Nous Hermes 3 70B
Llama-3.1-70B fine-tune from Nous Research with strong tool/agent capabilities and uncensored alignment.
Nous Hermes 3 70B is text & chat AI model from Together AI, priced at €0.000 per 1M input tokens with a 131.1K tokens context window.
0.7
Pricing
API Integration
Use our OpenAI-compatible API to integrate Nous Hermes 3 70B into your application.
npm install railwailimport railwail from "railwail";
const rw = railwail("YOUR_API_KEY");
// Simple — just pass a string
const reply = await rw.run("hermes-3-70b", "Hello! What can you do?");
console.log(reply);
// With message history
const reply2 = await rw.run("hermes-3-70b", [
{ role: "system", content: "You are a helpful assistant." },
{ role: "user", content: "Explain quantum computing simply." },
]);
console.log(reply2);
// Full response with usage info
const res = await rw.chat("hermes-3-70b", [
{ role: "user", content: "Hello!" },
], { temperature: 0.7, max_tokens: 500 });
console.log(res.choices[0].message.content);
console.log(res.usage);Deep dive — Nous Research's Nous Hermes 3 70B
Nous Research is a community-driven open-source AI collective founded in 2023, co-led by Karan 'Teknium' Malhotra, Jeffrey Quesnelle and Bowen Peng with a distributed contributor base. Nous focuses on uncensored, steerable, character-rich fine-tunes of open base models. The Hermes line (Hermes, OpenHermes, Hermes 2, Hermes 2.5, Hermes 3) is its flagship instruction-following family. Hermes 3 70B is the mid-sized variant of the August 2024 Hermes 3 release, fine-tuned from Llama 3.1 70B for steerable behaviour with native tool-use and scratchpad tags — the sweet spot for organisations that can run a 70B model on a small GPU cluster.
Visit Nous Research →Hermes 3 70B is a full-parameter supervised fine-tune of Meta's Llama 3.1 70B base. The architecture is identical to Llama 3.1 70B: 80 layers, 8,192 hidden size, 64-head grouped-query attention with 8 KV heads, RoPE positional embeddings with Llama 3 scaling (128K context), SwiGLU activations, and the 128,000-token Llama 3 BPE tokeniser. The fine-tune mixes role-play, function calling, code, math, RAG, agent traces and creative writing — largely Nous-curated synthetic data distilled from larger models. The model uses ChatML formatting with native `<tool_call>` JSON-schema tags and `<scratchpad>` chain-of-thought tags. A light DPO preference-optimisation stage was applied (unlike the 405B which is SFT-only). Released August 2024 under the Llama 3.1 Community License.
- Parameters
- 70B (dense)
- Context
- 128K tokens
- Full-parameter fine-tune of Llama 3.1 70B with light DPO
- Excellent system-prompt steerability for agents and characters
- Native ChatML `<tool_call>` and `<scratchpad>` tags
- More tractable to self-host than the 405B (~140GB FP16, ~35GB INT4)
- Strong instruction following and creative writing
- 128K context inherited from Llama 3.1
- Comparable to Llama 3.1 70B Instruct on benchmarks with friendlier tool-use format
- Best for: self-hosted assistants, tool-using agents, creative platforms, fine-tuning base for community projects.
Supervised fine-tuning on ~390M instruction tokens across ~2.5M examples covering role-play, function calling, code, math, RAG, agent traces and creative writing — largely Nous-curated synthetic data. A light DPO preference-optimisation pass was applied. Base knowledge cutoff December 2023.
License: Llama 3.1 Community License. Commercial use permitted, but services with >700M monthly active users require a separate Meta license. Meta's Acceptable Use Policy applies to all derivatives.
Known limitations
- Reduced safety guardrails versus Meta's Llama 3.1 70B Instruct
- Less capable than the 405B variant on hard reasoning, math and code
- No vision modality
- Knowledge cutoff inherited from Llama 3.1 (December 2023)
- Llama 3.1 license restricts services with >700M MAU
Frequently asked questions
Related Models
View all Text & ChatClaude Opus 4
Anthropic's most powerful model. Exceptional at complex analysis, agentic tasks, and extended reasoning.
Claude Sonnet 4
Anthropic's most capable model. Excellent for complex analysis, coding, math, and creative writing.
DeepSeek V3.1
DeepSeek's refreshed V3.1 release. 671B MoE / 37B active. Tops open-weights leaderboards on coding and reasoning.
DeepSeek V4 Pro
DeepSeek's April 2026 flagship. 1.6T MoE / 49B active params, 1M context, rivals top closed-source models on STEM and coding at a fraction of the price.
Start using Nous Hermes 3 70B today
Get started with free credits. No credit card required. Access Nous Hermes 3 70B and 100+ other models through a single API.