Open Llama instruction model for multilingual chat, reasoning, and coding
Llama 3.2 3B Instruct by meta is offered by 10 providers on this page. Public prices are shown for 9 of them. Its reference price is $0.10 per 1M input tokens and $0.335 per 1M output tokens. The lowest paid channel is Inference at $0.02 / $0.02 per 1M, about 5.0× below the reference price. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it. It also has 1 free ($0) channel; free tiers usually carry rate limits, and subscription-covered access bills $0 per token only after the subscription fee.
The context window is 131,072 tokens at the reference host, but hosts report different limits, from 16,000 to 131,072, so the usable window depends on the provider you pick. It supports structured output. Accepted input modalities are Text and PDF. The weights are open, so it can also be self-hosted or served through a gateway of your choice. Providers report the capability flags inconsistently, so verify a specific feature against the host you plan to use. Its training knowledge cuts off at 2023-12.
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| Nvidia | Cloud | Free | — | — | 32,768 ⚠ | 32,000 | deprecated | |
| Inference | Gateway | $0.02 | $0.02 | — | — | 16,000 ⚠ | 4,096 | |
| NovitaAI | Gateway | $0.03 | $0.05 | — | — | 32,768 ⚠ | 32,000 | |
| DevPass (LLM Gateway) | Gateway | $0.03 | $0.05 | — | — | 32,768 ⚠ | 32,000 | |
| LLM Gateway | Gateway | $0.03 | $0.05 | — | — | 32,768 ⚠ | 32,000 | |
| NanoGPT | Gateway | $0.031 | $0.049 | $0.015 | — | 131,072 | 8,192 | |
| OpenRouter | Gateway | $0.05 | $0.33 | — | — | 131,072 | 117,964 | |
| Kilo Gateway | Gateway | $0.05 | $0.33 | — | — | 131,072 | 117,964 | |
| Cloudflare Workers AI | Cloud | $0.051 | $0.34 | — | — | 80,000 ⚠ | 80,000 | |
| Pioneer meta-llama/Llama-3.2-3B-Instruct | Gateway | $0.10 | $0.34 | $0.10 | $0.10 | 131,072 | 80,000 |
Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.
1 more channels offer $0 (Nvidia); free tiers usually have rate limits and no SLA, excluded from ranking.