Meta: Llama 3.2 1B Instruct
Open Llama instruction model for multilingual chat, reasoning, and coding
Sources
Same model, different sources. Our first-party rate is listed first, then router and aggregator rows stay separate so you can see the spread instead of a single blended number.
| Source | Provider | Input | Output | Cache read | Context |
|---|---|---|---|---|---|
| models.devcheapestmeta/llama-3.2-1b-instruct | Inference | $0.01 | $0.01 | $0 | 16K |
| models.devmeta-llama/llama-3.2-1b-instruct | Novita AI | $0.02 | $0.02 | $0 | 131K |
| LiteLLMmeta-llama/llama-3.2-1b-instruct | N/A | $0.02 | $0.02 | $0.002 | N/A |
| LiteLLMnovita/meta-llama/llama-3.2-1b-instruct | N/A | $0.02 | $0.02 | $0.002 | N/A |
| models.devmeta-llama/llama-3.2-1b-instruct | Kilo Gateway | $0.027 | $0.201 | $0 | 60K |
| OpenRoutermeta-llama/llama-3.2-1b-instruct | OpenRouter | $0.027 | $0.201 | $0 | 60K |
| models.dev@cf/meta/llama-3.2-1b-instruct | Cloudflare | $0.027 | $0.201 | $0 | 60K |
| models.devcloudflare/@cf/meta/llama-3.2-1b-instruct | Eden AI | $0.027 | $0.201 | $0 | 60K |
| LiteLLM@cf/meta/llama-3.2-1b-instruct | N/A | $0.027 | $0.201 | $0.0027 | N/A |
| LiteLLMcloudflare/@cf/meta/llama-3.2-1b-instruct | N/A | $0.027 | $0.201 | $0.0027 | N/A |
| LiteLLMllama-3.2-1b-instruct | N/A | $0.027 | $0.201 | $0.0027 | N/A |
| LiteLLMmeta-llama/Llama-3.2-1B-Instruct | N/A | $0.06 | $0.06 | $0.006 | N/A |
| LiteLLMLlama-3.2-1B-Instruct | N/A | $0.06 | $0.06 | $0.006 | N/A |
| LiteLLMtogether_ai/meta-llama/Llama-3.2-1B-Instruct | N/A | $0.06 | $0.06 | $0.006 | N/A |
| LiteLLMmeta-llama/llama-3-2-1b-instruct | N/A | $0.1 | $0.1 | $0.01 | N/A |
| LiteLLMllama-3-2-1b-instruct | N/A | $0.1 | $0.1 | $0.01 | N/A |
| LiteLLMwatsonx/meta-llama/llama-3-2-1b-instruct | N/A | $0.1 | $0.1 | $0.01 | N/A |
Capabilities
- Tool calling
- Structured output
- Open weights
- In: text
- Out: text
Scores
Sparse coverage on purpose. Missing a score means we have not linked one yet, not that the model is unranked. Hover or tap the i next to any score for its source. Full boards on /benchmarks.
Arena rows are community-vote Elo from Arena AI, Artificial Analysis indices arrive via OpenRouter, and launch-eval figures are collected from vendor announcements, analyst writeups, and community benchmarks. Full boards and credits on /benchmarks.
See what this model costs you
The app reads the sessions your tools already wrote and prices this model's tokens at the published API rate. Free on your computer.