Apertus v1.5 70B
infomaniak/apertus-v1-5-70bVon infomaniak · veröffentlicht 2026-07-24
Prices in USD per 1M tokens. Unknown means the provider does not publish per-token pricing.
Fähigkeiten
Model fit scores
0–100 · higher is betterThese scores reward declared capabilities, context size, price and provider availability — they are not benchmark results. Use them as a directional signal alongside your own evaluation.
Coding41
- Tool calling40/40
- Structured output0/20
- Reasoning0/10
- Context window (100K → 1M)0/20
- Provider availability1/10
Agents41
- Tool calling35/35
- Structured output0/25
- Reasoning0/15
- Output token limit5/15
- Provider availability1/10
JSON / structured output42
- Structured output / JSON mode0/50
- Tool calling20/20
- Temperature control10/10
- Price-friendly for high-volume12/20
Cost efficiency48
- Headline price (log-scaled)48/95
- Has prompt-cache pricing0/5
Long context40
- Context window (100K → 2M)30/90
- Has published price for full window10/10
Vision76
- Accepts image input50/50
- Context window (10K → 1M)15/30
- Has published price10/10
- Provider availability1/10
Production-readiness65
- Number of independent providers5/40
- Has published per-token price20/20
- Context window ≥ 8K15/15
- No data inconsistencies across providers10/10
- Official model (not derivative)15/15
Cost Efficiency Index
Open full calculator →Estimated cost using the recommended provider's headline rate. Each scenario fixes average input/output tokens — the assumptions are shown in the third column.
| Scenario | Cost | Assumption |
|---|---|---|
RAG answer per 1,000 RAG answers | $5.90 < $0.01 per request | 5K input tokens (query + 4 retrieved chunks of ~1K each) and a 500-token answer. Typical SaaS knowledge-base bot. |
Support ticket triage per 10,000 tickets | $11.80 < $0.01 per request | 1K input tokens (ticket body + system prompt) and a 100-token JSON classification reply. High-volume customer support. |
Data extraction per 1,000 documents | $3.29 < $0.01 per request | 2K input tokens (a single document page) and a 500-token JSON extraction. ETL / invoice / form pipelines. |
Code review per 1,000 PRs | $10.06 $0.01 per request | 8K input tokens (diff + surrounding files) and a 1K-token review comment. PR-bot workloads. |
Agent step per 1,000 steps | $12.30 $0.01 per request | 12K input tokens (long-running tool history) and a 600-token tool-call decision. Cost per agent step. |
Preis-Details
Empfohlene Preise von infomaniak · swiss-ai/Apertus-v1.5-70B
Bei 1 Anbietern verfügbar
| Anbieter | Anbieter-Modell-ID | Eingabe / 1M | Ausgabe / 1M | Kontext | Veröffentlicht |
|---|---|---|---|---|---|
| Infomaniak infomaniak | swiss-ai/Apertus-v1.5-70B | $0.870 | $3.10 | 100K | 2026-07-24 |
Frequently asked questions
How much does Apertus v1.5 70B cost?
Apertus v1.5 70B costs $0.870 per 1M input tokens and $3.10 per 1M output tokens, sourced from infomaniak. Cache reads, audio tokens and >200K-context tiers (where applicable) are listed in the Pricing detail block above.
What is the context window of Apertus v1.5 70B?
Apertus v1.5 70B has a context window of 100K tokens, with a max output of 8K tokens per reply. This is the total combined size of prompt + completion.
Does Apertus v1.5 70B support tool calling?
Yes. Apertus v1.5 70B supports tool calling (function calling). This makes it suitable for production agent and automation workloads where the model has to invoke external functions reliably.
Does Apertus v1.5 70B support structured output / JSON mode?
Support for structured output / JSON-schema-constrained decoding is not reported for Apertus v1.5 70B in our data source. Verify with infomaniak's official documentation before relying on it in production.
Can Apertus v1.5 70B accept image input?
Yes. Apertus v1.5 70B accepts both text and image input. Vision pricing per image is usually billed on top of the regular token rate — check infomaniak's docs for the exact rule.
Is Apertus v1.5 70B open-weight?
Yes. Apertus v1.5 70B's weights are publicly available, so you can self-host or fine-tune. Note that open weights ≠ open source — the training data and code are typically not released.
What are the best alternatives to Apertus v1.5 70B?
If Apertus v1.5 70B doesn't fit, consider All-MiniLM-L12-v2. Each one targets the same use case — see the Related links below for direct head-to-head pages.
Where does this data come from?
All numbers are normalised into a single canonical model record and reconciled with each provider's official documentation. We re-pull daily and write any changes (price, context, capability) to the /changelog page.
Explore more
More infomaniak models
- All-MiniLM-L12-v2Unknown pricing
Capability lists this model is in
Zuletzt aktualisiert:
Pricing and capabilities are refreshed daily and reconciled against each provider's official documentation. Always verify critical production decisions with the provider directly.