KAT-Coder-Air V2.5
Kwaipilot · released Jul 10, 2026
- Type
- Proprietary
- Input
- None held
- Output
- None held
- Cached
- None held
We don't hold a list price for this model yet · hosted only — we hold no downloadable copy
Our take
Written Aug 3, 2026KAT-Coder-Air V2.5 is a hosted-only coding model from Kwaipilot that can handle up to 256,000 tokens in a single request. It is available through two providers at the same rate, with no measured quality scores yet in our data.
Pick this for long-context code review or large-file analysis where you need a quarter-million-token request limit. Use it when StreamLake's measured throughput of 197 tokens per second meets your latency needs, or when you want identical pricing across both tracked hosts. Skip it if you need image or video input, if you require published benchmark scores to compare quality, or if you want to self-host or run the model on your own hardware.
The case for it
- Very long context for code work: 256,000 tokens in a single request, enough for large repositories or extensive review tasks.
- Identical pricing across both tracked providers, so switching hosts does not change cost.
The case against it
- No measured quality data: no Elo, coding benchmark or reasoning score is listed in our catalogue.
- Size and architecture are undisclosed by the vendor, so there is no way to estimate hardware needs or compare density.
- Only two tracked offers, with no cheaper tier available across either host.
How good is it?
We hold no score for this model.
We look for every model we track on every board we watch, and none of them has turned up KAT-Coder-Air V2.5 — so there is no intelligence, coding, agentic or writing score to show you, not a low one, none.
Or rent it from someone else
Cheapest of 2 live listings. Picked at the widest standard context we hold, within one quantisation slice, so the numbers beside it are a price one host actually charges.
- per 1M tokens
- $0.15 in / $0.60 out
- Context served
- 256K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouter | $0.15 / $0.60 | 256K | not measured | Unknown | Unknown | Unknown |
| StreamLake | $0.15 / $0.60 | 256K | 112 tok/s | No | Yesunknown period | Unknown |
Across the 2 listings we hold: 1 say they do not train on prompts, 0 say they do and 1 do not say. 0 appear in the zero-retention registry we check; the rest are unknown to us rather than confirmed either way.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
- ✓
- Supported
- ✗
- Not supported
- Not published
- host gave no parameter list
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouter | ✓ | ✓ | ✓ |
| StreamLake | ✓ | ✓ | ✓ |
Tool calling: 2 of 2 listings say yes. JSON output: 2 of 2 listings say yes. Strict schema: 2 of 2 listings say yes.
When we formed this view
Dates behind this page
Prices last checked 9d ago
What we do not know about this model yet
- No board we watch has turned up a score, so we hold no quality figures at all.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 1 of 2 listings do not say whether they train on prompts.
- We don't hold a list price for this model yet — the gap is ours, not the lab's.
Licence and identifiers
What the licence allowsWe hold no licence record for this model. Inside are the identifiers you need to pull it — its Hugging Face repo where we have one, our slug and a machine-readable card.
Licence
Commercial API terms. We hold no licence record for this model, so there is nothing to summarise here.
Identifiers
- Modality record
- text->text
- Catalogue slug
- kwaipilot-kat-coder-air-v2-5