🤖
2,100
Models Tracked
🏢
116
Providers
📊
5
Categories
⏱️
6h
Update Frequency
Categories
budget: 945standard: 711flagship: 261code: 118embedding: 65
💰 Top 10 Cheapest Models
View all →Sorted by input price per million tokens
| Model | Input/M | Output/M | Context | Category |
|---|---|---|---|---|
|
Gemini 1.5 Flash Exp 0827🏆 Best Value
vertex_ai-language-models
|
$0.0047 | $0.0047 | 1.0M | budget |
|
Qwen2.5 Coder 3b Instruct
nscale
|
$0.010 | $0.030 | 0 | code |
|
Qwen2.5 Coder 7b Instruct
nscale
|
$0.010 | $0.030 | 0 | code |
|
Llama3.2 11b Vision Instruct
lambda_ai
|
$0.015 | $0.025 | 131k | budget |
|
Llama3.2 3b Instruct
lambda_ai
|
$0.015 | $0.025 | 131k | budget |
|
IBM: Granite 4.0 Micro
ibm-granite
|
$0.017 | $0.110 | 131k | budget |
|
Google: Gemma 3 4B
google
|
$0.017 | $0.068 | 96k | budget |
|
DeepSeek: DeepSeek R1 0528 Qwen3 8B
deepseek
|
$0.020 | $0.100 | 32k | budget |
|
Google: Gemma 3n 4B
google
|
$0.020 | $0.040 | 32k | budget |
|
Nous: DeepHermes 3 Mistral 24B Preview
nousresearch
|
$0.020 | $0.100 | 32k | budget |
📈 Recent Changes
View all →
✨
No recent price changes
Prices are stable
🔔 Never Miss a Price Drop
Get instant notifications when LLM prices change. Be the first to save on AI costs.