Apertus v1.5 70B

by Swiss AIChat

Open, ethically-sourced Swiss AI model for multilingual, multimodal chat and instruction following

Context
100K tokens
Max output
8,192 tokens
Parameters
72B total
Released
2026-07-24
Weights
Open
Licence
apache-2.0

Weights on Hugging Face

swiss-ai/apertus-v1-5-70b

Specifications

Full facts as recorded, incl. what is unknown.

Released
2026-07-24
Weights
Opengated
License
apache-2.0
Input
Text, Image, Audio
Output
Text
Context window
100,000 max across endpoints
Max output
8,192
Providers
1
Epoch Capabilities Index
not evaluated
Direct price range
$0.87 in · $3.10 out per 1M tokens · from its one provider
More details
Last updated
2026-08-01
Knowledge cutoff
Weights link
Hugging Face · swiss-ai/Apertus-v1.5-70B
Parameters
72B total

Capabilities

Across all endpoints: supported if any endpoint supports it.

  • Tool calling
  • Parallel toolsunknown
  • Structured outputunknown
  • Reasoning
  • Image input
  • PDF input
  • Audio input
  • Audio outputunknown
  • Video input
  • Prompt cachingunknown
  • Web searchunknown
  • Computer useunknown
  • System messagesunknown
  • Assistant prefillunknown
  • Temperature
  • Streamingunknown
  • Attachments

Endpoints

One row per provider and variant; gateways are listed separately.

Loading endpoints…

Price history

No change since 19 Oct 2026. The cheapest direct price has been $0.87 in / $3.10 out per 1M tokens at Infomaniak on every data refresh since then.

Tracked from 19 Oct 2026. Headline-eligible direct prices only, so a price the sanity check flags never draws a spike. Series as JSON

Cost calculator

Loading endpoints…

More from Swiss AI

Newest Swiss AI models in the catalogue. All Swiss AI models

ModelReleasedContextListed price
Apertus 70B Instruct2025-09-0265.5Kfrom $0.46
Apertus-8B-Instruct-2509——from $0.10
Apertus-70B-Instruct-2509——from $0.82
apertus-8b-instruct—8.2Kunpriced
Heads up: prices are indicative list rates scraped from provider pricing pages; verify with the provider before relying on them. Report incorrect data for this model