Llama API pricing
Llama API pricingLlama API pricing on 2 platforms: 24 Llama endpoints by Meta and 51 current prices. The cheapest exact price is $0.027/M in for Llama 3.2 1B Instruct, on OpenRouter. Prices are read from each platform daily and tagged by task, resolution and duration.
- Endpoints
- 24
- Current prices
- 51
- Platforms
- 2
- Cheapest
- $0.027/M in
Llama API pricing by platform
One row per model, matched across platforms by its model id; each cell is input / output per million tokens. Green is the cheapest platform for that model. Different models are never ranked against each other.
| Model | OpenRouter | Replicate |
|---|---|---|
| Llama 4 Maverick | $0.35 in$1 out | $0.25 in$0.95 out |
| Llama 4 Scout | $0.1 in$0.3 out | $0.17 in$0.65 out |
| Llama Guard 4 12B | $0.18 in$0.18 out | $0.2 in$0.2 out |
Sold on one platform only (18)
Nothing to compare these with yet, so no price here is marked cheapest.
| Model | Platform | USD |
|---|---|---|
| Llama 3.3 70B Instruct | OpenRouter | $0.59 in$0.79 out |
| Llama 3.2 1B Instruct | OpenRouter | $0.027 in$0.201 out |
| Llama 3.2 3B Instruct | OpenRouter | $0.05 in$0.33 out |
| Llama 3.1 70B Instruct | OpenRouter | $0.72 in$0.72 out |
| AionLabs Aion-RP 1.0 (8B) | OpenRouter | $0.8 in$1.6 out |
| Llama 3.1 8B Instruct | OpenRouter | $0.05 in$0.08 out |
| llama-3-70b | Replicate | $0.65 in$2.75 out |
| llama-3-70b-instruct | Replicate | $0.65 in$2.75 out |
| llama-3-8b | Replicate | $0.05 in$0.25 out |
| llama-3-8b-instruct | Replicate | $0.05 in$0.25 out |
| llama-2-13b | Replicate | $0.1 in$0.5 out |
| llama-2-13b-chat | Replicate | $0.1 in$0.5 out |
| llama-2-70b | Replicate | $0.65 in$2.75 out |
| llama-2-70b-chat | Replicate | $0.65 in$2.75 out |
| llama-2-7b | Replicate | $0.05 in$0.25 out |
| llama-2-7b-chat | Replicate | $0.05 in$0.25 out |
| Llama 3 8B Lunaris | OpenRouter | $0.04 in$0.05 out |
| Llama 3.1 Euryale 70B v2.2 | OpenRouter | $0.85 in$0.85 out |
Claude
Gemini
DeepSeek
Qwen
Mistral
Kimi
GLM
MiniMax
Hunyuan
Nemotron