Skip to content

25 listings across 25 models

Data policies

from the provider's published policies

Headquarters: US

On training

Heroku Managed Inference and Agents doesn’t use your prompts and completions to train any models and doesn’t distribute them to third parties for training.

Source: elements.heroku.com/addons/heroku-inference

On keeping your data

Heroku Managed Inference and Agents doesn’t store or log your prompts and completions.

Source: elements.heroku.com/addons/heroku-inference

Other statements

Salesforce has been issued SOC1, 2 and 3 reports by an independent auditor.

Source: Heroku security, privacy & compliance documentation

We take these statements from Heroku's own published policies each time we refresh the data, so they can change or disappear when those pages do. Check with the provider before you rely on any of this.

Sold by Heroku

25 listings sold by Heroku.

Default order. Select a score for details.

About these columns
llminfo IQ
llminfo IQ (capability index). How llminfo IQ is computed
Coding IQ
llminfo Coding IQ (coding capability, its own scale). How Coding IQ is computed
Value
Value for money. 50 means as expected for its results. Above 50, cheaper per task. How Value for money works
Yap
Tokens used per coding task vs. models with the same results. Includes agents that write code. Chattiness on maths doesn't predict it. How the Yap score works
Claude Opus 5.5🇪🇺🇺🇸 eu, us
$4.00$20.00Not published by the provider
Claude Fable 5.1🇺🇸 us
$10.00$50.00Not published by the provider
Claude Sonnet 5.5🇪🇺🇺🇸 eu, us
$2.00$10.00Not published by the provider
Claude Opus 4.8🇪🇺🇺🇸 eu, us
$5.50$27.50Not published by the provider
Claude Opus 4.7🇪🇺🇺🇸 eu, us
$5.50$27.50Not published by the provider
Claude Opus 4.6🇪🇺🇺🇸 eu, us
$5.50$27.50Not published by the provider
Claude Haiku 5.5🇪🇺🇺🇸 eu, us
$0.50$2.50Not published by the provider
Claude Opus 4.5🇪🇺🇺🇸 eu, us
$5.00$25.00Not published by the provider
Claude Sonnet 4.6claude-4-6-sonnet · 🇪🇺🇺🇸 eu, us
$3.30$16.50Not published by the provider
Claude Sonnet 4.5claude-4-5-sonnet · 🇪🇺🇺🇸 eu, us
$3.30$16.50Not published by the provider
Claude Sonnet 4heroku/claude-4-sonnet
——200K
Claude Sonnet 3.7heroku/claude-3-7-sonnet
——200K
Claude Haiku 4.5claude-4-5-haiku · 🇪🇺🇺🇸 eu, us
$1.10$5.50Not published by the provider
Claude 3.5 Sonnetheroku/claude-3-5-sonnet-latest · latest
——200KNot measured
GPT OSS 120B🇪🇺🇺🇸 eu, us
$0.15$0.60Not published by the provider
Nova 2 Lite🇺🇸 us
$0.33$2.75Not published by the providerNot measuredNot measured
Claude Haiku 3.5heroku/claude-3-5-haiku
——200KNot measured
Nova Pro🇪🇺🇺🇸 eu, us
Not enough data yet$0.80$3.20Not published by the providerNot measuredNot measured
Nova Lite🇪🇺🇺🇸 eu, us
$0.06$0.24Not published by the providerNot measured
Cohere Embed Multilingual🇪🇺🇺🇸 eu, us
Not enough data yetNot enough data yet$0.10—Not published by the providerNot enough data yetNot measuredNot measured
Embed v4cohere-embed-v4 · 🇪🇺🇺🇸 eu, us
Not enough data yetNot enough data yet$0.12—Not published by the providerNot enough data yetNot measuredNot measured
Amazon Rerank 1.0🇪🇺🇺🇸 eu, us
Not enough data yetNot enough data yet——Not published by the providerNot enough data yetNot measuredNot measured
Rerank V3.5cohere-rerank-3-5 · 🇪🇺🇺🇸 eu, us
Not enough data yetNot enough data yet——Not published by the providerNot enough data yetNot measuredNot measured
Stable Image Core🇺🇸 us
Not enough data yetNot enough data yet——Not published by the providerNot enough data yetNot measuredNot measured
Stable Image Ultra🇺🇸 us
Not enough data yetNot enough data yet——Not published by the providerNot enough data yetNot measuredNot measured

Data credits: Epoch AI Benchmarking Hub, CC BY 4.0 (licence)

How this data works