LLM Provider Manager
6
Connected
27
Available Models
99.7%
Avg Uptime
$47.67
Cost Today
O
OpenAI
Connected8 models340ms avg latency99.9% uptime (24h)
Models
| Model ID | Context | Input Cost | Output Cost | Enabled |
|---|---|---|---|---|
| gpt-4o | 128k | $2.5/M | $10/M | |
| gpt-4o-mini | 128k | $2.5/M | $10/M | |
| gpt-4-turbo | 128k | $2.5/M | $10/M | |
| gpt-3.5-turbo | 128k | $2.5/M | $10/M | |
| o1 | 128k | $2.5/M | $10/M | |
| o1-mini | 128k | $2.5/M | $10/M | |
| o3-mini | 128k | $2.5/M | $10/M | |
| dall-e-3 | 128k | $2.5/M | $10/M |
Usage today: 2.4M tokensCost today: $24.15No failures
Active
A
Anthropic
Connected4 models520ms avg latency99.8% uptime (24h)
Models
| Model ID | Context | Input Cost | Output Cost | Enabled |
|---|---|---|---|---|
| claude-sonnet-4-20250514 | 200k | $3/M | $15/M | |
| claude-haiku-3-5 | 200k | $3/M | $15/M | |
| claude-opus-4 | 200k | $3/M | $15/M | |
| claude-3-5-sonnet-latest | 200k | $3/M | $15/M |
Usage today: 1.8M tokensCost today: $18.722 failures
Active
G
Google AI
Connected3 models410ms avg latency99.7% uptime (24h)
Models
| Model ID | Context | Input Cost | Output Cost | Enabled |
|---|---|---|---|---|
| gemini-2.0-flash | 128k | $1.5/M | $7.5/M | |
| gemini-2.0-pro | 128k | $1.5/M | $7.5/M | |
| gemini-1.5-pro | 128k | $1.5/M | $7.5/M |
Usage today: 0.6M tokensCost today: $4.80No failures
Active
L
Local (Ollama)
Connected12 models1.2s avg latency98.5% uptime (24h)
Models
| Model ID | Context | Input Cost | Output Cost | Enabled |
|---|---|---|---|---|
| llama3.3-70b | 32k | $0/M | $0/M | |
| llama3.2-8b | 32k | $0/M | $0/M | |
| mixtral-8x7b | 32k | $0/M | $0/M | |
| deepseek-coder-v2 | 32k | $0/M | $0/M | |
| codellama-34b | 32k | $0/M | $0/M | |
| mistral-7b | 32k | $0/M | $0/M | |
| qwen2.5-72b | 32k | $0/M | $0/M | |
| phi-3-mini | 32k | $0/M | $0/M | |
| neural-chat-7b | 32k | $0/M | $0/M | |
| starling-lm-7b | 32k | $0/M | $0/M | |
| dolphin-mixtral | 32k | $0/M | $0/M | |
| orca-mini | 32k | $0/M | $0/M |
Usage today: 7.6M tokensCost today: $0.00No failures
Active
G
Groq
Connected3 models180ms avg latency99.6% uptime (24h)
Models
| Model ID | Context | Input Cost | Output Cost | Enabled |
|---|---|---|---|---|
| llama3-70b-8192 | 128k | $0.7/M | $0.8/M | |
| mixtral-8x7b-32768 | 128k | $0.7/M | $0.8/M | |
| gemma2-9b-it | 128k | $0.7/M | $0.8/M |
Usage today: 0.3M tokensCost today: $0.21No failures
Active
T
Together AI
Connected5 models280ms avg latency99.5% uptime (24h)
Models
| Model ID | Context | Input Cost | Output Cost | Enabled |
|---|---|---|---|---|
| llama3.3-70b | 128k | $0.9/M | $0.9/M | |
| mixtral-8x22b | 128k | $0.9/M | $0.9/M | |
| deepseek-v2 | 128k | $0.9/M | $0.9/M | |
| Qwen2-72B | 128k | $0.9/M | $0.9/M | |
| dbrx-instruct | 128k | $0.9/M | $0.9/M |
Usage today: 0.2M tokensCost today: $0.181 failures
Active