Hermes 3 Llama 3.1 70B is Nous Research's language model with a 131K context window and up to 16K output tokens, available from 3 providers, starting at $0.120 / 1M input and $0.300 / 1M output. A 70B-parameter Llama 3.1-based LLM from Nous Research with Hermes 3 fine-tuning for improved agentic capabilities and long-context coherence.
Specifications
Canonical IDnousresearch-hermes-3-llama-3-1-70b
TypeLanguage
StatusActive
CreatorNous ResearchNous Research
Providers
Context Window131K tokens
Max Output16K tokens
Input ModalitiesText
Output ModalitiesText
Parameters70B
HuggingFace Likes123
HuggingFace Downloads (30d)2,494
HuggingFace Downloads (all-time)179,146
Release Date · 2 years ago
Knowledge Cutoff
Benchmarks
Intelligence Index
10.6
#380
MMLU-Pro
0.6
#259
GPQA
0.4
#364
HLE
0.0
#378
LiveCodeBench
0.2
#255
AIME
0.0
#153
Time to First Token
0.41s
#229
SciCode
0.2
#310
MATH-500
0.5
#149
Output TPS
35.5
#245

Capabilities

Input1/5
Text
Image·
Audio·
Video·
PDF·
Output1/5
Text
Image·
Audio·
Video·
Embedding·
Capabilities4/13
Reasoning·
Adaptive Reasoning·
Function Calling
Parallel Function Calling
Structured Outputs
Native JSON Schema
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·

Pricing by Provider

Cost Calculator

Preset:

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
Llama 3.3 70B Instruct131K$0.100$0.200Available
Llama 3.2 3B Instruct131K$0.015$0.020Deprecated
Llama 3.2 1B Instruct131K$0.027$0.080Deprecated
Llama 3.1 405B Instruct131K$0.120$0.300Deprecating
Llama 3.1 70B Instruct131K$0.100$0.100Available
Llama 3.1 8B Instruct200K$0.020$0.030Available
Llama 3.1 70B128K$0.600$0.600Available
Llama 3.1 8B131K$0.030$0.050Available
Llama 3 70B Instruct131K$0.120$0.300Available
Llama 3 8B Instruct32K$0.030$0.040Available
Hermes 3 Llama 3.1 70B131K$0.120$0.300Current

Model IDs