Speed
Output tokens / second
Hermes 3 70B Instruct overview
Hermes 3 70B Instruct specs
- Model ID
nousresearch/hermes-3-llama-3.1-70b- Developer
- NousResearch
- Context window
- 131,072 tokens
- Max output
- 16,384 tokens
- Input
- Image, Text
- Output
- Text
- API
- OpenAI-compatible, base URL
https://api.aimlapi.com/v1
What is Hermes 3 70B Instruct API?
Where to Use Hermes 3 70B Instruct
Coding and code review
Generate, debug, and review code across languages, reading whole files or repos in a single prompt.
Agentic and multi-step workflows
Reliable tool-calling and instruction-following suit agent loops that plan, call tools, and iterate.
Use cases
This model is documented as suitable for agentic tasks, including tool use and structured multi-step interactions. The model card describes Hermes 3 as a “generalist language model” with “advanced agentic capabilities” and the technical report calls it a “generalist instruct and tool use model.”
It is also documented for reasoning-heavy conversational use. The source materials explicitly mention “reasoning,” “multi-turn conversation,” and “long context coherence” as strengths of Hermes 3 70B Instruct.
Another documented use case is roleplaying and creative dialogue. The model card highlights “much better roleplaying,” and the technical report says Hermes 3 has “strong reasoning and creative abilities.”
A fourth documented use case is code-related agentic work. The technical report includes an example labeled “Agentic coding (Hermes 3 70B),” indicating suitability for coding workflows that involve tool use and planning.
Capabilities
- Function calling
- Reasoning
- Streaming
- Structured outputs
- Web search
Hermes 3 70B Instruct benchmarks by 
Artificial Analysis
See how Hermes 3 70B Instruct compares in generation speed and latency. Data retrieved Nov 3, 2026.
Benchmark results
Compare 14 models available on AI/ML API across 5 independent benchmarks.
Humanity's Last Exam
Expert-written questions across academic subjects.
GPQA Diamond
Graduate-level science questions written to resist web search.
LiveCodeBench
Competitive programming problems published after training cutoffs.
MMLU-Pro
Multiple-choice knowledge and reasoning across 14 subjects.
MATH-500
Competition mathematics problems.
Hermes 3 70B Instruct API pricing
| Usage | Price | Unit |
|---|---|---|
| Input | $0.7406 | 1M tokens |
| Output | $0.7406 | 1M tokens |
Prices from the AI/ML API price list, checked on Nov 4, 2026.
Hermes 3 70B Instruct vs other models: token prices
AI/ML API input and output rates for 5 models, per million tokens.
| Model | Input | Output |
|---|---|---|
 Hermes 3 70B Instruct | $0.7406 | $0.7406 |
 Mercury 3 | $0.2116 | $0.7406 |
| Mercury 2.5 | $0.2116 | $0.7935 |
| Hermes 3 405B Instruct | $1.06 | $1.06 |
| Hermes 4 405B | $1.06 | $3.17 |
How to use the Hermes 3 70B Instruct API
View docs
Build with your agent
Give your agent the model details, code and documentation.
Paste it into your coding agent to build the integration.
1Get your API key
Create API keyexport AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"2Make your first request
curl 'https://api.aimlapi.com/v1/chat/completions' \
-H "Authorization: Bearer $AIMLAPI_KEY" \
-H 'Content-Type: application/json' \
-d '{
"model": "nousresearch/hermes-3-llama-3.1-70b",
"messages": [
{
"role": "user",
"content": "Write a haiku about the ocean."
}
]
}'import os
import requests
headers = {
"Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
"Content-Type": "application/json",
}
payload = {
"model": "nousresearch/hermes-3-llama-3.1-70b",
"messages": [
{
"role": "user",
"content": "Write a haiku about the ocean."
}
]
}
response = requests.post("https://api.aimlapi.com/v1/chat/completions", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())const response = await fetch("https://api.aimlapi.com/v1/chat/completions", {
method: "POST",
headers: {
Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"model": "nousresearch/hermes-3-llama-3.1-70b",
"messages": [
{
"role": "user",
"content": "Write a haiku about the ocean."
}
]
}),
});
if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());Models similar to Hermes 3 70B Instruct
Related articles
Hermes 3 70B Instruct FAQ
What is the context window of Hermes 3 70B Instruct?
Hermes 3 70B Instruct has a 131,072 tokens context window and can return up to 16,384 tokens.
What inputs and outputs does Hermes 3 70B Instruct support?
Hermes 3 70B Instruct takes image, text as input and returns text.
What is the model ID for Hermes 3 70B Instruct?
Use nousresearch/hermes-3-llama-3.1-70b as the model id. Requests go to https://api.aimlapi.com/v1/chat/completions.
How much does Hermes 3 70B Instruct cost?
Hermes 3 70B Instruct costs $0.7406 input and $0.7406 output per 1M tokens on AI/ML API, billed as you go with no subscription.
Does Hermes 3 70B Instruct support streaming?
Yes, Hermes 3 70B Instruct can stream responses as they are generated.
Can Hermes 3 70B Instruct read images?
Yes, Hermes 3 70B Instruct accepts image input alongside text.
Who created Hermes 3 70B Instruct?
Hermes 3 70B Instruct was built by NousResearch.
Does Hermes 3 70B Instruct support tool calling?
Yes, it supports function calling along with parallel tool calls.