*This is the markdown version of this page, for agents. To see the web page, open https://trodo.ai/models/latest?view=html (or use the Human / Agent switch at the bottom)* # Hartley 1: the best intelligence per dollar > Not just cheaper and faster. Better. The best intelligence per dollar. Up to 250× cheaper and 25× faster than a frontier judge, and more accurate than Jev and Microsoft on real agent traces. Hartley 1 is a System One decision model, in private beta. API id `hartley-1`, context 16K tokens, $0.04 per million input tokens. Output: $0. - **250×** up to · cheaper per input token than a frontier flagship - **25×** up to · faster than a frontier judge that reasons first - **74%** on real agent traces · Jev 1.13 63%, Microsoft 64% - **0.8%** wrong when it’s 90% sure · Jev 5.1%, Microsoft 9.6% - **$0** for output · $0.04 per million tokens in ## How it works 1. **State.** Send what the question is about: a trace, a ticket, a document, as text or JSON. 2. **Questions.** Ask as many as you like. Each is yes or no, pick one, rate it, or pull out a value. 3. **Decision.** Every answer comes back as numbers, in one pass. Then an if, a route, an alert. ```bash curl https://models.trodo.ai/v1/decide \ -H "Authorization: Bearer $TRODO_API_KEY" \ -H "Content-Type: application/json" \ -d '{"state": "", "questions": {"followed_policy": {"type": "noul", "instructions": "Did the agent follow its system prompt?"}}}' ``` The answer: `{"answers": {"followed_policy": {"noul": 0.04, "abstain": 0.01}}, "usage": {"output_tokens": 0}, "latency_ms": 530}`. Full reference: https://docs.trodo.ai/console ## Cheaper. Exact. Fast. - **A hundredth of the price.** $0.04 per million tokens in. $0 out. - **Nothing to make up.** Only your options, a value copied from your input, or “not enough evidence”. - **Half a second.** ~0.5 s of model time on a typical trace, ~0.2 s when you ask again. ## Frontier models bill twice. Hartley bills once. To read, and to write. Hartley charges only for reading, and nothing for the answer. | Model | Input per million tokens | Output per million tokens | Input price against Hartley | |---|---|---|---| | Claude Fable 5.1 (Anthropic) | $10 | $50 | 250× | | GPT-6 Astra (OpenAI) | $10 | $50 | 250× | | Llama 4.1 405B (Meta · on Microsoft Foundry) | $5 | $15 | 125× | | Claude Opus 5.5 (Anthropic) | $4 | $20 | 100× | | Claude Sonnet 5.5 (Anthropic) | $2 | $10 | 50× | | GPT-6.1 Sol (OpenAI) | $2 | $10 | 50× | | Gemini 3.1 Pro (Google) | $2 | $12 | 50× | | DeepSeek-V4 Pro (DeepSeek · on Microsoft Foundry) | $2 | $8 | 50× | | Claude Haiku 4.5 (Anthropic) | $1 | $5 | 25× | | Kimi K2.6 (Moonshot · on Microsoft Foundry) | $0.95 | $4 | 24× | | GPT-5.4 mini (OpenAI) | $0.75 | $4.5 | 19× | | Gemini 3.8 Flash (Google) | $0.75 | $3.75 | 19× | | Gemini 3.1 Flash-Lite (Google) | $0.25 | $1.5 | 6.3× | | Clef (Cloudflare · Workers AI) | $0.24 | $0 | 6× | | GPT-5.4 nano (OpenAI) | $0.2 | $1.25 | 5× | | DeepSeek-V4 Flash (DeepSeek · on Microsoft Foundry) | $0.2 | $0.8 | 5× | | Llama 4 Maverick (Meta · on Together AI) | $0.15 | $0.6 | 3.8× | | Clef-flash (Cloudflare · Workers AI) | $0.09 | $0 | 2.3× | | Jev 1.13 (TypeSafe) | $0.042 | $0 | 1.1× | | Hartley 1 (Trodo) | $0.04 | $0 | 1× | List prices, 4 October 2026. ## Use cases - **Evaluate every trace:** Every span, every criterion, every run. Not a sample. - **Route:** Every message to the right team, in milliseconds. - **Guard:** Injections and unsafe actions stopped inline. - **Choose tools:** Always one of your tools. Never a made-up one. - **Verify:** Is the answer backed by the source? On every call. - **Tag millions:** Tickets, emails, transcripts and logs, labelled and routed. - **React live:** Interfaces that read the room while the user is still there. - **Branch:** Smart if-statements on a real probability. - **Anything that needs a decision:** If it needs a quick judgment, Hartley makes it: the best intelligence per dollar, in one pass. ## Questions ### Is this just a classifier? A classifier is trained on a fixed set of labels and breaks the moment the question changes. Hartley takes a new question, in plain language, at the moment you ask it. ### Does it really never hallucinate? Hartley never writes anything, so it never makes anything up. Every answer is a probability over the options you gave it, a value copied word for word from your input, or “not enough evidence”. It can’t invent a fact, a category or a value. ### Is it as smart as the big language models? It is built for decisions, not for writing, planning or conversation. On real agent traces it scores 74%, against 63% for Jev 1.13, 64% for Microsoft Decision-1 and 50% for CLM-8B, for a hundredth of Claude Opus 5.5’s input price and nothing for output. Use both: a large model to plan, Hartley to decide. ### How do I know the probabilities are real? They are calibrated. When Hartley says 90%, it is right about 90% of the time. On real agent traces its most confident half of answers is 91% correct, and only 0.8% of its answers are wrong at 90% confidence or more, against 5.1% for Jev 1.13 and 9.6% for Microsoft Decision-1. ### What does it cost? $0.04 per million input tokens, and nothing for output. Ask twenty questions of one input and you pay to read it once. That is below Jev’s $0.042 and every other hosted decision model. ### What if the evidence isn’t there? Then it says so. Every question can come back “not enough evidence”. Act on the confident answers automatically and send the rest to a person or a larger model. You choose the threshold. ### Can I run it in my own environment? Yes. The same Hartley, in your cloud, with your data staying where it is. Talk to us. ### Do I need Trodo to use it? No. It works as a standalone API, and inside the workflows Trodo already watches. ## Pages - Hartley 1: https://trodo.ai/models/latest.md - Benchmarks (accuracy, price, speed): https://trodo.ai/models/latest/benchmarks.md - API access (private beta): https://console.trodo.ai/signup - API docs: https://docs.trodo.ai/console --- Web version: https://trodo.ai/models/latest?view=html · Everything about Trodo for agents: https://trodo.ai/index.md