Kev 4B
Kev 4B is a small open-weight decision model from Jared Palmer, built as a LoRA adapter and pointer head on Qwen3.5-4B-Base and served over the same /v1/systemone contract as TypeSafe's Jev. Send a state and typed questions (yes/no, multiple choice, or score) and it returns a calibrated probability per question in one forward pass, with no generated text. It is the recommended checkpoint in the Kev family (0.8B, 4B, 9B) and is suited for routing, classification, and policy checks that want a compact, Apache-2.0 alternative to Jev. Code, model cards, and eval suites: https://github.com/jaredpalmer/kev
Model card on Hugging Face- Input / output price
- $0.042 / $0.00 per 1M
- Context
- 8K tokens
- Released
- Sep 24, 2026
Paste into Claude Code, Cursor, or Codex
Help me set up the Respan gateway: fetch and follow https:/
Providers
One provider serves this model, priced per 1M tokens after gateway discounts.
| Provider | Input | Output |
|---|---|---|
OpenRouter openrouter/kev-4b | $0.042/M | $0.00/M |
Is a provider down? OpenRouter status
Pricing
USD per 1M tokens on OpenRouter, after gateway discounts.
- Input
- $0.042 per 1M
- Output
- $0.00 per 1M
Cost by volume
Total cost from 0 to 1T tokens.
Benchmarks
2 published scores from 1 source, each linked to where it was published.
Published scores
| Benchmark | Score | Source | Published |
|---|---|---|---|
| MMLUhuggingface.co | 72.5% | huggingface.co | Sep 24, 2026 |
| MMLU-Prohuggingface.co | 56.5% | huggingface.co | Sep 24, 2026 |
Apps
Use Kev 4B in the tools you already run. Each guide points the app at the Respan gateway.
Setup guides for more apps are in the integration docs.
Kev 4B FAQ
Short answers, built from the data on this page.
Kev 4B is a model from Other, released on Sep 24, 2026. Kev 4B is a small open-weight decision model from Jared Palmer, built as a LoRA adapter and pointer head on Qwen3.5-4B-Base and served over the same /v1/systemone contract as TypeSafe's Jev. Send a state and typed questions (yes/no, multiple choice, or score) and it returns a calibrated probability per question in one forward pass, with no generated text. It is the recommended checkpoint in the Kev family (0.8B, 4B, 9B) and is suited for routing, classification, and policy checks that want a compact, Apache-2.0 alternative to Jev. Code, model cards, and eval suites: https://github.com/jaredpalmer/kev.
On the Respan gateway, Kev 4B costs $0.042 per 1M input tokens and $0.00 per 1M output tokens on OpenRouter, after gateway discounts.
Kev 4B is served by OpenRouter.
Kev 4B accepts up to 8K tokens of context.
Point any OpenAI-compatible SDK at https://gateway.respan.ai/v1 with your Respan API key and set the model to "kev-4b". To set it up with a coding agent, copy the agent setup prompt at the top of this page.
Kev 4B has 2 published benchmark scores, including MMLU 72.5%. Each score links to where it was published; the data is collected by Respan.
Certified where it counts.
Built to meet the security and privacy standards that enterprise and healthcare teams require.
ISO 27001
The internationally recognized standard for information security management.
SOC 2
Secure, compliant management of your data across all of our systems.
GDPR
Operated under GDPR, the world's strictest standard for data privacy.
HIPAA
HIPAA compliant, with a BAA available for healthcare teams.