Apertus 70B Instruct Intelligence, Performance & Price Analysis
Model summary
Intelligence
Artificial Analysis Intelligence Index
Speed
Output tokens per second
Input Price
USD per 1M tokens
Output Price
USD per 1M tokens
Verbosity
Output tokens from Intelligence Index
Metrics are compared against models of the same class:
- Non-reasoning models → compared only with other non-reasoning models
- Reasoning models → compared across both reasoning and non-reasoning
- Open weights models → compared only with other open weights models of the same size class:
- Tiny: ≤4B parameters
- Small: 4B–40B parameters
- Medium: 40B–150B parameters
- Large: >150B parameters
- Proprietary models → compared across proprietary and open weights models of the same price range, using a blended 3:1 input/output price ratio:
- <$0.15 per 1M tokens
- $0.15–$1 per 1M tokens
- >$1 per 1M tokens
| Reasoning | No This page shows the non-reasoning version of this model. A reasoning variant may also exist. |
|---|---|
| Input modality | Supports: text |
| Output modality | Supports: text |
| Context window | 66k ~98 A4 pages of size 12 Arial font |
| Total parameters | 70B |
| License | Apache 2.0 |
| Model weights | Hugging Face |
Apertus 70B Instruct is among the least intelligent models and particularly expensive when comparing to other open weight non-reasoning models of similar size. It's also slower than average, however highly concise. The model supports text input, outputs text, and has a 66k tokens context window.
Apertus 70B Instruct scores 8 on the Artificial Analysis Intelligence Index, placing it at the lower end among comparable models (averaging 13). When evaluating the Intelligence Index, it generated 1.1M tokens, which is very concise in comparison to the average of 3.8M.
Pricing for Apertus 70B Instruct is $0.82 per 1M input tokens (expensive, average: $0.20) and $2.92 per 1M output tokens (expensive, average: $0.57). In total, it cost $3.78 to evaluate Apertus 70B Instruct on the Intelligence Index.
At 62 tokens per second, Apertus 70B Instruct is slower than average (62).
Intelligence
Artificial Analysis Intelligence Index
Artificial Analysis Intelligence Index by Open Weights / Proprietary
Intelligence Evaluations
Openness
Artificial Analysis Openness Index: Results
Intelligence Index Comparisons
Intelligence vs. Price
Intelligence Index Token Use & Cost
Output Tokens Used to Run Artificial Analysis Intelligence Index
Cost to Run Artificial Analysis Intelligence Index
Context Window
Context Window
Pricing
Pricing: Input and Output Prices
Intelligence vs. Price (Log Scale)
Pricing Comparison of Apertus 70B Instruct API Providers
Speed
Measured by Output Speed (tokens per second)
Output Speed
Output Speed vs. Price
Latency
Measured by Time (seconds) to First Token
Latency: Time To First Answer Token
End-to-End Response Time
Seconds to output 500 Tokens, calculated based on time to first token, 'thinking' time for reasoning models, and output speed
End-to-End Response Time
Model Size (Open Weights Models Only)
Model Size: Total and Active Parameters
Frequently Asked Questions
Common questions about Apertus 70B Instruct
Apertus 70B Instruct was released on September 2, 2025.
Apertus 70B Instruct was created by Swiss AI Initiative.
Apertus 70B Instruct scores 8 on the Artificial Analysis Intelligence Index, placing it at the lower end among other open weight non-reasoning models of similar size (median: 13).
Apertus 70B Instruct generates output at 62.4 tokens per second (based on the median across providers serving the model), which is above average compared to other open weight non-reasoning models of similar size (median: 62.4 t/s).
Apertus 70B Instruct has a time to first token (TTFT) of 2.14s (based on the median across providers serving the model), which is somewhat higher than average compared to other open weight non-reasoning models of similar size (median: 1.40s).
Apertus 70B Instruct costs $0.82 per 1M input tokens (somewhat higher than average, median: $0.52) and $2.92 per 1M output tokens (somewhat higher than average, median: $0.81), 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 (3:1 input to output ratio), this is $1.34 per 1M tokens. Pricing may vary by provider. Compare provider pricing
When evaluated on the Intelligence Index, Apertus 70B Instruct generated 1.1M output tokens, which is very competitive compared to other open weight non-reasoning models of similar size (median: 3.8M).
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. View license
Apertus 70B Instruct achieves a score of 8 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. Compare API providers
Apertus 70B Instruct is available through 1 API provider. Compare providers