🤖 Supported Providers
Providers Supportés
Monitorez les coûts de tous les providers d'IA majeurs dans un seul dashboard
OpenAI
GPT-4o, GPT-4o-mini, DALL-E 3
Fully SupportedSupported Models
| Model | Input Price | Output Price | Use Case |
|---|---|---|---|
| GPT-4o | $2.50 / 1M tokens | $10.00 / 1M tokens | Advanced Tasks |
| GPT-4o-mini | $0.15 / 1M tokens | $0.60 / 1M tokens | Cost-Effective |
| GPT-4 Turbo | $10.00 / 1M tokens | $30.00 / 1M tokens | High Performance |
| DALL-E 3 | $0.040 / image (1024x1024) | Image Generation | |
Anthropic
Claude 3.5 Sonnet, Haiku, Opus
Fully SupportedSupported Models
| Model | Input Price | Output Price | Use Case |
|---|---|---|---|
| Claude 3.5 Sonnet | $3.00 / 1M tokens | $15.00 / 1M tokens | Balanced Performance |
| Claude 3.5 Haiku | $0.80 / 1M tokens | $4.00 / 1M tokens | Fast & Affordable |
| Claude 3 Opus | $15.00 / 1M tokens | $75.00 / 1M tokens | Highest Intelligence |
Mistral AI
Mistral Large, Small, Medium
Fully SupportedSupported Models
| Model | Input Price | Output Price | Use Case |
|---|---|---|---|
| Mistral Large | $2.00 / 1M tokens | $6.00 / 1M tokens | Complex Reasoning |
| Mistral Small | $0.20 / 1M tokens | $0.60 / 1M tokens | Budget-Friendly |
| Mistral Medium | $0.70 / 1M tokens | $2.10 / 1M tokens | General Purpose |
Replicate
Flux Pro, SDXL, Stable Diffusion
Fully SupportedSupported Models
| Model | Price per Image | Resolution | Use Case |
|---|---|---|---|
| Flux Pro | $0.055 / image | Up to 1440px | Professional Quality |
| SDXL | $0.004 / image | 1024x1024 | Cost-Effective |
| Stable Diffusion 1.5 | $0.001 / image | 512x512 | Rapid Prototyping |
Google Gemini
Gemini Pro, Ultra, 1.5-Pro
Fully SupportedSupported Models
| Model | Input Price | Output Price | Use Case |
|---|---|---|---|
| Gemini 1.5 Pro | $1.25 / 1M tokens | $5.00 / 1M tokens | Long Context |
| Gemini Pro | $0.50 / 1M tokens | $1.50 / 1M tokens | General Purpose |
| Gemini Ultra | $1.25 / 1M tokens | $3.75 / 1M tokens | Advanced Reasoning |
xAI Grok
Grok-1, Grok-1.5
Fully SupportedSupported Models
| Model | Input Price | Output Price | Use Case |
|---|---|---|---|
| Grok-1.5 | $7.50 / 1M tokens | $22.50 / 1M tokens | Real-Time Data |
| Grok-1 | $5.00 / 1M tokens | $15.00 / 1M tokens | Conversational AI |
Meta Llama
Llama 2, Llama 3
Fully SupportedSupported Models (via Together.ai, Replicate)
| Model | Input Price | Output Price | Use Case |
|---|---|---|---|
| Llama 3 70B | $1.10 / 1M tokens | $1.10 / 1M tokens | Open Source |
| Llama 3 8B | $0.20 / 1M tokens | $0.20 / 1M tokens | Ultra Low Cost |
| Llama 2 70B | $0.90 / 1M tokens | $0.90 / 1M tokens | Legacy Support |
DeepSeek
Chat, Coder
Fully SupportedSupported Models
| Model | Input Price | Output Price | Use Case |
|---|---|---|---|
| DeepSeek Chat | $0.14 / 1M tokens | $0.28 / 1M tokens | Extremely Affordable |
| DeepSeek Coder | $0.14 / 1M tokens | $0.28 / 1M tokens | Code Generation |
Best Value! DeepSeek offers exceptional quality at a fraction of the cost of other providers.
Perplexity
70B Online, 7B Online
Fully SupportedSupported Models
| Model | Input Price | Output Price | Use Case |
|---|---|---|---|
| PPLX 70B Online | $1.00 / 1M tokens | $1.00 / 1M tokens | Real-Time Search |
| PPLX 7B Online | $0.20 / 1M tokens | $0.20 / 1M tokens | Fast Search |
Alibaba Qwen
Qwen Turbo, Plus, Max
Fully SupportedSupported Models
| Model | Input Price | Output Price | Use Case |
|---|---|---|---|
| Qwen Max | $2.00 / 1M tokens | $6.00 / 1M tokens | High Performance |
| Qwen Plus | $0.80 / 1M tokens | $2.00 / 1M tokens | Balanced |
| Qwen Turbo | $0.30 / 1M tokens | $0.60 / 1M tokens | Cost-Effective |
Moonshot Kimi
Kimi Chat
Fully SupportedSupported Models
| Model | Input Price | Output Price | Use Case |
|---|---|---|---|
| Kimi Chat | $1.20 / 1M tokens | $1.20 / 1M tokens | Long Context (200K+) |
Ultra Long Context: Kimi excels at handling extremely long conversations and documents (200K+ tokens).
💰 Cost Comparison
Compare Costs Across Providers
See how much you could save by switching models or providers
Example: Processing 10M Tokens (Input + Output)
| Provider | Model | Cost (10M tokens) | Savings vs GPT-4o |
|---|---|---|---|
| OpenAI | GPT-4 Turbo | $200.00 | -220% |
| Anthropic | Claude 3 Opus | $450.00 | -620% |
| OpenAI | GPT-4o (Baseline) | $62.50 | - |
| Anthropic | Claude 3.5 Sonnet | $90.00 | -44% |
| Mistral | Mistral Large | $40.00 | +36% |
| OpenAI | GPT-4o-mini | $3.75 | +94% |
| Anthropic | Claude 3.5 Haiku | $24.00 | +62% |
| Mistral | Mistral Small | $4.00 | +94% |
Tip: Our recommendation engine automatically suggests the most cost-effective model for your use case.
🔌 Integration
Easy Integration for All Providers
Use our unified proxy for all AI providers. Just change the base URL.
OpenAI Integration
import openai
openai.api_base = "https://api.cost-monitor.com/proxy/openai"
openai.api_key = "your_project_token"
response = openai.ChatCompletion.create(
model="gpt-4o",
messages=[{"role": "user", "content": "Hello!"}]
)Anthropic Integration
import anthropic
client = anthropic.Anthropic(
api_key="your_project_token",
base_url="https://api.cost-monitor.com/proxy/anthropic"
)
response = client.messages.create(
model="claude-3-5-sonnet-20240620",
messages=[{"role": "user", "content": "Hello!"}]
)Mistral Integration
from mistralai.client import MistralClient
client = MistralClient(
api_key="your_project_token",
endpoint="https://api.cost-monitor.com/proxy/mistral"
)
response = client.chat(
model="mistral-large-latest",
messages=[{"role": "user", "content": "Hello!"}]
)Replicate Integration
import replicate
replicate.api_base_url = "https://api.cost-monitor.com/proxy/replicate"
replicate.api_token = "your_project_token"
output = replicate.run(
"black-forest-labs/flux-pro",
input={"prompt": "A beautiful sunset"}
)
FAQ
Frequently Asked Questions
Monitor all your AI providers in one place
Start tracking your OpenAI, Anthropic, Mistral, and Replicate costs today.
Start Free Trial