Ultra low-latency unified API gateway routing to 40+ world-class AI models (Claude Sonnet 5, Gemini 3.7 Flash, GPT-5.6, DeepSeek V4, Llama 4, Qwen 3.8). 100% OpenAI SDK compatible.
Use a single shared credit balance to invoke all models below. Simply pass the model parameter in your request payload.
| Provider | Model Name | Model ID (Click to Copy) | Prompt (1M) | Completion (1M) | Status | Action |
|---|---|---|---|---|---|---|
|
Anthropic
|
Claude Sonnet 5 (Frontier) |
claude-sonnet-5
|
$2.0000 | $10.0000 | Available | |
|
Anthropic
|
Claude Opus 5 (Maximum Power) |
claude-opus-5
|
$5.0000 | $25.0000 | Available | |
|
Anthropic
|
Claude 3.5 Sonnet (Coding) |
claude-3.5-sonnet
|
$0.0000 | $0.0000 | Available | |
|
Anthropic
|
Claude 3.5 Haiku (Fast) |
claude-3.5-haiku
|
$0.0000 | $0.0000 | Available | |
|
Anthropic
|
Claude 3 Opus (Deep Analysis) |
claude-3-opus
|
$0.0000 | $0.0000 | Available | |
|
Gemini
|
Gemini 3.7 Flash (Next-Gen) |
gemini-3.7-flash
|
$0.7500 | $3.7500 | Available | |
|
Gemini
|
Gemini 3.6 Flash (High-Speed) |
gemini-3.6-flash
|
$0.7500 | $3.7500 | Available | |
|
Gemini
|
Gemini 3.5 Flash Lite |
gemini-3.5-flash-lite
|
$0.3000 | $2.5000 | Available | |
|
Gemini
|
Gemini 2.5 Flash (1M Context) |
gemini-2.5-flash
|
$0.3000 | $2.5000 | Available | |
|
Gemini
|
Gemini 1.5 Pro (Multimodal) |
gemini-1.5-pro
|
$0.0000 | $0.0000 | Available | |
|
OpenAI
|
GPT-5.6 Luna Pro (Agentic) |
gpt-5.6-luna-pro
|
$0.2000 | $1.2000 | Available | |
|
OpenAI
|
GPT-5.6 Terra Pro |
gpt-5.6-terra-pro
|
$2.0000 | $12.0000 | Available | |
|
OpenAI
|
GPT-5.4 Mini |
gpt-5.4-mini
|
$0.7500 | $4.5000 | Available | |
|
OpenAI
|
GPT-4o (Omni Flagship) |
gpt-4o
|
$2.5000 | $10.0000 | Available | |
|
OpenAI
|
GPT-4o Mini (Ultra Fast) |
gpt-4o-mini
|
$0.1500 | $0.6000 | Available | |
|
OpenAI
|
o1 Mini (STEM Reasoning) |
o1-mini
|
$0.0000 | $0.0000 | Available | |
|
DeepSeek
|
DeepSeek V4 Pro (Frontier) |
DeepSeek-V4-Pro
|
$0.6600 | $1.9800 | Available | |
|
DeepSeek
|
DeepSeek V4 Flash |
DeepSeek-V4-Flash
|
$0.0795 | $0.1590 | Available | |
|
DeepSeek
|
DeepSeek V3 (Flagship) |
DeepSeek-V3
|
$0.2574 | $1.0287 | Available | |
|
DeepSeek
|
DeepSeek R1 (Reasoner) |
DeepSeek-R1
|
$0.7000 | $2.5000 | Available | |
|
Meta
|
Llama 4 Maverick (Frontier) |
llama-4-maverick
|
$0.2000 | $0.8000 | Available | |
|
Meta
|
Llama 4 Scout (Long-Context) |
llama-4-scout
|
$0.1100 | $0.3400 | Available | |
|
Meta
|
Llama 3.3 70B (SOTA Open) |
llama-3.3-70b
|
$0.7100 | $0.7100 | Available | |
|
Meta
|
Llama 3.1 405B (Massive) |
llama-3.1-405b
|
$0.0000 | $0.0000 | Available | |
|
Qwen
|
Qwen 3.8 27B (Next-Gen) |
qwen-3.8-27b
|
$0.4250 | $2.5500 | Available | |
|
Qwen
|
Qwen 3.8 Max |
qwen-3.8-max
|
$2.0000 | $6.0000 | Available | |
|
Qwen
|
Qwen 3.7 Flash (Ultra Low Cost) |
qwen-3.7-flash
|
$0.0300 | $0.1300 | Available | |
|
Qwen
|
Qwen 2.5 72B (Multilingual) |
qwen-2.5-72b
|
$0.3600 | $0.4000 | Available | |
|
Qwen
|
Qwen 2.5 Coder 32B |
qwen-2.5-coder-32b
|
$0.6600 | $1.0000 | Available | |
|
xAI
|
Grok 4.6 (Next-Gen Flagship) |
grok-4.6
|
$2.0000 | $6.0000 | Available | |
|
xAI
|
Grok 4.5 |
grok-4.5
|
$2.0000 | $6.0000 | Available | |
|
xAI
|
Grok 2 Beta |
grok-2
|
$0.0000 | $0.0000 | Available | |
|
Mistral
|
Mistral Large 2 |
mistral-large-2
|
$0.5000 | $1.5000 | Available | |
|
Mistral
|
Mistral Small 24B |
mistral-small-24b
|
$0.0500 | $0.0800 | Available | |
|
Mistral
|
Codestral 2508 (Code Engine) |
codestral-2508
|
$0.3000 | $0.9000 | Available | |
|
Moonshot
|
Moonshot Kimi K3 (Next-Gen) |
kimi-k3
|
$3.0000 | $15.0000 | Available | |
|
Moonshot
|
Kimi K2.7 Code (Programming) |
kimi-k2.7-code
|
$0.6600 | $3.4000 | Available | |
|
Perplexity
|
Sonar (Online Web Search) |
sonar-search
|
$1.0000 | $1.0000 | Available | |
|
Perplexity
|
Sonar Reasoning Pro |
sonar-reasoning
|
$2.0000 | $8.0000 | Available | |
|
Cohere
|
Command R+ (Enterprise RAG) |
command-r-plus
|
$2.5000 | $10.0000 | Available |
Enjoy an exclusive 50% Launch Discount on all USD credit balances. Transparent deduction per request with lifetime validity.
import openai
client = openai.OpenAI(
api_key='tk-your-api-key-here',
base_url='https://onerouter.web.id/v1'
)
response = client.chat.completions.create(
model='DeepSeek-V3',
messages=[
{'role': 'user', 'content': 'Hello from OneRouter (onerouter.web.id)!'}
]
)
print(response.choices[0].message.content)Live 24/7 endpoint availability and latency metrics across all neural networks.
100% drop-in replacement compatible with official OpenAI SDKs and tooling.
https://onerouter.web.id/v1
Set this endpoint as your base URL in the OpenAI SDK, LangChain, LlamaIndex, LiteLLM, or cURL.
Bearer tk-xxxxxxxxxxxxxxxx
Include your OneRouter API key in the Authorization: Bearer <key> HTTP header.
POST /v1/chat/completions
Standard chat completions endpoint supporting model, messages, temperature, stream.
GET /v1/models
Retrieve the complete, dynamically updated catalog of active models in standard OpenAI JSON format.