Inceptron AB
EU-based (Lund, Sweden) model optimization and inference platform; API payloads discarded immediately after processing by default. Requesty routes to 3 Inceptron AB models starting at $0.28 per 1M input tokens with context windows up to 262K tokens. One API key, OpenAI-compatible SDK, no markup.
All Inceptron AB models
| Model | Context | Max Output | Input/1M | Output/1M | Capabilities | SWE-Bench |
|---|---|---|---|---|---|---|
minimax-m2.5 | 197K | 197K | $0.28 | $1.10 | 🧠🔧⚡ | — |
kimi-k2.6 | 262K | 262K | $0.80 | $3.50 | 👁🧠🔧⚡ | — |
glm-5.1 | 203K | 203K | $1.40 | $4.40 | 🔧 | — |
About Inceptron AB on Requesty
How many Inceptron AB models are available through Requesty?
Requesty routes to 3 Inceptron AB models including regional variants, with pricing synced in real time to the upstream provider.
What is the cheapest Inceptron AB model?
The cheapest Inceptron AB model starts at $0.28 per million input tokens. See the pricing column in the table below for full per-model rates.
Does Requesty add markup on Inceptron AB pricing?
No. Requesty passes through exactly what Inceptron AB charges. You pay the same per-token rates as going direct — plus you get smart routing, caching, analytics, and one unified API for 400+ models.
Is my data used to train Inceptron AB models?
Inceptron AB's terms state that API data is not used for training. See their privacy policy for the authoritative statement.
Where are Inceptron AB models hosted?
Inceptron AB models are hosted in 🇪🇺 EU (Sweden). Some models are available in additional regions through AWS Bedrock, Azure, or Google Vertex AI — filter by region on the Inceptron AB rows in the models explorer.