Moonshot AI has released Kimi K3.1 Pro with a 1M-token context window and API model ID kimi-k3.1-pro. The company plans to release the full weights by November 4, 2026. Availability in Tabbit depends on your account's live model picker.
Use in Tabbit
Use in Tabbit Kimi K3.1 Pro
Kimi K3.1 Pro · Model overview
Check the evidence before choosing a workflow
A compact view of reviewed task guides, public evaluations, and evidence boundaries. Client access still depends on your current account.
Kimi K3.1 Pro API quickstart: model ID, base_url, and OpenAI SDK calls
To integrate Kimi K3.1 Pro, use the model ID kimi-k3.1-pro, base_url=https://api.moonshot.ai/v1, and the OpenAI SDK's Chat Completions interface. This flagship model is unlocked only after a successful top-up of at least $1; the cumulative top-up amount determines the account tier and the concurrency, RPM, TPM, and TPD limits.
Prepare
The flagship model kimi-k3.1-pro; the official page also lists the high-speed variant kimi-k3.1-pro-highspeed, whose pricing and availability require separate verification., Python 3.9+, openai>=1.0, Kimi API Chat Completions, and clients using the same OpenAI-compatible endpoint.
Runtime
Python 3.9+, openai>=1.0, Kimi API Chat Completions, and clients using the same OpenAI-compatible endpoint.
Kimi K3.1 Pro reasoning levels and parameter configuration: reasoning_effort low, high, and max
Kimi K3.1 Pro always reasons. Set its reasoning level through the top-level reasoning_effort field in a Chat Completions request; the available values are low, high, and max, with max as the default.
Prepare
The official page explicitly covers kimi-k3.1-pro; it describes this field as K3's top-level reasoning field but does not list a compatibility matrix for other model versions., The Kimi API Chat Completions interface and compatible clients that can pass through the top-level reasoning_effort field.
Runtime
The Kimi API Chat Completions interface and compatible clients that can pass through the top-level reasoning_effort field.
API configuration · Visual prototypeSource reviewed
Kimi K3.1 Pro image and video input configuration: Base64, file IDs, and multimodal message structure
For Kimi K3.1 Pro vision requests, write the user message's content as a JSON array; images can use a Base64 image_url, while videos must be uploaded first and then referenced through a video_url using ms://<file-id>.
Prepare
kimi-k3.1-pro; the official page also lists kimi-k3, kimi-k2.6, kimi-k2.7-code, and kimi-k2.7-code-highspeed, and states that these models can understand videos., Kimi API Chat Completions; the official example uses the Python OpenAI SDK and https://api.moonshot.ai/v1.
Runtime
Kimi API Chat Completions; the official example uses the Python OpenAI SDK and https://api.moonshot.ai/v1.
Kimi K3.1 Pro JSON Schema structured output configuration: strict, MFJS, and final content parsing
Kimi K3.1 Pro uses response_format.type="json_schema" and strict=true to constrain fields, types, and nested structures; the client should parse only choices[0].message.content and should not treat reasoning_content or the entire response object as the JSON body.
Prepare
kimi-k3.1-pro., Kimi API Chat Completions; the official example uses the Python OpenAI SDK and https://api.moonshot.ai/v1.
Runtime
Kimi API Chat Completions; the official example uses the Python OpenAI SDK and https://api.moonshot.ai/v1.
Kimi K3.1 Pro official release: Evaluation boundaries for coding, 3D, and finance benchmarks
Kimi reports that K3.1 Pro scored 65.7% on Terminal-Bench 4.0, 92.7% on BenchCAD with tools, and 64.4 on OfficeQA Pro v2. These results come from different harnesses, with some based on internal benchmarks or external references, so they are useful for locating capability areas but cannot be treated as independent win rates under uniform conditions.
Evidence
Vendor report
Boundary
Treating Kimi's internal benchmarks as daily success rates; combining different harnesses, model reports, or vendor charts directly into a ranking; inferring stable production quality from examples.
Kimi K3.1 Pro: Artificial Analysis independent intelligence index, cost, and speed snapshot
In this page snapshot, Kimi K3.1 Pro has an Artificial Analysis Intelligence Index of 55 (#4/215), placing its quality signal near the top; however, 80.7 token/s, 150M index output tokens, and approximately $2.11 per task indicate that waiting time and output volume are the main costs of long-chain reasoning.
Evidence
Independent measurement
Boundary
Production billing, success rates for all Chinese-language or multimodal tasks, a fixed SLA, or absolute rankings across different evaluation harnesses.
Plotly's 43-question data analysis exam: Kimi K3.1 Pro scores 42/43
On its own PlotlyDataAnalyticsBench, Plotly asked the standard Kimi K3.1 Pro to answer 43 synthetic wind-power data questions, getting 42/43 (98%, A); it found all 5 hidden patterns and 3 data-quality issues, but one run cost $13.47 and took a median of 2.5 minutes per question, showing a clear trade-off among accuracy, proactive analysis, and cost and speed.
Evidence
Independent measurement
Boundary
Overall success rates across all data-analysis tasks, real-world wind-power business data, general reasoning rankings, stable production costs, or latency.
