Nousresearch

Hermes 3 70B Instruct API Pricing 2026

Compare pricing, benchmarks, and providers for Hermes 3 70B Instruct. Find the best value for your use case.

8 Ways to Use Fewer Tokens
Last updated: November 21, 2026 at 08:43 AM

Overview

Hermes 3 70B Instruct was released on August 18, 2024. Pricing starts at $0.100 per million input tokens and $0.280 per million output tokens. The model supports a context window of up to 66K tokens. API access is available through Nousresearch.

Context Window
66K
tokens
Pricing
Input$0.100
Output$0.280
per 1M tokens
Speed
Output-
TTFT-
median latency
Capabilities
Tools

Hermes 3 70B Instruct is priced at $0.100 per million input tokens and $0.280 per million output tokens. It has a context window of 65,536 tokens. On benchmarks, Hermes 3 70B Instruct scores Intelligence 38.5 (81st percentile), MMLU Pro 41.4 (80th percentile), GPQA 14.9 (45th percentile).

Pricing Comparison

Compare Hermes 3 70B Instruct with 10 similar models by price.

Current Pricing (per 1M tokens)

11 models

Sponsored The Grid | Spot Priced LLM API
The Grid | Spot Priced LLM API — Why pay list price when providers will bid for your API usage? Up to 80% off.
View spot prices
Provider
Model
Input $/M
Output $/M
Coding
MMLU
GPQA
Context
Actions
$0.100
$0.280
—
41.4
14.9
65,536
Try
$0.100
$0.400
—
—
—
1,048,576
Try
$0.100
$0.000
—
—
—
-
Try
$0.100
$0.400
—
—
—
1,047,576
Try
$0.100
$0.300
—
—
—
327,680
Try
$0.100
$0.300
—
—
—
1,048,576
Try
$0.100
$0.320
—
48.1
10.5
131,072
Try
$0.100
$0.100
—
—
—
128,000
Try
$0.100
$0.200
—
36.5
5.5
32,768
Try
$0.100
$0.500
—
—
—
-
Try
$0.100
$0.100
—
—
—
128,000
Try

* Some models use tiered pricing based on prompt length. Displayed prices are for prompts ≤ 200k tokens.

Compare Providers

Hermes 3 70B Instruct is available from multiple providers with different pricing and availability.

No multi-provider data available for this model

This model may only be available from a single provider

Community Rankings

How does Hermes 3 70B Instruct perform? Vote based on your experience.

Cost vs. Quality

Compare Hermes 3 70B Instruct's benchmark performance against all models.

X-axis:
Y-axis:
Loading chart...
Hermes 3 70B Instruct
Other models

Detailed Benchmark Scores

Intelligence
38.5 (81st pct)
Coding
-
Math
-
MMLU Pro
41.4 (80th pct)
GPQA
14.9 (45th pct)
LiveCodeBench
-
AIME
-
Aider
-
Benchmark data from Artificial Analysis and HuggingFace Open LLM Leaderboard

Try Hermes 3 70B Instruct

Use our Calculator

Estimate your costs based on expected token usage.

Open Cost Calculator

Try in Playground

Test Hermes 3 70B Instruct directly in your browser.

Open Playground

Frequently Asked Questions

Hermes 3 70B Instruct costs $0.000100 per 1,000 input tokens and $0.000280 per 1,000 output tokens.
Hermes 3 70B Instruct scores Intelligence 38.5 (81st percentile), MMLU Pro 41.4 (80th percentile), GPQA 14.9 (45th percentile). Only benchmarks with published data for this model are shown.
We compare Hermes 3 70B Instruct with 10 similarly-priced models. See the benchmark scatter plot above to compare quality vs cost.

All Nousresearch Models

See pricing for all Nousresearch models.

View all Nousresearch models →