← Model list

Apertus 70B

swiss-ai·swiss-ai/apertus-70b·GA·Open weights

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.

At a glance
Reference price$1.39 / $2.23 per 1M
Cache read · Cortecs
Lowest paid$0.46 / $2.42
Regolo AI Gateway · 3× spread
Context65,536
⚠ Providers report 30,000–65,536; the table below is authoritative
Output limit65,536
Capabilities
ReasoningTool useStructured outputTemperatureAttachments
⚠ Providers report capability flags inconsistently
Modalities
Text
Knowledge cutoff2025-09
Released / updated2025-09-02 / 2025-09-02

Quality & performance

Artificial Analysis doesn't cover this model (267 of 2059 have data). Quality data comes from independent evals covering widely used models.

Available at 2 providers2 with public prices

ProviderTierInputOutputCache readCache writeContextOutput limitStatus
Regolo AIGateway$0.46$2.4230,00030,000
CortecsGateway$1.39$2.2365,53665,536

Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.

Your usage cost

1Regolo AI$213.00
2Cortecs$390.00
The cheapest paid channel is the only channel.

Related models

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$2.23$02026-08-082026-08-132026-08-08 · Input list $1.392026-08-09 · Input list $1.392026-08-10 · Input list $1.392026-08-11 · Input list $1.392026-08-12 · Input list $1.392026-08-13 · Input list $1.392026-08-08 · Output list $2.232026-08-09 · Output list $2.232026-08-10 · Output list $2.232026-08-11 · Output list $2.232026-08-12 · Output list $2.232026-08-13 · Output list $2.232026-08-08 · Min blended $0.952026-08-09 · Min blended $0.952026-08-10 · Min blended $0.952026-08-11 · Min blended $0.952026-08-12 · Min blended $0.952026-08-13 · Min blended $0.95