Model Library
Swiss AI InitiativeReleased September 2, 2025Apertus 70B Instruct
Swiss AI Initiative · Released September 2, 2025
Intelligence score
2
At a glance
- Intelligence
- 2
- Speed
- —
- Latency
- —
- Input price
- $0.82per 1M tokens
- Output price
- $2.92per 1M tokens
- Context window
- 66Ktokens
- Parameters
- 70billions
Summary
Comparison summary
Apertus 70B Instruct scores 2 (estimated) on the Artificial Analysis Intelligence Index, placing it at the lower end among other open weight non-reasoning models of similar size (median: 7). Apertus 70B Instruct costs $0.82 per 1M input tokens (somewhat higher than average, median: $0.53) and $2.92 per 1M output tokens (somewhat higher than average, median: $1.05), based on the median across providers serving the model.
Specifications
Technical specifications
| Model name | Apertus 70B Instruct |
|---|---|
| Provider | Swiss AI Initiative |
| Release date | September 2, 2025 |
| Intelligence score | 2 |
| Speed | — |
| Latency (TTFT) | — |
| Input price | $0.82 / 1M tokens |
| Output price | $2.92 / 1M tokens |
| Context window | 66,000 tokens |
| Parameters | 70B |
| Reasoning | No |
| Input modalities | text |
| Output modalities | — |
| Open weights | Yes |
| License | Apache 2 |
| API availability | — |
| Source | Model Intelligence legacy profile: apertus-70b-instruct |
Pricing
Token prices
Price per 1M tokens
Apertus 70B Instruct, as listed in the catalog record
- Input$0.82
- Output$2.92
| Token type | Price per 1M |
|---|---|
| Input | $0.82 |
| Output | $2.92 |
Model Intelligence legacy profile: apertus-70b-instruct
FAQ · 17
Frequently asked questions
Apertus 70B Instruct was released on September 2, 2025.
Apertus 70B Instruct was created by Swiss AI Initiative.
Apertus 70B Instruct scores 2 (estimated) on the Artificial Analysis Intelligence Index, placing it at the lower end among other open weight non-reasoning models of similar size (median: 7).
Apertus 70B Instruct costs $0.82 per 1M input tokens (somewhat higher than average, median: $0.53) and $2.92 per 1M output tokens (somewhat higher than average, median: $1.05), based on the median across providers serving the model.
Apertus 70B Instruct costs $0.82 per 1M input tokens and $2.92 per 1M output tokens (based on the median across providers serving the model). For a blended rate (7:2:1 cache hit/input/output ratio), this is $1.03 per 1M tokens. Pricing may vary by provider.
No, Apertus 70B Instruct is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.
Apertus 70B Instruct supports text input.
Apertus 70B Instruct supports text output.
No, Apertus 70B Instruct does not support image input. It can only process text.
No, Apertus 70B Instruct is not multimodal. It only supports text input.
Apertus 70B Instruct has a context window of 66k tokens. This determines how much text and conversation history the model can process in a single request.
Yes, Apertus 70B Instruct is open weights. The model weights are publicly available and can be downloaded for self-hosting.
Apertus 70B Instruct has 70 billion parameters.
Apertus 70B Instruct is released under the Apache 2.0 license. This license allows commercial use.
Apertus 70B Instruct achieves a score of 2 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.
Yes, Apertus 70B Instruct is available via API through 1 provider.
Apertus 70B Instruct is available through 1 API provider.