Open Llama instruction model for multilingual chat, reasoning, and coding
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...
Context
131K
131,072 tokens
Max output
118K
117,964 tokens
Input
$0.05
per 1M tokens
Output
$0.33
per 1M tokens
Providers
3
4 listings
Intelligence
5.7
Intelligence Index
Pricing
USD per 1M tokens · listed by Kilo Gateway
| Token type | Standard |
|---|---|
| Input | $0.05 |
| Output | $0.33 |
Lowest input price across providers: $0.02.
Capabilities
ReasoningNo
Tool callNo
Structured outputYes
TemperatureYes
AttachmentsNo
Interleaved reasoningNo
Open weightsYes
ModeratedNo
Input
Text
Output
Text
Benchmarks
Published scores and Design Arena Elo
- Intelligence5.7#201 of 208
- CodingNot scored—
- AgenticNot scored—
- ArenaNot scored—
Rankings
Position on each OneAtlas leaderboard
Providers · 3
4 listings
| Provider | Model ID | Context | Input limit | Output | Input $ | Output $ | Reasoning $ | Cache read | Cache write | Audio in | Audio out | Reasoning | Tools | Structured | Temp. | Updated |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| cloudflare/@cf/meta/llama-3.2-3b-instruct | 80K | — | 131K | $0.05 | $0.34 | — | — | — | — | — | No | No | No | Yes | Sep 25, 2024 | |
| deepinfra/meta-llama/Llama-3.2-3B-Instruct | 131K | — | 131K | $0.02 | $0.02 | — | — | — | — | — | No | Yes | No | Yes | Sep 25, 2024 | |
| meta-llama/llama-3.2-3b-instruct | 131K | — | 118K | $0.05 | $0.33 | — | — | — | — | — | No | No | Yes | Yes | Sep 25, 2024 | |
| meta-llama/llama-3.2-3b-instruct | 131K | 131K | 8K | $0.03 | $0.05 | — | $0.02 | — | — | — | No | No | No | Yes | Sep 25, 2024 |