Llama 3 70B Instruct
Newer version available: Llama 3.3 70B Instruct
- Family
- Llama 3
- Released
- 2024-04-18
- Context
- 8K
- Parameters
- 70B
- Architecture
- Decoder Only
- Knowledge cutoff
- 2023-12
- Specialization
- general
- Openness
- Open weights
- License
- Llama 3 CommunityRestricted
- Weights
- Available
- Code
- Unknown
- Training
- Fine-tuned
Large-scale open-source AI for social technologies.
Cheapest of 10 routes · Hyperbolic AI Inference
About
The Llama 3 70B Instruct model is a large language model with 70 billion parameters, released by Meta on April 18, 2024. It's an instruction-tuned variant optimized for conversational applications, utilizing an advanced auto-regressive transformer architecture. The model excels in following instructions and engaging in dialogue, having been trained on over 15 trillion tokens with a December 2023 knowledge cutoff. It demonstrates superior performance on industry benchmarks, scoring 82.0 on the MMLU (5-shot) test. The model incorporates extensive safety measures and optimizations, including RLHF, to enhance helpfulness and reduce harmful content generation.
Top use-case fit: coding, agents, and build tasks
Coding
Q/$ BClassification
Q/$ CProviders(10)
Compare all 10Compare API pricing across 10 tracked provider routes for input and output tokens, batch, and cached reads when available.
| Provider | Input / 1M | Output / 1M | Route |
|---|---|---|---|
| Hyperbolic AI Inference | $0.400 | $0.400 | Serverless |
| Novita AI | $0.510 | $0.740 | Serverless |
| Fireworks AI | $0.900 | $0.900 | Serverless |
| AWS Bedrock | $0.990 | $0.990 | Serverless Scheduled retirement: March 30, 2027 |
| IBM watsonx | $1.80 | $1.80 | Serverless |
| Replicate API | $0.650 | $2.75 | Serverless |
| GCP Vertex AI | $1.20 | $3.60 | Serverless |
| Baseten API | - | - | ServerlessPartial |
| OCI Generative AI | - | - | ServerlessPartial |
| Scale AI GenAI Platform | - | - | ServerlessPartial |
Deprecated provider routes(8)
| Provider | Status | Catalog ID |
|---|---|---|
| Microsoft Foundry | DeprecatedRetired June 30, 2025 | — |
| NVIDIA NIM | DeprecatedRetired April 15, 2026 | meta/llama3-70b-instruct |
| DeepInfra | DeprecatedRetired September 11, 2025 | meta-llama/Meta-Llama-3-70B-Instruct |
| OctoAI API (Deprecated) | Deprecated | — |
| Databricks Foundation Model Serving | DeprecatedRetired February 27, 2026 | — |
| Lepton AI API | Deprecated | — |
| Together AI | DeprecatedRetired April 24, 2025 | — |
| OpenRouter | Deprecated | meta-llama/llama-3-70b-instruct |
Available via routers & gateways(16)
LiteLLM
GatewayOpen-source Python SDK and proxy server that unifies 100+ LLM APIs behind a single OpenAI-compatible interface, with load balancing, cost tracking, and configurable failover.
OpenRouter
HybridUnified hybrid gateway to 400+ models from 60+ providers via a single OpenAI-compatible API, with optional auto-routing that selects the best model per prompt.
Portkey
GatewayProduction AI gateway routing to 1,600+ LLMs with failover, load balancing, semantic caching, and guardrails; Apache 2.0 core is fully self-hostable with the complete feature set.
AIRouter
RouterCommercial LLM router that analyzes incoming requests and routes to the optimal model for cost/quality/latency via a drop-in OpenAI-compatible API, with a privacy-preserving embedding mode that avoids sending prompt content.
Amazon Bedrock Intelligent Prompt Routing
RouterAWS Bedrock's native intelligent prompt router that routes prompts between Anthropic Claude model tiers (Haiku/Sonnet) based on predicted task complexity, with no extra per-routing charge.
Azure AI Foundry Model Router
RouterMicrosoft Azure AI Foundry's native model router that uses a trained ML model to route each prompt in real time to the optimal Azure-hosted model, with Balanced/Cost/Quality mode selection and automatic failover.
Capabilities
Benchmark peer barsfor Coding
Benchmark scores(5)
| Benchmark | Score | Version | Evaluation | Source |
|---|---|---|---|---|
| 72.6 | pass@1Observed 2026-03-06 | — | ||
| 82.0 | 5-shotObserved 2026-03-06 | — | ||
| 77.8 | v2Observed 2026-04-14 | — | ||
| 57.4 | —Observed 2026-04-14 | — | ||
| 1277.0 | text_style_control overall 2026-10-22 (style control, default view)Observed 2026-10-26 | Configuration: Llama 3 70B Instruct Harness: LMArena blind pairwise human votes, Bradley-Terry Evaluator: LMArena Confidence: confirmed Notes: LMArena text style control leaderboard, overall category, published 2026-10-22 (HF lmarena-ai/leaderboard-dataset @9761a3ce, latest split). Board entry 'Llama 3 70B Instruct': rank 307, Arena Score 1276.6 (95% CI 1273.0-1280.2), 156876 votes. Retrieved 2026-10-26. | Source Source: LMArena (lmarena.ai), CC BY 4.0 |
Migration checks
No linked migration route is available for this model yet.
Compare Llama 3 70B Instruct with other models
- Llama 3 70B Instruct vs Llama 3.1 70B Instruct5K
- Llama 3 70B Instruct vs Qwen2.5-72B-Instruct461
- Llama 3 70B Instruct vs Qwen3.6-27B410
- Llama 3 70B Instruct vs DeepSeek V4 Flash407
- Llama 3 70B Instruct vs Qwen3.6-35B-A3B381
- Llama 3 70B Instruct vs DeepSeek V4 Pro226
- Llama 3 70B Instruct vs Mixtral 8x7B206
- Llama 3 70B Instruct vs Claude Opus 4.7186
Comparison and alternatives
Browse all comparisons →Show all 41 popular comparisonssorted by 7-day search impressions
Large-scale open-source AI for social technologies.
Cheapest of 10 routes · Hyperbolic AI Inference