GPT-4o
OpenAI
Context
128k Tokens
Cost / 1M
$5.00
TEXTVISIONAUDIO
Model Management
Model Performance Matrix
High Quality Low Latency
Quality Score
Latency (ms)
GPT-4o (98/120ms)
Claude 3.5 Sonnet (94/180ms)
Llama 3 70B (88/240ms)
Mistral Large (91/310ms)
Available Models
Claude 3.5 Sonnet
Anthropic
Context
200k Tokens
Cost / 1M
$3.00
TEXTVISION
Llama 3.1 405B
Meta / Open Source
Context
128k Tokens
Cost / 1M
$0.80
TEXTCODE
Custom Model Endpoints
| Endpoint Name | Base URL | Status | Latency | Actions |
|---|---|---|---|---|
Local-Llama-FineTune | http://192.168.1.45:8000/v1 | ONLINE | 42ms | |
Corporate-Mistral-Proxy | https://ai-proxy.internal.co | STANDBY | -- |