# API100 — Unified Multi-Model AI API Infrastructure

> API100 is a high-performance, OpenAI-compatible AI gateway that provides developers with unified access to frontier and open-source AI models from Anthropic, OpenAI, Google, DeepSeek, and Meta through a single API key and wallet.

## Overview
- **Product**: API100 AI Gateway
- **Base URL**: https://api.apihundred.com/v1
- **Format**: 100% OpenAI-compatible Chat Completions format
- **Official Website**: https://apihundred.com
- **Developer Documentation**: https://apihundred.com/docs
- **Model Catalog**: https://apihundred.com/models
- **Live Benchmarks**: https://apihundred.com/benchmarks
- **Knowledge Hub**: https://apihundred.com/learn
- **Pricing**: https://apihundred.com/pricing
- **Security & Privacy**: https://apihundred.com/security
- **SLA & Uptime**: https://apihundred.com/sla
- **Company About**: https://apihundred.com/about

## Core Value Proposition & Architecture
1. **One Unified Gateway**: Replace 5+ vendor SDKs with one single endpoint (`https://api.apihundred.com/v1`).
2. **Drop-in OpenAI Parity**: Switch from OpenAI to Claude 3.5 Sonnet, DeepSeek R1, or Gemini 1.5 Pro by changing just two lines of code (`baseURL` and `apiKey`).
3. **100% Zero-Retention Privacy**: Prompts and completions are processed in volatile memory with zero disk logging and zero training on customer data.
4. **Sub-50ms Routing Overhead**: Ultra-low latency edge gateway with intelligent regional routing.
5. **Automated Multi-Provider Failover**: Automatic circuit breaking and failover when upstream providers experience rate limits or downtime.
6. **Unified Credit Wallet**: Single prepaid or pay-as-you-go balance across all models with transparent per-token deduction.

## Verified Models & Pricing (Per 1 Million Tokens)
- **Claude 3.5 Sonnet** (Anthropic) | Slug: `claude-3-5-sonnet` | Context: 200,000 | Input: $3.00 | Output: $15.00 | Strengths: Coding, Agentic Tool Use, Multimodal
- **GPT-4o** (OpenAI) | Slug: `gpt-4o` | Context: 128,000 | Input: $2.50 | Output: $10.00 | Strengths: General Reasoning, Vision, Structured Output
- **DeepSeek R1** (DeepSeek) | Slug: `deepseek-r1` | Context: 64,000 | Input: $0.55 | Output: $2.19 | Strengths: Math, Advanced Reasoning, Code Synthesis
- **Gemini 1.5 Pro** (Google) | Slug: `gemini-1-5-pro` | Context: 2,000,000 | Input: $1.25 | Output: $5.00 | Strengths: Massive Context, Document Analysis, Video
- **Gemini 1.5 Flash** (Google) | Slug: `gemini-1-5-flash` | Context: 1,000,000 | Input: $0.075 | Output: $0.30 | Strengths: Low Latency, High Throughput, Cost Efficiency
- **Llama 3.3 70B** (Meta) | Slug: `llama-3-3-70b-instruct` | Context: 128,000 | Input: $0.40 | Output: $0.40 | Strengths: Open Weights, Fast Inference, Summarization

## Code Examples

### Python (OpenAI SDK Drop-In)
```python
from openai import OpenAI

# Initialize client pointing to API100 Gateway
client = OpenAI(
    base_url="https://api.apihundred.com/v1",
    api_key="your_api100_api_key"
)

# Call any model (Claude, GPT, DeepSeek, Gemini, Llama) with identical syntax
response = client.chat.completions.create(
    model="claude-3-5-sonnet",
    messages=[
        {"role": "system", "content": "You are a senior software architect."},
        {"role": "user", "content": "Explain zero-retention gateway proxying."}
    ],
    temperature=0.7,
    stream=False
)

print(response.choices[0].message.content)
```

### TypeScript / Node.js
```typescript
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.apihundred.com/v1",
  apiKey: process.env.API100_API_KEY,
});

const stream = await client.chat.completions.create({
  model: "deepseek-r1",
  messages: [{ role: "user", content: "Optimize this SQL query for time-series indexing." }],
  stream: true,
});

for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content || "");
}
```

### cURL
```bash
curl https://api.apihundred.com/v1/chat/completions \
  -H "Authorization: Bearer $API100_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-1-5-pro",
    "messages": [{"role": "user", "content": "Summarize the latest trends in multi-model routing."}]
  }'
```

## IDE & Agent Integrations
- **Cursor**: Set OpenAI Base URL to `https://api.apihundred.com/v1` and use model `claude-3-5-sonnet` or `gpt-4o`.
- **VS Code Continue**: Configure `~/.continue/config.json` with provider `openai` and apiBase `https://api.apihundred.com/v1`.
- **Cline / Roo Code**: Select `OpenAI Compatible`, set base URL to `https://api.apihundred.com/v1`.
- **LangChain / LlamaIndex**: Set `openai_api_base="https://api.apihundred.com/v1"`.

## Performance Benchmarks (Empirical Telemetry)
- Median Time to First Token (TTFT): 290ms
- Average Generation Speed: 48 - 120 tokens/sec (provider dependent)
- Gateway Routing Overhead: < 45ms P95
- Network Availability: 99.98% measured uptime across 30-day window
- Full methodology & downloadable datasets: https://apihundred.com/benchmarks

## Knowledge Hub & Technical Guides (98 Comprehensive Evergreen AI & API Developer References)

### API Fundamentals & Developer Tutorials
- What is an API? A Beginner's Guide: https://apihundred.com/learn/what-is-an-api
- How Does an API Work (Request-Response Lifecycle): https://apihundred.com/learn/how-does-an-api-work
- What is a REST API (Architecture & Methods): https://apihundred.com/learn/what-is-a-rest-api
- What is an API Endpoint (URIs & Paths): https://apihundred.com/learn/what-is-an-api-endpoint
- What is an API Key (Authentication & Bearer Tokens): https://apihundred.com/learn/what-is-an-api-key
- What is a JSON API (Data Formats & Headers): https://apihundred.com/learn/what-is-a-json-api
- What is API Integration: https://apihundred.com/learn/what-is-api-integration
- How to Call an API Using JavaScript (Fetch & Axios): https://apihundred.com/learn/how-to-call-an-api-using-javascript
- How to Use an API with Python (Requests & HTTPX): https://apihundred.com/learn/how-to-use-api-with-python
- How to Call a REST API in C# .NET: https://apihundred.com/learn/how-to-call-rest-api-in-csharp
- How to Connect an API to a Database: https://apihundred.com/learn/how-to-connect-an-api-to-a-database
- How to Test APIs Using Postman: https://apihundred.com/learn/how-to-test-apis-using-postman
- How to Handle API Errors & HTTP Status Codes: https://apihundred.com/learn/how-to-handle-api-errors-and-status-codes
- How to Build an AI Chatbot Using an API: https://apihundred.com/learn/how-to-build-an-ai-chatbot-using-api
- What is an AI Inference API: https://apihundred.com/learn/what-is-an-inference-api
- What is a Multimodal API: https://apihundred.com/learn/what-is-a-multimodal-api

### Frontier Models & Reasoning
- GPT-6 Astra API (Computer Use & Software Engineering): https://apihundred.com/learn/gpt-6-astra-agentic-architecture-api
- GPT-6 Sol & GPT-6 Luna Token Economics: https://apihundred.com/learn/gpt-6-sol-and-luna-cost-efficiency
- GPT-5.6 Sol, Terra & Luna Architecture: https://apihundred.com/learn/gpt-5-6-sol-terra-luna-architecture
- GPT-Live 1 Realtime Voice API: https://apihundred.com/learn/gpt-live-1-and-realtime-voice-apis
- Gemini 3.8 Flash API & Thinking Budgets: https://apihundred.com/learn/gemini-3-8-flash-api-guide
- Gemini 3.7 Flash, 3.6 Flash & 3.1 Pro Ecosystem: https://apihundred.com/learn/gemini-3-7-and-3-6-flash-ecosystem
- Gemini Live & Live Extended Thinking: https://apihundred.com/learn/gemini-live-and-extended-thinking
- Gemini Omni Flash & Nano Banana Pro: https://apihundred.com/learn/gemini-omni-flash-and-nano-banana
- Claude Opus 5.5 & Sonnet 5 (Frontier Coding): https://apihundred.com/learn/claude-opus-5-5-and-sonnet-5
- Claude Haiku 4.5 & Fable 5.1 (High-Speed Inference): https://apihundred.com/learn/claude-haiku-4-5-and-fable
- GPT-6 vs Claude 5 vs Gemini 3.8 Comparison: https://apihundred.com/learn/gpt-vs-claude-vs-gemini-api-comparison
- Grok 4.7 API (Colossus Supercluster Reasoning): https://apihundred.com/learn/grok-4-7-reasoning-api
- DeepSeek-R1 Architecture & Reasoning API: https://apihundred.com/learn/deepseek-r1-architecture-reasoning-api
- DeepSeek-V3 MoE Architecture & MLA: https://apihundred.com/learn/deepseek-v3-moe-architecture-explained
- Meta Llama 4 Scout & Llama 3.1 405B Frontier: https://apihundred.com/learn/meta-llama-4-scout-and-405b-frontier
- Meta Llama 3.3 70B & 405B Production: https://apihundred.com/learn/llama-3-3-70b-and-405b-deployment
- Qwen 2.5 Coder 32B Code Generation: https://apihundred.com/learn/qwen-2-5-coder-and-deep-reasoning
- Mistral Large 2, Codestral & Pixtral: https://apihundred.com/learn/mistral-large-codestral-pixtral-guide
- Microsoft Phi-4 & Cohere Command R+: https://apihundred.com/learn/microsoft-phi-4-and-cohere-command-r
- NVIDIA Nemotron 70B & 340B Alignment: https://apihundred.com/learn/nvidia-nemotron-synthetic-data-models

### Multimodal & Audio APIs
- GPT-Image-2.5 Sunburst, Flare, and FLUX.1: https://apihundred.com/learn/gpt-image-2-5-sunburst-and-flux
- GPT-Transcribe & Gemini Flash TTS Voice APIs: https://apihundred.com/learn/gpt-transcribe-and-gemini-tts
- Gemini Embedding 2 vs text-embedding-3: https://apihundred.com/learn/gemini-embedding-2-and-rag
- Speech-to-Speech & WebRTC Real-Time Voice: https://apihundred.com/learn/speech-to-speech-realtime-voice-agents
- Vision LLM APIs & Image Understanding: https://apihundred.com/learn/vision-llm-apis-image-understanding
- Multimodal Document Parsing & OCR: https://apihundred.com/learn/multimodal-document-parsing-and-ocr
- Reranking Models & Cross-Encoders: https://apihundred.com/learn/reranking-models-and-cross-encoders
- Video Understanding & Generation APIs (Sora): https://apihundred.com/learn/video-understanding-and-generation-apis

### Core Fundamentals
- What is an AI API: https://apihundred.com/learn/what-is-an-ai-api
- What is an LLM: https://apihundred.com/learn/what-is-an-llm
- What is an LLM API: https://apihundred.com/learn/what-is-an-llm-api
- Context Windows & Token Limits: https://apihundred.com/learn/context-window-tokens-explained
- How to Choose the Best AI API: https://apihundred.com/learn/how-to-choose-the-best-ai-api
- Temperature, Top-P, and Top-K Sampling: https://apihundred.com/learn/what-is-temperature-and-top-p-in-llms
- System Prompts vs User Prompts: https://apihundred.com/learn/system-prompts-vs-user-prompts
- What is Retrieval-Augmented Generation (RAG): https://apihundred.com/learn/what-is-retrieval-augmented-generation-rag
- Fine-Tuning vs RAG vs Prompt Engineering: https://apihundred.com/learn/fine-tuning-vs-rag-vs-prompt-engineering
- What is Mixture-of-Experts (MoE): https://apihundred.com/learn/what-is-mixture-of-experts-moe

### Architecture & Gateway Infrastructure
- What is an AI Gateway: https://apihundred.com/learn/what-is-an-ai-gateway
- Multi-Model Routing & Failover: https://apihundred.com/learn/multi-model-routing-and-failover
- AI Inference Latency (TTFT & TPS): https://apihundred.com/learn/ai-inference-latency-explained
- Streaming AI Responses (SSE): https://apihundred.com/learn/streaming-ai-responses-sse
- Zero Data Retention in AI: https://apihundred.com/learn/zero-data-retention-ai-privacy
- Semantic Caching with Vector Redis: https://apihundred.com/learn/semantic-caching-for-ai-applications
- Load Balancing AI Providers: https://apihundred.com/learn/load-balancing-ai-providers-at-scale
- GPU Cold Starts & vLLM Orchestration: https://apihundred.com/learn/cold-starts-and-gpu-orchestration-in-ai
- WebRTC vs WebSockets vs SSE for AI: https://apihundred.com/learn/webrtc-and-websockets-for-ai-streaming
- Speculative Decoding Inference Acceleration: https://apihundred.com/learn/speculative-decoding-explained
- Tensor Parallelism vs Pipeline Parallelism: https://apihundred.com/learn/distributed-inference-and-tensor-parallelism

### Token Economics & Cost Optimization
- Cheapest LLM APIs in 2026: https://apihundred.com/learn/cheapest-llm-apis-cost-comparison
- OpenAI-Compatible API Endpoint Guide: https://apihundred.com/learn/openai-compatible-api-endpoint-guide
- LLM Token Pricing Explained: https://apihundred.com/learn/llm-token-pricing-explained
- Prompt Caching Cost Optimization: https://apihundred.com/learn/prompt-caching-cost-optimization
- LLM Rate Limits & Concurrency: https://apihundred.com/learn/llm-rate-limits-and-concurrency
- Batch API vs Real-Time Inference (50% Off): https://apihundred.com/learn/batch-api-pricing-vs-realtime-inference
- How to Calculate & Forecast LLM Costs: https://apihundred.com/learn/how-to-calculate-and-forecast-llm-costs
- Context Caching vs Prompt Caching: https://apihundred.com/learn/context-caching-vs-prompt-caching
- How to Reduce AI API Costs by 80%: https://apihundred.com/learn/how-to-reduce-ai-api-costs-by-80-percent
- Cost-Per-Task Evaluation: https://apihundred.com/learn/evaluating-cost-per-task-in-ai-apps
- Tier-Based Rate Limits & Enterprise Quotas: https://apihundred.com/learn/tier-based-rate-limits-and-enterprise-quotas

### Engineering & Autonomous Agents
- How to Integrate AI APIs into Next.js: https://apihundred.com/learn/how-to-integrate-ai-api-into-nextjs
- Which AI API to Build Coding Agents: https://apihundred.com/learn/which-ai-api-to-build-coding-agents
- Building Autonomous AI Agents: https://apihundred.com/learn/building-ai-agents-with-apis
- Function Calling & Tool Use: https://apihundred.com/learn/function-calling-and-tool-use
- Structured JSON Outputs: https://apihundred.com/learn/structured-json-outputs
- Open Weights vs. Closed Models: https://apihundred.com/learn/open-weights-vs-closed-frontier-models
- Model Context Protocol (MCP) Guide: https://apihundred.com/learn/model-context-protocol-mcp-guide
- The ReAct Agent Pattern (Reason + Act): https://apihundred.com/learn/react-agent-pattern-reasoning-and-action
- AI Code Execution Sandboxes (E2B & Docker): https://apihundred.com/learn/ai-code-execution-sandboxes-e2b-docker
- LLM-as-a-Judge Automated Evaluation: https://apihundred.com/learn/evaluating-llm-outputs-with-llm-as-a-judge
- LangChain vs LlamaIndex vs Raw APIs: https://apihundred.com/learn/langchain-vs-llamaindex-vs-raw-apis
- Prompt Injection & Jailbreak Defense: https://apihundred.com/learn/prompt-injection-prevention-and-jailbreak-defense
- Deterministic AI Outputs with Seed: https://apihundred.com/learn/deterministic-ai-outputs-with-seed-and-temperature
- Multi-Agent Orchestration (CrewAI & LangGraph): https://apihundred.com/learn/multi-agent-orchestration-crewai-autogen

### Security, Privacy & Enterprise Compliance
- AI API Security & Best Practices: https://apihundred.com/learn/ai-api-security-and-best-practices
- HIPAA & GDPR Compliance for AI APIs: https://apihundred.com/learn/hipaa-and-gdpr-compliance-for-ai-apis
- PII Redaction & Data Masking in AI: https://apihundred.com/learn/pii-redaction-and-data-masking-in-ai
- AI Guardrails (NeMo & Llama Guard): https://apihundred.com/learn/guardrails-nemo-llama-guard-in-production
- Enterprise SSO & RBAC for AI Access: https://apihundred.com/learn/enterprise-sso-and-rbac-for-ai-access
- Data Poisoning & OWASP Top 10 for LLMs: https://apihundred.com/learn/data-poisoning-and-model-vulnerabilities
- SOC 2 Type II Compliance in AI Infra: https://apihundred.com/learn/soc2-type-2-compliance-in-ai-infrastructure
- Private VPC & Air-Gapped AI Gateways: https://apihundred.com/learn/private-vpc-and-on-premise-ai-gateways

## Support & Community
- Developer Forum: https://community.apihundred.com
- Technical Inquiries: support@apihundred.com
- Status & Telemetry: https://apihundred.com/benchmarks