9 decision models, every provider
Each model is tested on every provider that serves it, because price, speed and limits differ from host to host.
- Jev 1.14TypeSafe · Text and images · closed weightsTypeSafe's newest decision model, available since 14 Oct 2026. It answers choice, score and yes/no questions about a text or JSON state in one pass and returns a probability for every option. Image input is available behind an opt-in header. It costs $0.042 per million input tokens.
- Jev 1.13TypeSafe · Text only · closed weightsThe Jev version TypeSafe's jev-latest alias pointed to on 20 Oct 2026. Text and JSON states, choice, score and yes/no questions, a probability for every option, $0.042 per million input tokens. TypeSafe launched Jev, the first decision model, on 15 Sep 2026.
- ClefCloudflare · Text and images · open weightsCloudflare's larger decision model, released on 1 Oct 2026 with open weights under Apache 2.0, post-trained from Qwen3.8-27B. It follows the same request format as Jev, takes text and up to four images, has a 65,536-token context and costs $0.24 per million input tokens on Workers AI. No other host serves it as of 20 Oct 2026.
- Clef-FlashCloudflare · Text and images · open weightsCloudflare's small decision model, a post-train of Qwen3.5-9B with a head that scores all options together, released with open weights under Apache 2.0 on 1 Oct 2026. Text and up to four images, a 24,576-token context, $0.038 per million input tokens on Workers AI.
- pplx-decider v1.2Perplexity · Text and images · closed weightsPerplexity's 27B decision model. It takes yes/no, choice (up to 255 options) and score questions with up to 8 images per question, a 256k context, and costs $0.02 per million input tokens.
- pplx-decider-flash v1.2Perplexity · Text and images · closed weightsPerplexity's 4B decision model, on the same API as pplx-decider, at $0.01 per million input tokens.
- OpenAI DecisionsOpenAI · Text and images · closed weightsOpenAI's Decisions API, in public beta as of 20 Oct 2026. It answers predicate (yes/no), choice and score questions about text and images and returns a probability for every option, at $0.10 per million input tokens.
- Microsoft-Decision-1Microsoft · Text only · closed weightsMicrosoft's decision model on Microsoft Foundry. It uses the System One request format with yes/no, choice and score questions over a text or JSON state. It needs an Azure subscription and a deployment.
- Kev-4BJared Palmer · Text only · open weightsAn open decision model from Jared Palmer, Qwen3.5-4B plus an adapter, Apache 2.0, that serves the same /v1/systemone request format as Jev. Text only. Hosted on OpenRouter at $0.042 per million input tokens.
Every model on every provider
| Model | Input | Weights | Provider | List price | Status |
|---|---|---|---|---|---|
| Jev 1.14TypeSafe | Text and images | Closed | TypeSafe APIserverless | $0.042 per million input tokens, no output charge | Not run yet |
| OpenRouterserverless | $0.042 per million input tokens (to confirm) | Not tested yet: needs an account | |||
| Jev 1.13TypeSafe | Text only | Closed | TypeSafe APIserverless | $0.042 per million input tokens, no output charge | Not run yet |
| OpenRouterserverless | $0.042 per million input tokens (to confirm) | Not tested yet: needs an account | |||
| ClefCloudflare | Text and images | Open, Apache 2.0 | Cloudflare Workers AIserverless | $0.24 per million input tokens, no output charge | Not run yet |
| Clef-FlashCloudflare | Text and images | Open, Apache 2.0 | Cloudflare Workers AIserverless | $0.038 per million input tokens, no output charge | Not run yet |
| pplx-decider v1.2Perplexity | Text and images | Closed | Perplexity APIserverless | $0.02 per million input tokens, no output charge | Not tested yet: needs an account |
| pplx-decider-flash v1.2Perplexity | Text and images | Closed | Perplexity APIserverless | $0.01 per million input tokens, no output charge | Not tested yet: needs an account |
| OpenAI DecisionsOpenAI | Text and images | Closed | OpenAI APIserverless | $0.10 per million input tokens, no output charge | Not tested yet: needs an account |
| Microsoft-Decision-1Microsoft | Text only | Closed | Microsoft Foundry (Azure)serverless | not published on Microsoft's page | Not tested yet: needs an account |
| OpenRouterserverless | $0.042 per million input tokens (to confirm) | Not tested yet: needs an account | |||
| Kev-4BJared Palmer | Text only | Open, Apache 2.0 | OpenRouterserverless | $0.042 per million input tokens, no output charge | Not tested yet: needs an account |
| Our Mac Mini (run it yourself)self-run | no per-decision price | Optional, after hosted results |
Not tested yet
- Kev-9B: no hosted API; self-host only.
- Von and Laya: no hosted API; small enough for the later run-it-yourself track.
- H2O-Lightning-4B: no hosted API; candidate for the run-it-yourself track.
- CLM-8B: no hosted API with a published model ID or price.
- Chon-1.0-12B, basal-omni-1.0-ultra, Quyet-1.0-Large: no hosted API; would need a paid GPU host.
- OpenJev: no hosted API; non-commercial licence to check.
As of 20 Oct 2026, decidingbench has not published results. The planned lineup is Jev 1.14, Jev 1.13, Clef, Clef-Flash, pplx-decider v1.2, pplx-decider-flash v1.2, OpenAI Decisions, Microsoft-Decision-1 and Kev-4B. Published figures for these models so far come from vendors (Cloudflare's leaderboard) or from boards that use written or academic items (JevBench, the Artificial Analysis Decision Index). As of this date we found no independent test against real recorded outcomes.