Skip to content

AvalAI Docs

Guides API Reference Models Pricing

فاADeveloper Dashboard

Updates

Introduction
Quick Start
Libraries
Performance
Pricing
Service Tiers
Credit Packages
Rate Limits
Deprecated Models

Cost Tracking Guide
Enterprise Guide

Overview
Authentication
User API
Models
Response Headers
Chat Completions
Images
Embeddings
Audio
Moderation
Fine-tuning
Assistants
Batch
Files
Responses
Rerank
Messages
v1beta (GenAI SDK)
Text:Synthesize (Vertex AI)
Search
OCR
Video

Model Explorer
Alibaba (Qwen)
OpenAI
Anthropic
Google
Meta (Llama)
Mistral AI
XAI (Grok)
Cohere
Stability AI
DeepSeek
BFL (FLUX)
Cloudflare
BytePlus
Perplexity
Tavily
DataForSEO
Exa.AI
Parallel AI
Firecrawl
Moonshot AI
Runway
groq
Nvidia NIM
MiniMax
ElevenLabs
Serper
Fireworks.ai

Using built-in tools
Web Search
File Search
Code Interpreter
Shell
Computer Use
MCP and Connectors

Best Practices Overview
Prompt engineering
Production best practices
API Deployment Checklist
Data controls
Safety best practices
Safety checks
Red Teaming
Cost optimization
Citation formatting
Prompt Caching
Token counting
Predicted Outputs
Model selection
Latency optimization
Accuracy optimization
Advanced usage
Responses vs. Chat Completions
RAG best practices
Provider-Specific Parameters

Generate images with GPT Image
Stateful Responses Workflows
Durable Agent Memory with Embeddings
Manual RAG with Embeddings
Reasoning Models with Function Calls
Rate-Limit-Safe Parallel Requests
Promptfoo Evals with AvalAI
Agentic Guardrails for Schema Workflows
Web Search Capabilities
Processing PDFs in Chat Completions
Processing Audio in Gemini
Process documents using Mistral OCR
Processing Excel Files
Nano Banana Image Generation
Generate images using Google Imagen Models (Native API)
Edit images using Seedream
Direct Web Search
AI in Robotics with Gemini Robotics-ER
Building Conversational Apps with Audio Models
Speaker-Aware Meeting Intelligence
Image Generation with Gemini (Nano Banana Series)

Content Policy
Service Status
Contact Support
Privacy Policy

Need help?

Create a support ticket Debug with AvalAI Chat

Paste the current public documentation link into the Chat platform and ask the available models for help debugging.

Ask AI

Ask AvalAI Ask Claude Ask ChatGPT

Ask AI

Ask AvalAI Ask Claude Ask ChatGPT

Compare AI models

Compare two to four models using AvalAI facts and separately labeled external benchmark evidence.

Select at least two models to compare.

Return to Model Explorer

Privacy

Privacy settings

Essential browser storage keeps your settings. With your permission, we can also measure documentation performance or enable live third-party model data.

Select one privacy levelEssentialsAlways availableRemembers this choice and local reading preferences. No analytics and no optional third-party requests.Includes consent settings, theme and reading preferences, search, navigation, and first-party site operation.PerformanceOptionalAdds Google Analytics 4 so we can understand page visits and improve the documentation.Includes Essentials plus event-based page views, page title, route, language, and basic device and performance information. No advertising or personalization.Full featuresOptionalEnables performance measurement and optional live third-party model information.Includes Performance plus live OpenRouter model-data refreshes on supported model pages. Your IP address and request metadata may be visible to that provider.

We do not enable advertising storage, advertising user data, or advertising personalization. You can change this choice at any time.