Choose the next step for an agent acting in a UI, game or environment
Four or more companies' docs show a full fit.
What counts as done
A move per call, chosen from the offered options.
Measured, for our own tests: each move in under 400 ms hosted or 200 ms local, the episode completed at least as often as a rule baseline, without always picking the first option. No docs we read state these figures, so they don't count against a listing here.
How agents ask for it: which direction should the agent move
, click, wait, retry or stop
, which link on this page leads to the target
, is the game state winning
Does the job 6
The docs show it meets the test above, and nothing we read says otherwise.
| Listing | Why |
|---|---|
| Clef B Cloudflare, Inc. | Images on Workers AI (up to 4 per request, 16 megapixels each) and video through the weights or Clef-omni; Clef-flash median 38.8 ms, Clef 209 ms. No option-order control. source |
| Decision 3.0 B vLLM Semantic Router project | Images (several, up to 1.6 megapixels) and video at 2 frames a second; d3-mini answers an image request in 112 ms median, d3 in 290 ms; permutation_average counters first-option bias. source |
| Liquid d1 C Liquid AI, Inc. | Up to 8 base64 images a request on the hosted API at 0.20 s p50 (Arize); d1-2B adds video and runs on MLX and llama.cpp locally. source |
| OpenAI Decisions API A OpenAI OpCo, LLC | Images as base64 or public URLs, conversation and tool outputs in input, 0.16 s p50 at Arize, and a voice guide for GPT-Live action selection. No option-order control. source |
| pplx-decider BB Perplexity AI, Inc. | Up to 8 base64 images a question at 2,048 tiles each, a browser-agent cookbook asking six questions a screenshot; images over the tile cap time out at 504 rather than failing fast. source |
| pplx-decider-flash B Perplexity AI, Inc. | Images up to 8 a question on the hosted API and the Mac app; the 4B is built for latency, and the Mac app's examples label screenshots locally. source |
Does the job, with a limit 15
It does the job, but something in the docs or a user's account will get in an agent's way. The limit is named in each row.
| Listing | Why |
|---|---|
| Celeris-1 Decision D Marqo Inc | Up to 8 images a request at 25 megapixels, read in order as image_1, image_2. No published latency for the decision model and no control for option order. source |
| Laya BB Convai Innovations Pvt. Ltd. | Fast enough at 33 ms on a GPU, but the core checkpoints read text only (images route to the optional vega engine) and issue 131 shows a position bias on score options. source |
| Decider BB Mark Marosi (Mapika) | Images in /v1/systemone since 1.10.0 on the CUDA Python path (GGUF is text only); the README's browser results are 22 click-only MiniWoB++ tasks and issue 9 shows a destructive click. 133 ms on MPS. source |
| Drex Max v1 C Nace AI, Inc. | Images need the Python loader on an NVIDIA GPU (up to 4,194,304 pixels each); the GGUF, Q4, Kapitsa and MLX paths read text only. Public vision index 73.92 is the vendor's run. No latency figure for image requests. source |
| elephant-1 D Baseten Labs, Inc. | Images are accepted, but the report says the vision encoder is frozen and training ran on text alone, so image decisions are untested by the authors. No per-decision latency on the card. source |
| Kev BB Jared Palmer | Text only, no image input; a chess demo and the permute endpoint cover order bias, and Kev-4B answers in 18 ms on an H100. Screenshot environments need a text description. source |
| JEV-27B-VL C AutoTrust AI Lab | Reads screenshots and camera images: about 150 to 300 ms a decision in the Mario, Tetris and robot-arm demos and 239 ms a robot-arm step, on an 80 GB GPU. Over the 200 ms local target and no order control. source |
| joey-1 C Baseten Labs, Inc. | Images are accepted, but the report says the vision encoder is frozen and training ran on text alone, so image decisions are untested by the authors. No per-decision latency on the card. source |
| mammoth-1 D Baseten | Images are accepted, but the report says the vision encoder is frozen and training ran on text alone, so image decisions are untested by the authors. No per-decision latency on the card. source |
| Drex 1.5 BB Nace AI, Inc. | Images (up to 8 PNG or JPEG) are accepted on the Drex Max models only, as an images array or the TypeSafe multipart form. No latency figure for image requests. source |
| RightNow System Zero B RightNow AI, Inc. | Images, 16 kHz WAV audio, PDFs and preview video as inline input, each with its own file fee (USD 0.011 an image); a measured latency table exists but no guarantee. Uncalibrated probabilities. source |
| SPEV D Sprag AI, Inc. | One inline image per request plus audio and video; no latency figure, one image means no before-and-after comparison. source |
| kettei C Sqwish Ltd, trading as Sqwish Labs | kettei-chub and kettei-fat read up to 8 pictures with the context; the default kettei-core is text only and no latency is published. source |
| Strands Decider 2B B Amazon Web Services, Inc. | Text first; the Qwen3.5 v1 model answers over images zero-shot with the vision extra (Gemma 4 models are text only), 115 ms on a GPU, and the 55 percent first-answer preference measured by AWS Builder. source |
| Jev B TypeSafe AI, Inc. | Images via the TypeSafe-Danger-Zone-Images header and replies under 400 ms through OpenRouter, but the jaggedness page records a lean to the first option and users saw Jev keep picking the first move in a six-room map and fail basic mazes. source |
Doesn't do this job 5
Listings in the category that do something else, with the reason.
| Listing | Why |
|---|---|
| GLiClass C Knowledgator Engineering Ltd. | Text only; no image input in the pipeline or server. source |
| Granite Switch 4.1 B International Business Machines Corporation | Text and audio only; the model pages document no image input. source |
| Microsoft-Decision-1 E Microsoft | Text and JSON input only; OpenRouter lists text as the sole input modality. source |
| ScaleDown E Carbon ScaleDown, Inc. | Images and PDFs are OCR-extracted to text before classification, so the model never reads pixels; no screenshot decisions. source |
| Vela 2.0 BB vLLM Semantic Router project (with KR Labs) | Text only; the card documents no image input. source |
1 listings in the category were added after this reading and aren't marked yet.
What stops agents finishing
- first-option bias stalls exploration
- models fail multi-step reasoning such as mazes
- images need a CUDA loader on several open models
Around it
Before: browser-automation.screenshot, computer-use.read-screen. After: browser-automation.click, computer-use.act.
Where this comes from
Weight 7 of 100 in Decision models: 6 of 41 accounts, all small experiments (mazes, rooms, games, form filling); weighted below the business uses because none was in production
The same as data: /api/v1/use-cases/decision-models.agent-step-choice.json, or the MCP tool get_use_case with id decision-models.agent-step-choice. Other jobs in this category: /api/v1/niches?category=decision-models.
For companies
Do agents find, use and choose your tools?
An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.