3.1 70B Instruct
Llama 3Balanced
Tool UseStructured Output
About this model
Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 70B instruct-tuned version is optimized for high quality dialogue usecases. It has demonstrated strong...
Performance Tier
Balanced
3.1 70B Instruct is a balanced model from Llama 3 : strong performance at a reasonable price.
Strong cost-performance ratio. Reliable for most professional use cases without premium pricing.
Pricing
This model is included in Elosia plansEco
Minimal cost. Ideal for very high volume or simple tasks.
| Type | per 1M tokens |
|---|---|
| Input (prompt) | $0.400 |
| Output (completion) | $0.400 |
Capabilities
Context Length131K
Max Output Tokens16K
TokenizerLlama3
Inputtext
Outputtext
Release DateJuly 23, 2024
Benchmarks
General Intelligence
MMLU
83.6%
MMLU-Pro
66.4%
Mathematics
MATH-500
68%
Programming
HumanEval
80.5%
Recommended Use Cases
General ChatCodingSummarizationTranslation
Strengths
- Battle-tested open model with wide ecosystem support
- 128K context window for document analysis
- Good general-purpose performance for its size
Limitations
- Previous generation — Llama 3.3 and 4 recommended
- Lower benchmark scores than current-gen models
Resources
This model may use your data for training
