Unified OpenAI-compatible interface for 100+ AI models. Input/output flat rate, no hidden fees, save up to 70% vs direct API.
โ 100% OpenAI Compatible ยท Works with LangChain, Cursor, NextChat ยท Zero Code Changes Required
YOUR-API-KEY with your actual API key from the Dashboard. Never share your API key publicly.
# 1. Get your API key โ Sign up at llmbridge.io โ Go to Dashboard โ API Keys โ Copy your key # 2. Set environment variable (recommended) export OPENAI_API_KEY="your-api-key-here" # Or set in code: api_key="your-api-key-here" # 3. Test your setup curl https://llmbridge.io/v1/models \ -H "Authorization: Bearer your-api-key-here"
๐น All prices are input/output flat rate per 1M tokens, no extra fees
| Model | Provider | Context | Price / 1M Tokens | vs OpenAI |
|---|---|---|---|---|
| GPT-4o | OpenAI | 128K | $4.99 | โ 50% |
| GPT-4o Mini | OpenAI | 128K | $0.99 | โ 50% |
| GPT-4 Turbo | OpenAI | 128K | $9.99 | โ 50% |
| GPT-3.5 Turbo | OpenAI | 16K | $0.99 | โ 50% |
| Claude-3.5 Sonnet | Anthropic | 200K | $3.99 | โ 50% |
| Claude-3 Opus | Anthropic | 200K | $14.99 | โ 50% |
| Claude-3 Haiku | Anthropic | 200K | $0.99 | โ 50% |
| Gemini-1.5 Pro | 1M | $1.99 | โ 50% | |
| Gemini-1.5 Flash | 1M | $0.49 | โ 50% |
| Model | Provider | Context | Price / 1M Tokens | Best For |
|---|---|---|---|---|
| Llama-3.1 70B | Meta | 128K | $0.88 | Reasoning, Coding |
| Llama-3.1 8B | Meta | 128K | $0.22 | Fast, Efficient |
| Mistral-Nemo | Mistral | 128K | $0.49 | Multilingual |
| Mistral-Large | Mistral | 128K | $2.99 | Complex Tasks |
| Qwen-2.5 72B | Alibaba | 128K | $0.99 | Coding, Math |
| Qwen-2.5 7B | Alibaba | 128K | $0.25 | Fast Inference |
| Yi-34B | 01.AI | 200K | $0.99 | Long Context |
| DeepSeek-V2.5 | DeepSeek | 128K | $0.49 | Coding, Math |
| CodeLlama-70B | Meta | 128K | $0.88 | Code Generation |
| Gemma-2-27B | 8K | $0.49 | Lightweight |
๐ฐ All Closed-Source Models: Save 50-70% vs Direct API
Zero code changes required ยท 100% OpenAI SDK compatible ยท Instant access
Get API key in 10 seconds.
Save up to 70% vs direct API.
Change one line of code.
Low latency worldwide.
99.9% uptime.
Encryption in transit.