Llama 3.2 3B Instruct
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 supports eight languages, including English, Spanish, and Hindi, and is adaptable for additional languages. Trained on 9 trillion tokens, the Llama 3.2 3B model excels in instruction-following, complex reasoning, and tool use. Its balanced performance makes it ideal for applications needing accuracy and efficiency in text generation across multilingual settings. Click here for the original model card. Usage of this model is subject to Meta's Acceptable Use Policy.
- Input / output price
- $0.05 / $0.33 per 1M
- Context
- 131K tokens
- Released
- Sep 25, 2024
Paste into Claude Code, Cursor, or Codex
Help me set up the Respan gateway: fetch and follow https:/
Providers
4 providers, cheapest first, OpenRouter last, priced per 1M tokens after gateway discounts.
| Provider | Input | Output |
|---|---|---|
Inference.net inference_net/llama-3.2-3b-instruct | $0.05/M | $0.33/M |
Parasail parasail/llama-3.2-3b-instruct | $0.05/M | $0.33/M |
ConcentrateRetiring concentrate/llama-3.2-3b-instruct | $0.0509/M | $0.335/M |
OpenRouterRetiring openrouter/llama-3.2-3b-instruct | $0.0509/M | $0.335/M |
Is a provider down? OpenRouter status
Pricing
Averaged across 4 providers, in USD per 1M tokens after gateway discounts.
- Average input
- $0.05 per 1M
- Average output
- $0.33 per 1M
Cost by volume
Total cost from 0 to 1T tokens on the cheapest and most expensive provider.
Throughput and latency
30-day averages from requests through the Respan gateway. Under each figure, every model on the gateway by its average, this one in blue.
Output speed
Higher is better4.9tokens/sacross providers
Response latency
Lower is better0.5sacross providers
Benchmarks
5 published scores from 3 sources, each linked to where it was published.
Published scores
| Benchmark | Score | Source | Published |
|---|---|---|---|
| BFCL-v2github.com | 67% | github.com | Oct 24, 2024 |
| BALROGBALROG | 10.1% | BALROG | Nov 11, 2024 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| IFEvalgithub.com | 77.4% | github.com | Oct 24, 2024 |
| MMLUgithub.com | 63.4% | github.com | Oct 24, 2024 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| LMArena EloLMArena | 1167 Elo · #187 of 191 | LMArena | Nov 19, 2026 |
Apps
Use Llama 3.2 3B Instruct in the tools you already run. Each guide points the app at the Respan gateway.
Setup guides for more apps are in the integration docs.
Llama 3.2 3B Instruct FAQ
Short answers, built from the data on this page.
Llama 3.2 3B Instruct is a model from Meta, released on Sep 25, 2024. 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 supports eight languages, including English, Spanish, and Hindi, and is adaptable for additional languages. Trained on 9 trillion tokens, the Llama 3.2 3B model excels in instruction-following, complex reasoning, and tool use. Its balanced performance makes it ideal for applications needing accuracy and efficiency in text generation across multilingual settings. Click here for the original model card. Usage of this model is subject to Meta's Acceptable Use Policy.
On the Respan gateway, Llama 3.2 3B Instruct costs from $0.05 per 1M input tokens and $0.33 per 1M output tokens on Inference.net and Parasail, after gateway discounts. Averaged across its 4 providers, it costs $0.05 per 1M input tokens and $0.33 per 1M output tokens.
Llama 3.2 3B Instruct is available through 4 providers: Inference.net, Parasail, Concentrate, and OpenRouter.
Llama 3.2 3B Instruct accepts up to 131K tokens of context on its largest provider route.
Point any OpenAI-compatible SDK at https://gateway.respan.ai/v1 with your Respan API key and set the model to "llama-3.2-3b-instruct". To set it up with a coding agent, copy the agent setup prompt at the top of this page.
Llama 3.2 3B Instruct has 5 published benchmark scores, including BFCL-v2 67%, IFEval 77.4%, and LMArena Elo 1167. Each score links to where it was published; the data is collected by Respan.
Certified where it counts.
Built to meet the security and privacy standards that enterprise and healthcare teams require.
ISO 27001
The internationally recognized standard for information security management.
SOC 2
Secure, compliant management of your data across all of our systems.
GDPR
Operated under GDPR, the world's strictest standard for data privacy.
HIPAA
HIPAA compliant, with a BAA available for healthcare teams.