Kyma APIKyma API
Nous Research

Nous Research

Hermes 3 70B

The 70B of the same tune, at 30% less per million. Keeps the steerability the 405B is chosen for and gives up depth on the hardest reasoning, which is the trade most persona and agent workloads are happy to make.

Modalities

Text → Text

Below release

fp8

Weights

Published

NousResearch/Hermes-3-Llama-3.1-70B

Where it sits in the catalogue Kyma measures

Every number against every text model Kyma prices per token — a stated rule, not a chosen line-up.

Price · input#34/69

$0.945

output $0.945

median $1.009 · best $0.0494

Price · output#15/69

$0.945

per 1M tokens generated

median $3.528 · best $0.2164

Availability · 30d#24/69

96.2%

368 observations since 2026-08-03

median 93.2% · best 100.0%

Throughput#59/69

25 tok/s

probe median, one fixed prompt

median 39.1 tok/s · best 328.7 tok/s

Response time#2/69

0.85 s

probe median, to a complete answer

median 2.34 s · best 0.69 s

Context

131K

max output 8,192

published by Nous Research, not measured here

Tick above each rail is this model, below it the other 68. Dashed rule is the field median, solid is its best. Better is left; the axis stops at the 90th percentile, so a few models sit past its right edge.

Usage

How much this model is actually called here.

Rank

#71

of 98 active models

Tokens served

88.1K

all-time

Platform share

0.0%

of all tokens

Two clocks, and why they disagree

Kyma measures this model twice. Both are real; they answer different questions.

Probe · every 6h · 30 days

0.85s to answer

One fixed prompt, on a schedule, to every model. Comparable, because the model is the only thing that changes.

Observations
368
Answered by a substitute
0

Real traffic · last 7 days

2.10s to answer

Your requests, at the lengths clients actually send. Not comparable between models, but it is what running this one feels like.

Requests
26
Completed
100%
p95
3.2 s

The gap is prompt length, not the model degrading. Use the probe figure to choose between models, the traffic figure to budget for your own.

Pricing

Pay per token. Cached input bills at this model’s own cached rate, listed below.

$0.945 /1M input$0.945 /1M output
Hobby10 req/day · 2K in / 500 out
~$0.71/mo
Production1,000 req/day · 2K in / 500 out
~$70.88/mo
Scale20,000 req/day · 2K in / 500 out
~$1,418/mo
+ Estimate your workload
1,000
2,000
500

Estimated monthly cost

$70.88

$2.36 / day on Hermes 3 70B

Same workload on:

Hermes 3 405B$101+43%
Qwen 3.8 27B$94.77+34%

Estimates use list pricing. Actual bills depend on real token counts, and every response includes its exact cost.

How it compares

Against the peers people actually weigh it against.

SpecHermes 3 70BHermes 3 405BQwen 3.8 27B
Input /1M$0.945$1.35$0.567
Output /1M$0.945$1.35$4.05
Context131K131K1M
ToolsYesYesYes
ReasoningNoNoYes
Throughput25 tok/s17 tok/s46 tok/s

Quick start

Up and running in under two minutes.

  1. 1

    Create an API key

    Sign up and grab a key from the dashboard. Hermes 3 70B needs a top-up — the signup credit covers the free tier.

    Get API key →
  2. 2

    Make your first request

    Drop in your key and send a chat completion — fully OpenAI-compatible.

    curl https://kymaapi.com/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "hermes-3-70b",
    "messages": [
      {"role": "user", "content": "Explain prompt caching in one paragraph."}
    ]
  }'
  3. 3

    Stream responses

    Add "stream": true to receive tokens as they arrive.

    curl https://kymaapi.com/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "hermes-3-70b",
    "stream": true,
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

FAQ

Common questions about this model.

What is the context window of Hermes 3 70B?

Hermes 3 70B has a 131K-token context window — roughly 193 pages of text in a single request.

How much does the Hermes 3 70B API cost?

$0.945 per 1M input tokens and $0.945 per 1M output tokens. No subscription; you pay only for what you use.

Does Hermes 3 70B support function calling?

Yes — Hermes 3 70B supports tool/function calling and structured outputs (JSON mode), so it works with agent frameworks out of the box.

Are the weights for Hermes 3 70B publicly available?

Yes. Nous Research publishes Hermes 3 70B's weights as NousResearch/Hermes-3-Llama-3.1-70B, so you can download and run the model yourself (https://nousresearch.com/wp-content/uploads/2024/08/Hermes-3-Technical-Report.pdf, read 2026-08-14). Kyma serves it because it is convenient and has failover behind it, not because it is the only way to reach it.

Is Hermes 3 70B ever served below the precision its creator released it at?

Sometimes. Hermes 3 70B was released by Nous Research at bf16 (https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-70B, read 2026-08-14), and at least one route serving it here reports fp8 — narrower than that. Weights compressed below the release usually answer close to it, but it is not the identical artefact, and nothing in the response tells you which one answered. Kyma checked the routes on 2026-09-12, so it is your call rather than a silent one.

How do I use Hermes 3 70B?

Kyma is OpenAI-compatible: point your SDK's base URL at https://kymaapi.com/v1, use your Kyma API key, and set the model to hermes-3-70b. Signing up is free, but this model needs a top-up: the $0.50 signup credit covers the free tier only.

Needs a top-up — the signup credit covers the free tier.Create account →

More models by Nous Research

ModelContextInputOutput
Nous ResearchHermes 3 405B131K$1.35$1.35