> ## Documentation Index > Fetch the complete documentation index at: https://docs.tess.im/llms.txt > Use this file to discover all available pages before exploring further. # Kimi K3.1 Pro > Meet Kimi K3.1 Pro, the first model in the K3.1 series: the terminal, a 3D part from views, and a financial document. Kimi K3.1 Pro is the first model in the K3.1 series. Moonshot describes it as its most capable 3T-class open-weight model to date, with a 1-million-token window. On this page it is for **the terminal, a 3D part from views, and a financial document**. | **Provider model** `kimi-k3.1-pro` | **Context** 1 million tokens | **Output** Text | **Provider** Moonshot AI | | :- | :- | :- | :- | | **Input** Text and image | **Reasoning** Yes | **Family** First K3.1 | **Weights** Announced by November 4, 2026 | Artificial Analysis still classifies the model as proprietary and lists text and image input, text output, and a 1-million-token context. Moonshot says the weights ship by November 4, 2026. The announcement does not include the license. Check the model card when the weights arrive. ## When to use K3.1 Pro, and when to use Opus 5.5 K3.1 Pro is for a terminal command with tests that already exist, a part reconstructed from views, or a brief on financial documents. Claude Opus 5.5 stays ahead on the two tests where Moonshot publishes both side by side. | | Kimi K3.1 Pro | Claude Opus 5.5 | | - | - | - | | Best for | Terminal, CAD from views, and financial documents | Open judgment, and the coding where Opus still leads Moonshot's table | | Input | Text and image | Text and image | | Context | 1 million tokens | 1M | | Speed | 41.4 tokens per second on Artificial Analysis | Faster in that band | > [!TIP] > > Use `kimi-k3.1-pro` when the task is a dossier or a change with tests. Use `kimi-k3.1-pro-highspeed` when someone is waiting for the answer. ## What Moonshot measured The figures below are the ones Moonshot published, at max reasoning effort, temperature 1.0, and top-p 0.95. Several scores for other models were taken from blogs or official leaderboards, not from the same harness. ### Terminal On Terminal-Bench 4.0, with the Claude Code harness, Moonshot measured 65.7%. On its table, GPT-6 Astra is at 58.2% and Claude Opus 5.5 at 66.4%. The other models' scores are the highest each one published on its blog or on the official leaderboard. Do not treat the three as the same run. On Kimi Code Bench 3.0, an internal test of multi-step execution and tool use, K3.1 Pro scored 61.2%, against 55.95% for K3. ### A part in 3D On BenchCAD, 3D reconstruction from renderings through CAD code, Moonshot measured 92.7% with tools, on a 1,000-file subset. On the same account, Claude Opus 5.5 is at 96.2% and GPT-6 Astra at 95.9%. Without tools, K3.1 Pro is at 72.8% and Opus 5.5 at 73.0%. ### A financial document On OfficeQA Pro v2, analysis of real financial documents delivered as images, Moonshot measured 64.4 and called the result state of the art. On Frontier Finance, 58.6. On internal tests, K3.1 Pro is up 7.2 points on financial modeling (57.6 against K3's 50.4) and 11.6 points on financial research (70.4 against 58.8). On a simulated business operation, Moonshot reports about 4.2 times K3's result (37 against 8.9). On Kimi Hallu Bench Hard, an internal stress test, the claim-level hallucination rate with tools fell from 23.4% on K3 to 8.3%. The share of responses with at least one factual error was 42.4% of the predecessor's rate. On the same test with tools, Moonshot lists GPT-6 Astra at 5.5% and Opus 5.5 at 15.0%. Without tools, it lists Astra at 4.2%, K3.1 Pro at 5.4%, and Opus 5.5 at 6.8%. Moonshot says the test was built to provoke errors and that these rates are not the rates of ordinary use. ### What was left out on purpose For the open-weight release, Moonshot says it removed cybersecurity data from mid-training and from the reinforcement-learning environment mix, and kept general programming tasks. It says the released model's offensive capability stays behind frontier proprietary models that had already been public for at least three months. This page does not describe those tasks. ## What Artificial Analysis measured | Benchmark | Kimi K3.1 Pro | What it tests | Source | | - | -: | - | - | | Terminal-Bench 4.0 | **65.7%** | Terminal coding | Moonshot | | BenchCAD, with tools | **92.7%** | CAD from views | Moonshot | | BenchCAD, without tools | **72.8%** | The same test, in one shot | Moonshot | | OfficeQA Pro v2 | **64.4** | Financial documents | Moonshot | | Intelligence Index | **55** | Aggregate index | Artificial Analysis | Artificial Analysis scored **55 on the Intelligence Index**, rank 4 of 220 models in the same class. The band median is 28. In that run the model generated 150 million output tokens, against a median of 81 million. The average cost was 2.11 dollars per index task. Output speed was 41.4 tokens per second, rank 186 of 192. The band median is near 85. That measurement is for `kimi-k3.1-pro`, not the Highspeed variant. > [!NOTE] > > The table mixes Moonshot figures with the Artificial Analysis Intelligence Index. Other models' Terminal-Bench and BenchCAD scores do not always come from the same harness. Results depend on the harness, the tools, and the effort setting. Validate on your own flow before changing a production configuration. ### Where it does not lead * At 41.4 tokens per second, standard Pro is slow. Highspeed is there for when the wait is the problem. * 150 million output tokens on the index, against a median of 81 million, is a verbose model. The task price rises with the text. * On Moonshot's Terminal-Bench 4.0 table, 65.7% sits behind Opus 5.5 at 66.4%. On BenchCAD with tools, 92.7% sits behind 96.2% and 95.9%. * On the factual stress test with tools, 8.3% is still above the 5.5% Moonshot lists for Astra. * The weights are not out yet. Artificial Analysis still classifies the model as proprietary. ## Where it creates the most value ### A terminal change, with tests The behavior is described and the tests already exist. K3.1 Pro edits, runs the check, and stops if the second attempt fails. **Expected result:** a diff inside the scope and the requested tests passing. ### A part from the views The drawing or the rendering shows the shape. The model returns measurements, what the image does not show, and the script, without treating the file as ready to print. **Expected result:** a list of what is in the view, and the gap for what still needs measuring. ### A brief on the documents The question is financial and the answer has to come from the files. The model cites the passage and lists what it did not find. **Expected result:** every number has a source, with no investment recommendation. ## How to apply it in Tess **1. Pick the terminal, the part, or the dossier** Prefer a change with tests, a part from views, or a brief on documents. For a short answer while someone is waiting, use Highspeed. **2. Close what counts as done** State the result, the files that may change, and the check that ends the task. **3. Set tools and approvals** Enable only the tools the task needs. Require confirmation before sending, publishing, or changing data. **4. Keep one effort level per session** The published scores use max effort. Changing the level mid-session drops the cache, according to the DataCamp guide drawing on the Kimi Code docs. **5. Sample before you scale** Run one full case, check what changed, and only then repeat the flow. ## Three playbooks to start ### 1. A terminal change with tests **Input:** the repository, the expected behavior, and the tests that already exist.\ **Tools:** read, edit, and run the tests. ```text theme={null} Implement only the behavior described. Edit the files you need and run the cited tests. If a test fails, fix it and run it again. If it fails a second time, stop and say what broke. Do not refactor what was not requested. ``` **Done when:** the requested tests pass and the diff stays inside the scope. ### 2. A part from the views **Input:** the views or the sketch, and the list of what to measure.\ **Tools:** image reading. ```text theme={null} Describe the part only from what the views show. Return each measurement with the source view. If a dimension is not there, write "the image does not say". Do not treat the result as ready to print and do not change the source files. ``` **Done when:** every measurement has a view, or the absence is written down. ### 3. A brief with a citation **Input:** the financial documents and the question.\ **Tools:** file reading. ```text theme={null} Answer only from what is in the documents. Cite the passage for each number. If the answer is not in the files, say you did not find it. Do not fill the gap from general knowledge and do not recommend an investment. ``` **Done when:** every fact has a source and a missing datum is explicit. ## Limits and good practice * The Kimi API list price is 2 dollars of input and 10 dollars of output per million tokens. Cache read is 0.20 dollars. DataCamp reports that this price is flat across the window and sits below K3's 3 dollars of input and 15 dollars of output. * Highspeed is faster and, on DataCamp's account, costs more. Use that variant when the wait is the limit. * On Kimi Enterprise, K3.1 Pro access starts off. An administrator has to enable it. * The model writes a lot. Ask for the answer in a format, so you do not pay for text nobody will read. * Keep a human approval for financial, legal, clinical, or high-impact decisions. See also: [Models and cost](https://docs.tess.im/en/models-and-cost.md) · [Kimi K3](https://docs.tess.im/en/kimi-k3.md) · [Claude Opus 5.5](https://docs.tess.im/en/claude-opus-5-5.md) · [Kimi K3.1 Pro — Moonshot](https://www.kimi.ai/blog/kimi-k3-1-pro) · [Kimi K3.1 Pro — Artificial Analysis](https://artificialanalysis.ai/models/kimi-k3-1-pro). This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.