-integration-guide.md): Use Claude Agent SDK and Claude Code with Infron AI models - [Anthropic SDK Compatibility](https://infronai.gitbook.io/docs/frameworks-and-integrations/anthropic-sdk-compatibility.md): Use Anthropic SDK with Infron AI models - [OpenAI Codex CLI](https://infronai.gitbook.io/docs/frameworks-and-integrations/openai-codex-cli.md): Use Codex CLI with Infron AI models - [OpenAI Agents SDK](https://infronai.gitbook.io/docs/frameworks-and-integrations/openai-agents-sdk.md): Use OpenAI Agents SDK with Infron AI models - [LiteLLM](https://infronai.gitbook.io/docs/frameworks-and-integrations/litellm.md): Integration with LiteLLM's OpenAI-Compatible Endpoints with Infron AI - [OpenCode](https://infronai.gitbook.io/docs/frameworks-and-integrations/opencode.md): Kickstart OpenCode with Infron - [OpenClaw](https://infronai.gitbook.io/docs/frameworks-and-integrations/openclaw.md): Guide to Using OpenClaw with Infron - [OpenWork](https://infronai.gitbook.io/docs/frameworks-and-integrations/openwork.md) - [Hermes Agent](https://infronai.gitbook.io/docs/frameworks-and-integrations/hermes-agent.md) - [Billing Tracking](https://infronai.gitbook.io/docs/observability/billing-tracking.md): Get cost details and usage details in every call - [Billing Logs](https://infronai.gitbook.io/docs/observability/billing-logs.md) - [Latency](https://infronai.gitbook.io/docs/observability/latency.md): Understanding Infron's performance characteristics. - [Performance Analysis](https://infronai.gitbook.io/docs/observability/performance-analysis.md): Performance Analysis - [Test Token Cache Rate](https://infronai.gitbook.io/docs/test-cases/test-token-cache-rate.md): Infron AI Token cache Rate A/B Testing Guide. - [Performance Stress Testing](https://infronai.gitbook.io/docs/test-cases/performance-stress-testing.md): Infron AI Performance Stress Testing Guide. - [Privacy and Logging](https://infronai.gitbook.io/docs/support/privacy-logging.md): Making sure your data is safe - [Contact Us](https://infronai.gitbook.io/docs/support/contact-us.md) - [Join Community](https://infronai.gitbook.io/docs/support/join-community.md) ## LLM APIs - [Streaming](https://infronai.gitbook.io/docs/llm-apis/api-guides/streaming.md): The Infron API allows streaming responses from any model. This is useful for building chat interfaces or other applications where the UI should update as the model generates the response. - [Authentication](https://infronai.gitbook.io/docs/llm-apis/api-guides/authentication.md): API Authentication - [Errors code](https://infronai.gitbook.io/docs/llm-apis/api-guides/errors-code.md): API Errors - [Overview](https://infronai.gitbook.io/docs/llm-apis/openai-compatible-api/overview.md) - [Create a chat completion](https://infronai.gitbook.io/docs/llm-apis/openai-compatible-api/create-a-chat-completion.md) - [Chat with Images Inputs](https://infronai.gitbook.io/docs/llm-apis/openai-compatible-api/chat-with-images-inputs.md) - [Chat with PDF Inputs](https://infronai.gitbook.io/docs/llm-apis/openai-compatible-api/chat-with-pdf-inputs.md) - [Chat with Tool Calling](https://infronai.gitbook.io/docs/llm-apis/openai-compatible-api/chat-with-tool-calling.md) - [Chat with Structured Outputs](https://infronai.gitbook.io/docs/llm-apis/openai-compatible-api/chat-with-structured-outputs.md) - [Reasoning configuration](https://infronai.gitbook.io/docs/llm-apis/openai-compatible-api/reasoning-configuration.md) - [Explicit Caching](https://infronai.gitbook.io/docs/llm-apis/openai-compatible-api/explicit-caching.md) - [Chat with OpenAI Compatible Web Search](https://infronai.gitbook.io/docs/llm-apis/openai-compatible-api/chat-with-openai-compatible-web-search.md) - [Chat with OpenAI Compatible Web Fetch](https://infronai.gitbook.io/docs/llm-apis/openai-compatible-api/chat-with-openai-compatible-web-fetch.md) - [Overview](https://infronai.gitbook.io/docs/llm-apis/anthropic-compatible-api/overview.md) - [Create a message](https://infronai.gitbook.io/docs/llm-apis/anthropic-compatible-api/create-a-message.md) - [Chat with Tool Calling](https://infronai.gitbook.io/docs/llm-apis/anthropic-compatible-api/chat-with-tool-calling.md) - [Reasoning configuration](https://infronai.gitbook.io/docs/llm-apis/anthropic-compatible-api/reasoning-configuration.md) - [Chat with Web Search](https://infronai.gitbook.io/docs/llm-apis/anthropic-compatible-api/chat-with-web-search.md) - [Chat with File Attachments](https://infronai.gitbook.io/docs/llm-apis/anthropic-compatible-api/chat-with-file-attachments.md) - [Overview](https://infronai.gitbook.io/docs/llm-apis/openresponses-api/overview.md) - [Create a response](https://infronai.gitbook.io/docs/llm-apis/openresponses-api/create-a-response.md) - [Chat with Tool Calling](https://infronai.gitbook.io/docs/llm-apis/openresponses-api/chat-with-tool-calling.md) - [Overview](https://infronai.gitbook.io/docs/llm-apis/embeddings-api/overview.md): Generate vector embeddings from text - [Submit an embedding request](https://infronai.gitbook.io/docs/llm-apis/embeddings-api/submit-an-embedding-request.md) - [Overview](https://infronai.gitbook.io/docs/llm-apis/rerank-api/overview.md): Generate ranks of relevancy between the query and documents - [Submit an ranking request](https://infronai.gitbook.io/docs/llm-apis/rerank-api/submit-an-ranking-request.md) ## Media APIs - [Overview](https://infronai.gitbook.io/docs/media-apis/api-guides/overview.md): Infron is a unified AI platform that provides access to 500+ state-of-the-art models for image generation, video creation, audio synthesis, and more. - [Upload Files](https://infronai.gitbook.io/docs/media-apis/advanced-features/upload-files.md): Upload images, videos, and audio files for use with Infron models. - [How to Write Better Prompts](https://infronai.gitbook.io/docs/media-apis/best-practices/how-to-write-better-prompts.md): Improve your AI generation results with effective prompt writing techniques. - [How to Reduce Costs](https://infronai.gitbook.io/docs/media-apis/best-practices/how-to-reduce-costs.md): Optimize your Infron usage to get the best results while managing costs effectively. - [Seedance 2.0 Real Human](https://infronai.gitbook.io/docs/media-apis/seedance-2.0-real-human.md): Generate videos featuring real people in Seedance 2.0 with identity consistency, native audio-video sync, and a one-time ByteDance verification in Infron. ## Search APIs - [Overview](https://infronai.gitbook.io/docs/search-apis/overview.md): Infron Web Search Model & Agent Integration Overview - [Tavily](https://infronai.gitbook.io/docs/search-apis/search-api/tavily.md) - [Jina](https://infronai.gitbook.io/docs/search-apis/search-api/jina.md) - [Firecrawl](https://infronai.gitbook.io/docs/search-apis/search-api/firecrawl.md) - [Perplexity](https://infronai.gitbook.io/docs/search-apis/search-api/perplexity.md) - [Exa](https://infronai.gitbook.io/docs/search-apis/search-api/exa.md) - [Cloudsway](https://infronai.gitbook.io/docs/search-apis/search-api/cloudsway.md) - [Tavily](https://infronai.gitbook.io/docs/search-apis/extract-api/tavily.md) ## Batch APIs - [Overview](https://infronai.gitbook.io/docs/batch-apis/overview.md) - [Create New Batch](https://infronai.gitbook.io/docs/batch-apis/llm-batch-api/create-new-batch.md) - [Get Status of a Batch](https://infronai.gitbook.io/docs/batch-apis/llm-batch-api/get-status-of-a-batch.md) - [Cancel a Batch](https://infronai.gitbook.io/docs/batch-apis/llm-batch-api/cancel-a-batch.md) ## Billing APIs - [Get remaining credits](https://infronai.gitbook.io/docs/billing-apis/credits/get-remaining-credits.md) - [Overview](https://infronai.gitbook.io/docs/billing-apis/usage-and-cost/overview.md): Track AI Model Token Usage and Cost Breakdowns - [Get cost & usage details (non streaming)](https://infronai.gitbook.io/docs/billing-apis/usage-and-cost/get-cost-and-usage-details-non-streaming.md) - [Get cost & usage details (streaming)](https://infronai.gitbook.io/docs/billing-apis/usage-and-cost/get-cost-and-usage-details-streaming.md) ## Models & Providers APIs - [Request preview](https://infronai.gitbook.io/docs/models-and-providers-apis/sandbox-api/request-preview.md) - [Response preview](https://infronai.gitbook.io/docs/models-and-providers-apis/sandbox-api/response-preview.md) - [List all models and their properties](https://infronai.gitbook.io/docs/models-and-providers-apis/models-api/list-all-models-and-their-properties.md) ## LLM Inference Handbook - [What is LLM inference?](https://infronai.gitbook.io/docs/llm-inference-handbook/llm-inference-basics/quickstart.md) - [How does LLM inference work?](https://infronai.gitbook.io/docs/llm-inference-handbook/llm-inference-basics/how-does-llm-inference-work.md): During inference, an LLM generates text one token at a time, using its internal attention mechanisms and knowledge of previous context. - [Where is LLM inference run?](https://infronai.gitbook.io/docs/llm-inference-handbook/llm-inference-basics/where-is-llm-inference-run.md) - [Training vs. Inference](https://infronai.gitbook.io/docs/llm-inference-handbook/llm-inference-basics/training-vs.-inference.md): LLM training and inference are two different phases in the lifecycle of a model. - [What is Serverless inference?](https://infronai.gitbook.io/docs/llm-inference-handbook/llm-inference-basics/what-is-serverless-inference.md) - [What is Server-based inference?](https://infronai.gitbook.io/docs/llm-inference-handbook/llm-inference-basics/what-is-server-based-inference.md) - [Serverless vs. Self-hosted LLM inference](https://infronai.gitbook.io/docs/llm-inference-handbook/llm-inference-basics/serverless-vs.-self-hosted-llm-inference.md) - [Serverless vs. Server-based LLM inference](https://infronai.gitbook.io/docs/llm-inference-handbook/llm-inference-basics/serverless-vs.-server-based-llm-inference.md) - [What is distributed inference?](https://infronai.gitbook.io/docs/llm-inference-handbook/llm-inference-basics/what-is-distributed-inference.md) - [Unified API compatibility](https://infronai.gitbook.io/docs/llm-inference-handbook/llm-inference-advanced/unified-api-compatibility.md) - [OpenAI-compatible API](https://infronai.gitbook.io/docs/llm-inference-handbook/llm-inference-advanced/unified-api-compatibility/openai-compatible-api.md): Once an LLM is running, you’ll need a standard way to interact with it. That’s where the OpenAI-compatible API comes in. - [Structured outputs](https://infronai.gitbook.io/docs/llm-inference-handbook/llm-inference-advanced/unified-api-compatibility/structured-outputs.md) - [Function calling](https://infronai.gitbook.io/docs/llm-inference-handbook/llm-inference-advanced/unified-api-compatibility/function-calling.md) - [Choosing the right model](https://infronai.gitbook.io/docs/llm-inference-handbook/llm-inference-advanced/editor.md): The first step is deciding what type of model fits your use case. Here’s a breakdown of common model types when it comes to LLMs. - [Choosing the right provider](https://infronai.gitbook.io/docs/llm-inference-handbook/llm-inference-advanced/choosing-the-right-provider.md) - [Choosing the right GPU](https://infronai.gitbook.io/docs/llm-inference-handbook/llm-inference-advanced/choosing-the-right-gpu.md) - [LLM fine-tuning](https://infronai.gitbook.io/docs/llm-inference-handbook/llm-inference-advanced/llm-fine-tuning.md) - [LLM quantization](https://infronai.gitbook.io/docs/llm-inference-handbook/llm-inference-advanced/llm-quantization.md) - [Choosing the right inference framework](https://infronai.gitbook.io/docs/llm-inference-handbook/llm-inference-advanced/choosing-the-right-inference-framework.md) - [What is LLM inference infrastructure?](https://infronai.gitbook.io/docs/llm-inference-handbook/infrastructure-and-operations/what-is-llm-inference-infrastructure.md) - [Challenges in building infrastructure for LLM inference](https://infronai.gitbook.io/docs/llm-inference-handbook/infrastructure-and-operations/challenges-in-building-infrastructure-for-llm-inference.md) - [How to build faster inference for open-source models](https://infronai.gitbook.io/docs/llm-inference-handbook/infrastructure-and-operations/how-to-build-faster-inference-for-open-source-models.md) - [Multi-cloud and cross-region inference](https://infronai.gitbook.io/docs/llm-inference-handbook/infrastructure-and-operations/multi-cloud-and-cross-region-inference.md) - [On-prem LLM deployments](https://infronai.gitbook.io/docs/llm-inference-handbook/infrastructure-and-operations/on-prem-llm-deployments.md) - [InferenceOps and management](https://infronai.gitbook.io/docs/llm-inference-handbook/infrastructure-and-operations/inferenceops-and-management.md) - [Key metrics for LLM inference](https://infronai.gitbook.io/docs/llm-inference-handbook/inference-optimization/key-metrics-for-llm-inference.md) - [Static, dynamic and continuous batching](https://infronai.gitbook.io/docs/llm-inference-handbook/inference-optimization/static-dynamic-and-continuous-batching.md) - [Speculative decoding](https://infronai.gitbook.io/docs/llm-inference-handbook/inference-optimization/speculative-decoding.md) - [Prefill-decode disaggregation](https://infronai.gitbook.io/docs/llm-inference-handbook/inference-optimization/prefill-decode-disaggregation.md) - [Prefix caching](https://infronai.gitbook.io/docs/llm-inference-handbook/inference-optimization/prefix-caching.md) - [KV cache offloading](https://infronai.gitbook.io/docs/llm-inference-handbook/inference-optimization/kv-cache-offloading.md) - [Offline batch inference](https://infronai.gitbook.io/docs/llm-inference-handbook/inference-optimization/offline-batch-inference.md) --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on a page URL with the `ask` query parameter: ``` GET https://infronai.gitbook.io/docs/overview/quickstart.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.