Llama 3.2 1B Instruct
Llama 3.2 1B is a 1-billion-parameter language model focused on efficiently performing natural language tasks, such as summarization, dialogue, and multilingual text analysis. Its smaller size allows it to operate efficiently in low-resource environments while maintaining strong task performance. Supporting eight core languages and fine-tunable for more, Llama 1.3B is ideal for businesses or developers seeking lightweight yet powerful AI solutions that can operate in diverse multilingual settings without the high computational demand of larger models. Click here for the original model card. Usage of this model is subject to Meta's Acceptable Use Policy.
- Input / output price
- $0.02 / $0.02 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 |
|---|---|---|
Novita novita/llama-3.2-1b-instruct | $0.02/M | $0.02/M |
ConcentrateRetiring concentrate/llama-3.2-1b-instruct | $0.027/M | $0.201/M |
Inference.net inference_net/llama-3.2-1b-instruct | $0.027/M | $0.201/M |
OpenRouterRetiring openrouter/llama-3.2-1b-instruct | $0.027/M | $0.201/M |
Is a provider down? OpenRouter status
Pricing
Averaged across 4 providers, in USD per 1M tokens after gateway discounts.
- Average input
- $0.03 per 1M
- Average output
- $0.16 per 1M
- Average cache read
- $0.0050 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 better46tokens/sacross providers
Time to first token
Lower is better0.6sacross providers
Response latency
Lower is better0.5sacross providers
Benchmarks
The Respan Index plus 6 published scores from 4 sources, each linked to where it was published.
5.3/ 100
Respan Index#176 of 176
- 176Llama 3.2 1B Instruct5.3
- 174Phi-49.2
- 175Llama 3.1 8B Instruct7.2
Published scores
| Benchmark | Score | Source | Published |
|---|---|---|---|
| GPQA DiamondEpoch AI | 23.9% | Epoch AI | Nov 8, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| OTIS Mock AIME 2024-2025Epoch AI | 0.6% | Epoch AI | Nov 8, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| IFEvalhuggingface.co | 59.5% | huggingface.co | Sep 25, 2024 |
| MMLUhuggingface.co | 49.3% | huggingface.co | Sep 25, 2024 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| LMArena EloLMArena | 1111 Elo · #191 of 191 | LMArena | Nov 19, 2026 |
Compare Llama 3.2 1B Instruct: Llama 3.2 1B Instruct vs Muse Wonder Full, Llama 3.2 1B Instruct vs Muse Wonder, Llama 3.2 1B Instruct vs Muse Ember, Llama 3.2 1B Instruct vs Muse Spark 1.3, Llama 3.2 1B Instruct vs Muse Spark 1.1, Llama 3.2 1B Instruct vs Muse Spark 1.2
Apps
Use Llama 3.2 1B 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 1B Instruct FAQ
Short answers, built from the data on this page.
Llama 3.2 1B Instruct is a model from Meta, released on Sep 25, 2024. Llama 3.2 1B is a 1-billion-parameter language model focused on efficiently performing natural language tasks, such as summarization, dialogue, and multilingual text analysis. Its smaller size allows it to operate efficiently in low-resource environments while maintaining strong task performance. Supporting eight core languages and fine-tunable for more, Llama 1.3B is ideal for businesses or developers seeking lightweight yet powerful AI solutions that can operate in diverse multilingual settings without the high computational demand of larger models. 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 1B Instruct costs from $0.02 per 1M input tokens and $0.02 per 1M output tokens on Novita, after gateway discounts. Averaged across its 4 providers, it costs $0.03 per 1M input tokens and $0.16 per 1M output tokens.
Llama 3.2 1B Instruct is available through 4 providers: Novita, Concentrate, Inference.net, and OpenRouter.
Llama 3.2 1B 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-3.2-1b-instruct". To set it up with a coding agent, copy the agent setup prompt at the top of this page.
Llama 3.2 1B Instruct scores 5.3 out of 100 on the Respan Index v1.1, ranking #176 of 176 models. By category: Coding 0.0 (estimated), Agents 0.2, Reasoning 12.5, Knowledge & language 0.3 (estimated), and Human preference 13.8. The Respan Index combines independent and lab-reported benchmark results into one score, using benchmark data collected by Respan.
Llama 3.2 1B Instruct has 6 published benchmark scores, including BALROG 6.6%, GPQA Diamond 23.9%, and OTIS Mock AIME 2024-2025 0.6%. 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.