Using Nous Hermes 2 Mixtral 8x7B on OctoML (Deprecated)

Implementation guide · Hermes 2 · Nous Research

Deprecated
Open Source

OctoML (Deprecated) exposes Nous Hermes 2 Mixtral 8x7B through model ID nous-hermes-2-mixtral-8x7b-dpo. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.

Last refreshed 2026-10-18. Next refresh: weekly.

Quick Start

  1. 1
    Create an account at OctoML (Deprecated) and generate an API key.
  2. 2
    Use the OctoML (Deprecated) SDK or REST API to call nous-hermes-2-mixtral-8x7b-dpo — see the documentation for request format.
  3. 3
    You'll be billed $0.40/1M input, $0.60/1M output tokens. See full pricing.
API PortalDocumentationPricing

Code Examples

See OctoML (Deprecated) documentation for integration details.

Pricing on OctoML (Deprecated)

TypePrice (per 1M)
Input tokens$0.40
Output tokens$0.60

Capabilities

No model capability flags are currently sourced.

About Nous Hermes 2 Mixtral 8x7B

Mixtral MoE variant of Hermes trained on 1M+ GPT-4 entries for content generation and customer service. Available in quantized formats (GGUF, GPTQ, AWQ) for flexible deployment.

Full model details →

Model Specs

Released2023-12-12
Parameters8x7B
Context32K
ArchitectureMixture of Experts
Knowledge cutoff2023-12

Also available on(3)

Together AI$0.40/1MOctoAI API (Deprecated)Fireworks AI
Compare all providers →

Provider

OctoML (Deprecated)

OctoML

Seattle, Washington, United States