Llama 3.2 3B Instruct: API pricing, providers and specs
Llama 3.2 3B Instruct is a text model by Meta. 7 providers serve it, from $0.05 to $0.60 /1M; the lowest price is at DevPass (LLM Gateway).
How Llama 3.2 3B Instruct compares
Against the 737 text models on the site priced the same way.
- Cheap for its class: at $0.05 /1M, its lowest price undercuts 98% of comparable models (median $1.10).
- Its 131K-token context window is larger than 21% of them (median 262K), about 200 pages of text.
- 7 providers serve it; 71% of comparable models have fewer.
- Its weights are open under the Llama 3.2 license: commercial use under the maker's terms.
Llama 3.2 3B Instruct prices by provider
Every provider's list price, read from its own price page or API. A price marked “from” changes with context length, resolution or mode.
| Provider | Input | Output | Prompt caching | Context |
|---|---|---|---|---|
| DevPass (LLM Gateway) | $0.03/1M | From$0.05/1M | — | — |
 Amazon Bedrock | $0.15/1M | $0.15/1M | — | — |
 AIHubMix | $0.20/1M | $0.20/1M | — | — |
 Cloudflare Workers AI | $0.051/1M | $0.335/1M | — | — |
| OpenRouter | $0.051/1M | From$0.335/1M | — | 131K |
 Prime Inference | $0.051/1M | $0.335/1M | — | — |
 Venice AI | $0.15/1M | $0.60/1M | — | — |
- DevPass (LLM Gateway)From$0.05
- Amazon Bedrock$0.15
- AIHubMix$0.20
- Cloudflare Workers AI$0.335
- Prime Inference$0.335
- OpenRouterFrom$0.335
- Venice AI$0.60
Specs
- Type
- Text
- Maker
- Meta
- Inputs
- Text
- Outputs
- Text
- Context
- 131K≈ 200 pages of text
- Max output
- 118K
- Capabilities
- JSON
- Released
- Sep 18, 2024
- License
- Llama 3.2commercial use under the maker's terms
- Open weights
- Yes, downloadable
- Parameters
- 3.2B
1 uncensored versions · See them
Alternatives to Llama 3.2 3B Instruct
Same kind of model from other makers, at a similar price.
| Model | Lowest price | Context | Arena | Providers |
|---|---|---|---|---|
| Llama 3.2 3B Instructthis model | $0.05/1M | 131K | — | 7 |
 DeepSeek V4.1 Flash | $0.03/1M | 1.05M | 1664 | 39 |
| GPT OSS 120B | $0.14/1M | 131K | 1366 | 32 |
 MiMo-V2.6-Flash | $0.10/1M | 1.05M | 1634 | 22 |
 Qwen3.5 9B | $0.13/1M | 262K | — | 12 |
| GPT OSS 20B | $0.09/1M | 131K | 1287 | 26 |
| Mercury 2.5 | $0.15/1M | 260K | — | 5 |
| Qwen3 8B | $0.06/1M | — | — | 3 |
 Solar Pro 4 | $0.127/1M | 524K | — | 3 |
More from Meta
Muse WonderMeta$16/1MMuse Spark 1.3Meta$4.25/1MMuse Spark OpenMeta$4.25/1MLlama 3 70B InstructMeta$0.70/1MLlama 4 MaverickMeta$0.20/1MLlama 4 Scout 17B InstructMeta$0.20/1MLlama 3.2 11B InstructMeta$0.16/1MLlama 3.1 405B (reasoning)Meta$4/1MLlama 3.2 3B Instruct FAQ
The lowest price for Llama 3.2 3B Instruct is $0.05 /1M, at DevPass (LLM Gateway).
DevPass (LLM Gateway), at $0.05 /1M. 7 providers serve Llama 3.2 3B Instruct; the table above lists every one with its price.
Llama 3.2 3B Instruct reads up to 131K tokens per request and writes up to 118K.
Yes. Llama 3.2 3B Instruct's weights can be downloaded from its maker's Hugging Face page, under the Llama 3.2 license.
About 3.2B, as the safetensors metadata of its official Hugging Face repo states.
7 API providers serve Llama 3.2 3B Instruct. Compare their prices above, or open a provider to see everything it offers.
Can't find what you're looking for? Contact us