Llama 3.2 3B Instruct
Meta · model · context window 16,000 tokens.
Pricing (per 1M tokens)
Specifications
Where else you can run Llama 3.2 3B Instruct
The same model is resold by 8 providers we track. The typical one charges 3.9× what the cheapest does — $0.0780 against $0.0200 per 1M tokens, blended 3:1. Routing the same workload to a different host is often a bigger saving than switching model.
| Provider | Input / 1M | Output / 1M | Blended |
|---|---|---|---|
| Inference | $0.0200 | $0.0200 | $0.0200 |
| LLM Gateway | $0.0300 | $0.0500 | $0.0350 |
| Llmgateway Providers | $0.0300 | $0.0500 | $0.0350 |
| NanoGPT | $0.0310 | $0.0490 | $0.0360 |
| Kilo | $0.0500 | $0.3300 | $0.1200 |
| OpenRouter ↗ | $0.0500 | $0.3300 | $0.1200 |
| Cloudflare Workers AI | $0.0510 | $0.3350 | $0.1220 |
| Pioneer | $0.1000 | $0.3350 | $0.1590 |
Third-party listings via models.dev, not rates we verify with each host the way we do first-party pricing. Treat them as a shortlist to check, not a quote — and confirm quantisation, context limits and rate limits before switching, since a cheaper host is not always serving the same thing.
Estimate cost with Llama 3.2 3B Instruct
Llama 3.2 3B Instruct is pre-selected below. Enter your token counts and volume to see the cost per request, per day and per month — then switch models to compare.
Results update automatically as you type.
- Input cost
- $0.0000200
- Output cost
- $0.0000100
- Per request
- $0.0000300
- Per day
- $0.0300
- Per month
- $0.9000
Source: community-hosted (cheapest of 8 providers, inference via models.dev). Prices are re-checked daily against the provider’s official pricing; this rate was last changed on 11 October 2026. A recent date here just means the price is still current, not that it moved.