Meta Llama 3 8B Instruct Reference
oah/llama-3-8b-chat-hfDeploy Meta Llama 3 8B Instruct Reference with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
Together.ai
Input: $0.20/MOutput: $0.20/M
Why deploy Llama through OpenSourceAIHub?
Automatic PII Redaction
Every Llama request is scanned for 28+ PII entity types — SSNs, credit cards, emails, API keys, and more — before it reaches any provider.
Smart Cost Routing
Llama is available across 3 providers. Our Smart Router picks the cheapest one per-request. 25% managed markup / 0% on Pro BYOK.
Zero Code Changes
Change two lines in your OpenAI SDK — base_url and api_key — and every request flows through the Hub. Full backward compatibility.
Full Observability
Per-request logging of token counts, latency, DLP violations, and cost. Never wonder what your AI spend is again.
Llama Strengths
- Open-weights — full transparency and audit capability
- Multi-provider availability (Groq, Together, DeepInfra) for cost arbitrage
- Llama 4 Maverick: 400B MoE with vision support
- Llama 4 Scout: 512K context window for long-document tasks
- Fine-tuning friendly — build domain-specific models on open weights
Available Llama Models (18)
Meta Llama 3.1 405B Instruct
oah/llama-3.1Deploy Meta Llama 3.1 405B Instruct with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
Together.ai
Input: $3.50/MOutput: $3.50/M
Llama 3.2 1B
oah/llama-3.2Deploy Llama 3.2 1B with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
Together.ai
Input: $0.06/MOutput: $0.06/M
Meta Llama 3.3 70B Instruct Turbo
oah/llama-3.3Deploy Meta Llama 3.3 70B Instruct Turbo with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
Together.aiDeepInfra
Input: $0.13/MOutput: $0.39/M
Llama 4 Maverick Instruct (17Bx128E) FP8
oah/llama-4-maverickDeploy Llama 4 Maverick Instruct (17Bx128E) FP8 with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
Together.aiDeepInfra
Input: $0.15/MOutput: $0.60/M
Llama 4 Scout Instruct (17Bx16E)
oah/llama-4-scoutDeploy Llama 4 Scout Instruct (17Bx16E) with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
Together.aiGroqDeepInfra
Input: $0.11/MOutput: $0.34/M
Meta Llama 3 8B Instruct Lite
oah/meta-llama-3-8b-instruct-liteDeploy Meta Llama 3 8B Instruct Lite with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
Together.ai
Input: $0.10/MOutput: $0.10/M
Meta Llama 3.1 8B Instruct Turbo
oah/meta-llama-3.1Deploy Meta Llama 3.1 8B Instruct Turbo with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
Together.aiDeepInfra
Input: $0.06/MOutput: $0.06/M
nim/nvidia/llama-3.3-nemotron-super-49b-v1
oah/nvidia/llama-3.3-nemotron-super-49bDeploy nim/nvidia/llama-3.3-nemotron-super-49b-v1 with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
Together.ai
Input: Free/MOutput: Free/M
llama-3.1-8b-instant
oah/llama-3.1-8b-instantDeploy llama-3.1-8b-instant with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
Groq
Input: $0.05/MOutput: $0.08/M
llama-3.3-70b-versatile
oah/llama-3.3-70b-versatileDeploy llama-3.3-70b-versatile with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
Groq
Input: $0.59/MOutput: $0.79/M
NousResearch/Hermes-3-Llama-3.1-405B
oah/hermes-3-llama-3.1Deploy NousResearch/Hermes-3-Llama-3.1-405B with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
DeepInfra
Input: $0.30/MOutput: $0.30/M
deepseek-ai/DeepSeek-R1-Distill-Llama-70B
oah/deepseek-r1-distill-llamaDeploy deepseek-ai/DeepSeek-R1-Distill-Llama-70B with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
DeepInfra
ReasoningInput: $0.20/MOutput: $0.60/M
meta-llama/Llama-3.2-11B-Vision-Instruct
oah/llama-3.2-11b-visionDeploy meta-llama/Llama-3.2-11B-Vision-Instruct with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
DeepInfra
Input: $0.05/MOutput: $0.05/M
meta-llama/Llama-Guard-4-12B
oah/llama-guard-4Deploy meta-llama/Llama-Guard-4-12B with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
DeepInfra
Input: $0.18/MOutput: $0.18/M
meta-llama/Meta-Llama-3-8B-Instruct
oah/meta-llama-3Deploy meta-llama/Meta-Llama-3-8B-Instruct with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
DeepInfra
Input: $0.03/MOutput: $0.06/M
nvidia/Llama-3.1-Nemotron-70B-Instruct
oah/llama-3.1-nemotronDeploy nvidia/Llama-3.1-Nemotron-70B-Instruct with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
DeepInfra
Input: $0.60/MOutput: $0.60/M
nvidia/Llama-3.3-Nemotron-Super-49B-v1.5
oah/llama-3.3-nemotron-super-49bDeploy nvidia/Llama-3.3-Nemotron-Super-49B-v1.5 with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
DeepInfra
Input: $0.10/MOutput: $0.40/M
Llama Pricing Comparison (per 1M tokens, USD)
Input / Output pricing by provider. Managed Mode adds a 25% managed markup. Pro BYOK = 0% markup.
| Model | Params | Context | Vision | Together.ai | DeepInfra | Groq |
|---|---|---|---|---|---|---|
Meta Llama 3 8B Instruct Reference oah/llama-3-8b-chat-hf | — | 8K | No | $0.20/$0.20 | — | — |
Meta Llama 3.1 405B Instruct oah/llama-3.1 | — | 4K | No | $3.50/$3.50 | — | — |
Llama 3.2 1B oah/llama-3.2 | — | 131K | No | $0.06/$0.06 | — | — |
Meta Llama 3.3 70B Instruct Turbo oah/llama-3.3 | — | 131K | No | $0.88/$0.88 | $0.13/$0.39 | — |
Llama 4 Maverick Instruct (17Bx128E) FP8 oah/llama-4-maverick | — | 1.0M | No | $0.27/$0.85 | $0.15/$0.60 | — |
Llama 4 Scout Instruct (17Bx16E) oah/llama-4-scout | — | 1.0M | No | $0.18/$0.59 | $0.15/$0.45 | $0.11/$0.34 |
Meta Llama 3 8B Instruct Lite oah/meta-llama-3-8b-instruct-lite | — | 8K | No | $0.10/$0.10 | — | — |
Meta Llama 3.1 8B Instruct Turbo oah/meta-llama-3.1 | — | 131K | No | $0.18/$0.18 | $0.06/$0.06 | — |
nim/nvidia/llama-3.3-nemotron-super-49b-v1 oah/nvidia/llama-3.3-nemotron-super-49b | — | 16K | No | Free/Free | — | — |
llama-3.1-8b-instant oah/llama-3.1-8b-instant | — | 131K | No | — | — | $0.05/$0.08 |
llama-3.3-70b-versatile oah/llama-3.3-70b-versatile | — | 131K | No | — | — | $0.59/$0.79 |
NousResearch/Hermes-3-Llama-3.1-405B oah/hermes-3-llama-3.1 | — | — | No | — | $0.30/$0.30 | — |
deepseek-ai/DeepSeek-R1-Distill-Llama-70B oah/deepseek-r1-distill-llama | — | — | No | — | $0.20/$0.60 | — |
meta-llama/Llama-3.2-11B-Vision-Instruct oah/llama-3.2-11b-vision | — | — | No | — | $0.05/$0.05 | — |
meta-llama/Llama-Guard-4-12B oah/llama-guard-4 | — | — | No | — | $0.18/$0.18 | — |
meta-llama/Meta-Llama-3-8B-Instruct oah/meta-llama-3 | — | — | No | — | $0.03/$0.06 | — |
nvidia/Llama-3.1-Nemotron-70B-Instruct oah/llama-3.1-nemotron | — | — | No | — | $0.60/$0.60 | — |
nvidia/Llama-3.3-Nemotron-Super-49B-v1.5 oah/llama-3.3-nemotron-super-49b | — | — | No | — | $0.10/$0.40 | — |
Llama Direct vs OpenSourceAIHub
What you get at each pricing tier. Hub adds security, governance, and multi-provider routing on top of raw API access.
| Mode | What You Pay | PII Redaction | Budget Caps | Routing | Audit Trail |
|---|---|---|---|---|---|
| Direct to Meta | Provider pricing only | None | None | Manual | None |
| Hub — Managed Mode | Provider + 25% markup | 28+ PII types | Per-key hard caps | Smart Router | Full compliance log |
| Hub — Pro BYOK ($29/mo) | Direct to provider (0% markup) | 28+ PII types | Per-key hard caps | Smart Router | Full compliance log |
Popular Use Cases
1
Privacy-sensitive deployments requiring model auditability
2
Cost-optimized chatbots and customer support agents
3
Long-document summarization and analysis (Scout 512K context)
4
Multi-provider redundancy with automatic failover
Integration — 2 Lines
from openai import OpenAI
client = OpenAI(
base_url="https://api.opensourceaihub.ai/v1",
api_key="your_hub_api_key"
)
# Use any virtual model name from the pricing table above
response = client.chat.completions.create(
model="oah/llama-3-8b-chat-hf",
messages=[{"role": "user", "content": "Hello!"}]
)Use any virtual model name from the pricing table above (prefixed with oah/). Works with the standard OpenAI SDK. Every request is PII-scanned before reaching Meta (Open Source).
Frequently Asked Questions
What is the Llama API pricing on OpenSourceAIHub?
Llama API pricing varies by provider and model variant. In Managed Mode, we add a 25% markup on top of the provider's rate. With Pro BYOK ($29/mo), you pay the provider directly at 0% markup. Our Smart Router automatically picks the cheapest available provider for each request.
Who is the cheapest Llama provider?
Llama 3.3 70B on Groq is typically the cheapest Llama provider. Our Smart Router compares real-time pricing across Groq, Together.ai, and DeepInfra and automatically routes to the cheapest one for you.
Llama 3 vs Llama 4 — which should I use?
Llama 4 Maverick (400B MoE) and Llama 4 Scout (512K context) are the latest and most capable. Llama 3.3 70B remains the best value for cost-sensitive production workloads. All versions run through the Hub with identical PII protection.
Can I use my own Llama API keys with OpenSourceAIHub?
Yes. With Pro BYOK mode, store your Groq, Together.ai, or DeepInfra keys in the Hub (AES-256 encrypted). We route requests through your account at 0% markup — you only pay the provider directly.
Does OpenSourceAIHub store my Llama prompts?
No. Prompts are processed in volatile memory (RAM) and discarded immediately. We never persist, log, or train on your content. Only metadata (token counts, latency, violation types) is stored.
What happens when a Llama model is retired?
Retired models automatically move to the 'Previous Versions' section on this page. If a replacement exists, it's shown alongside. Your API calls will return a clear error indicating the model is deprecated.
Deploy Llama with Enterprise-Grade Security
Get started with 1,000,000 free credits. Every Llama request is PII-scanned, cost-optimized, and fully logged — zero configuration.
Not ready yet? Get notified about Llama updates:
Explore Other Model Families
🧠GPT
OpenAI's GPT family powers the majority of commercial AI applications. Compare GPT-4 API cost and OpenAI API pricing acr…
💎Gemini
Google's Gemini family offers powerful multimodal capabilities with large context windows. Compare Gemini API pricing an…
🤖Claude
Anthropic's Claude family is built with safety and reliability at its core. Compare Claude API pricing and Claude Sonnet…
🔍DeepSeek
DeepSeek has rapidly risen as a leading open-source model family, known for exceptional coding performance and cost effi…
🌀Mistral
Mistral AI's model family spans from compact open-weights models to powerful commercial variants. Compare Mistral API pr…
Model registry last updated: . Pricing shown is the lowest available rate across providers (per 1M tokens, USD). Actual pricing depends on provider and plan.