Swiss Ai logo

Swiss Ai: Apertus 70B

Fully open 70B multilingual LLM supporting 1800+ languages with 65K context. Trained on 15T tokens of compliant open data. Apache 2.0, EU AI Act compliant.

Source-linked Open weights Apache-2.0 Released 2025-09-02
API record Report
InputT
OutputT
Input price$0.46/M
Output price$2.42/M
Context65.536K
Max output8.192K
Providers1
Inference availability

Providers

Provider-specific identifiers, limits, and listed prices per million tokens. Every row links back to the provider's own documentation.

Report a price
Providers offering Apertus 70B
ProviderProvider model IDContextMax outputInputOutputCache readCapabilitiesDocs
Regolo AI apertus-70b 30K 30K $0.46 $2.42 Tools Docs ↗

Capability badges appear only where the provider catalog explicitly lists support. A blank cell means the source is silent, not that the feature is absent.

Listed rates

Price across providers

Input price per million tokens as published by each provider. Bars are drawn from listed rates only — no traffic weighting, since the catalog observes no requests.

Lowest input $0.46/M

Across 1 priced provider

Median input $0.46/M

Midpoint of listed rates

Highest input $0.46/M

Same as the lowest listed rate

Output range $2.42 – $2.42

Per million output tokens

Regolo AI $0.46/MLowest
Cost calculator

Estimate a workload

$0.00
Excludes taxes, non-token charges, and tiered discounts.
Specification

Capabilities

Recorded from the source catalog and provider listings.

× Reasoning No
Tool calling Yes
? Structured output Unknown
× Attachments No
× Vision input No
Open weights Yes
Creator
Swiss Ai
Model family
Not documented
Knowledge cutoff
2025-09
License
Apache-2.0
Release date
2025-09-02
Model ID
swiss-ai/apertus-70b

Weights: Hugging Face ↗

Published evaluations

Benchmarks

Every result stays attached to its source, version, metric and harness. Scores from different versions are never merged, and the profile below plots each benchmark against its own population rather than on a shared scale.

Benchmark registry
No published benchmark results

ModelBench does not infer quality from price, context size, or model name. When a source publishes a comparable result, it appears here with its version and link.

Read the methodology
Catalog activity

Change log

Field-level changes detected between successful source imports.

Full change log
No changes recorded

This record has not changed within the retained import history.

Public API

Use this record

Fetch the complete source-linked model record. No key, no account, no rate-limited tier.

API documentation
Endpoint
GET https://www.modelbench.lol/api/v1/models/swiss-ai/apertus-70b
curl
curl "https://www.modelbench.lol/api/v1/models/swiss-ai/apertus-70b"
Common questions

Frequently asked questions

Answered directly from the stored record — nothing here is generated beyond the catalog's own fields.

What is Apertus 70B?

Fully open 70B multilingual LLM supporting 1800+ languages with 65K context. Trained on 15T tokens of compliant open data. Apache 2.0, EU AI Act compliant. It is published by Swiss Ai and catalogued here from Models.dev.

How much does Apertus 70B cost?

Listed input pricing starts at $0.46 per million tokens from Regolo AI.

What is the context length of Apertus 70B?

Apertus 70B accepts up to 65.536K tokens of context and returns up to 8.192K output tokens.

Does Apertus 70B support tool calling and structured output?

Provider catalogs list support for tool calling.

Which providers serve Apertus 70B?

1 provider list this model: Regolo AI.

Are the weights for Apertus 70B open?

Yes. The weights are published and downloadable from Hugging Face under the Apache-2.0 license.

When was Apertus 70B released?

The catalog records a release date of 2025-09-02, last verified Aug 08, 2026.