Documentation Index
Fetch the complete documentation index at: /llms.txt
Use this file to discover all available pages before exploring further.
All AI models and providers available through the OpenModex gateway.
| Model | Context | Best For | Features |
|---|---|---|---|
gpt-4o | 128K | General purpose, vision | Streaming, Function Calling, JSON Mode, Vision |
gpt-4o-mini | 128K | Cost-effective tasks | Streaming, Function Calling, JSON Mode |
o1 | 200K | Complex reasoning | Chain-of-thought |
o3 | 200K | Advanced reasoning | Chain-of-thought |
gpt-4-turbo | 128K | Legacy compatibility | Streaming, Function Calling, Vision |
| Model | Context | Best For | Features |
|---|---|---|---|
claude-3.5-sonnet | 200K | Code, analysis, long context | Streaming, Tool Use |
claude-3-opus | 200K | Complex tasks, research | Streaming, Tool Use |
claude-3-haiku | 200K | Fast, cost-effective | Streaming, Tool Use |
| Model | Context | Best For | Features |
|---|---|---|---|
gemini-2.0-flash | 1M | Speed, multimodal | Streaming, Function Calling, Vision |
gemini-1.5-pro | 2M | Long documents, analysis | Streaming, Function Calling, Vision |
gemini-1.5-flash | 1M | Balance of speed & quality | Streaming, Function Calling |
| Model | Context | Best For | Features |
|---|---|---|---|
deepseek-chat | 128K | General purpose, cost savings | Streaming |
deepseek-reasoner | 128K | Reasoning, math, code | Streaming, Chain-of-thought |
| Model | Context | Best For | Features |
|---|---|---|---|
mistral-large | 128K | Enterprise, multilingual | Streaming, Function Calling |
mistral-small | 128K | Cost-effective, fast | Streaming |
codestral | 32K | Code generation | Streaming |
| Model | Context | Best For | Features |
|---|---|---|---|
qwen-max | 128K | Chinese language, general purpose | Streaming |
qwen2.5-72b | 128K | Open-weight, versatile | Streaming |
qwen2.5-coder | 128K | Code generation | Streaming |
| Model | Dimensions | Provider | Best For |
|---|---|---|---|
text-embedding-3-small | 1536 | OpenAI | Cost-effective embeddings |
text-embedding-3-large | 3072 | OpenAI | High-precision embeddings |
text-embedding-ada-002 | 1536 | OpenAI | Legacy compatibility |
| Priority | Recommended |
|---|---|
| Cheapest | gpt-4o-mini, deepseek-chat, gemini-2.0-flash |
| Fastest | gemini-2.0-flash, gpt-4o-mini, claude-3-haiku |
| Best quality | gpt-4o, claude-3.5-sonnet, gemini-1.5-pro |
| Best at code | claude-3.5-sonnet, deepseek-reasoner, codestral |
| Longest context | gemini-1.5-pro (2M), gemini-2.0-flash (1M) |
| Best reasoning | o3, o1, deepseek-reasoner |
const response = await client.chat.completions.create({
model: 'auto',
messages: [{ role: 'user', content: 'Hello!' }],
routing: { strategy: 'cost_optimized' },
});
# List all models with pricing
curl https://api.openmodex.com/v1/models \
-H "Authorization: Bearer omx_sk_YOUR_KEY"
# Compare specific models
curl "https://api.openmodex.com/v1/models/compare?models=openai/gpt-4o,anthropic/claude-3.5-sonnet" \
-H "Authorization: Bearer omx_sk_YOUR_KEY"