Meta
Llama 3.2 3B Instruct
Released 2024-09-25 · Knowledge up to 2023-12-31
Llama 3.2 3B is a 3-billion-parameter multilingual large language model, optimized for advanced natural language processing tasks like dialogue generation, reasoning, and summarization. Designed with the latest transformer architecture, it...
You send / 1M
$0.050
tokens in
It replies / 1M
$0.330
tokens out
Memory
131K
tokens it can read at once
Typical request
$0.0002
1,000 words in, 400 out
Data privacy
No training or retention: Yes. At least one provider serves it with zero data retention.
| Provider | You send / 1M | It replies / 1M | Uptime | Privacy policy |
|---|---|---|---|---|
| Parasail · bf16 | $0.050 | $0.330 | 100% | Read |
| Cloudflare | $0.051 | $0.335 | 100% | Read |
Based on OpenRouter and Vercel AI Gateway data. Confirm terms with the provider before sending sensitive data.
What it can do
- Reads: text
- Writes: text
- Reasoning: No
- Tool calling: No
- Longest reply: 118K tokens
- Intelligence score: 5.7 / 100 (Artificial Analysis)
Similar models
- Llama 3.3 70B InstructMeta · $0.100 in / $0.320 out per 1M
- Voxtral Small 24B 2507Mistral · $0.100 in / $0.300 out per 1M
- Qwen3 30B A3B Instruct 2507Qwen · $0.100 in / $0.300 out per 1M
- Hy-MT2-30B-A3BTencent · $0.074 in / $0.295 out per 1M
- Hy-MT2-7BTencent · $0.074 in / $0.295 out per 1M
- Qwen3 Coder 30B A3B InstructQwen · $0.070 in / $0.280 out per 1M