Skip to main content

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
Agent setup

Paste into Claude Code, Cursor, or Codex

Help me set up the Respan gateway: fetch and follow https://www.respan.ai/docs/agent-setup.md. Use model "llama-3.2-3b-instruct".

Read docs

Providers

4 providers, cheapest first, OpenRouter last, priced per 1M tokens after gateway discounts.

ProviderInputOutput
Inference.netinference_net/llama-3.2-3b-instruct
$0.05/M$0.33/M
Parasailparasail/llama-3.2-3b-instruct
$0.05/M$0.33/M
ConcentrateRetiringconcentrate/llama-3.2-3b-instruct
$0.0509/M$0.335/M
OpenRouterRetiringopenrouter/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.

Highest$0.0509/MConcentrate and OpenRouterLowest$0.05/MInference.net and Parasail

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 better

4.9tokens/sacross providers

Faster than 9% of the other 599 models on the gateway

Response latency

Lower is better

0.5sacross providers

Faster than 86% of the other 780 models on the gateway

Benchmarks

5 published scores from 3 sources, each linked to where it was published.

Published scores

BenchmarkScore
BFCL-v2github.com67%
BALROGBALROG10.1%

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.

Works with your entire stack

Use Respan with your favorite frameworks and tools.

AnthropicAI21 LabsxAIVercel AI SDK
LangChainOpenRouterAssemblyAICursor
LiteLLMGroqBasetenMem0
CohereCogneeLlamaIndexFireworks
DeepSeekLinkupHaystackTogether AI
PerplexityInference.netPostHogRubyLLM
SlackMastraAzure OpenAIMistral
AWS BedrockMoonshotHyperspellBAML
ModaInstructorGoogle GeminiParasail
ReductoZapierAgnoNebius
OpenAINovita AIReplicateSuperagent

Built for AI agents.
Break less.
Ship more.