Kimi K3.1 Pro vs Step 5 Preview
Moonshot AI · China | StepFun · China · Updated June 2026
Quick verdict
Pick Kimi K3.1 Pro for sparse moe with 2.8t total and about 104b active parameters, post-trained from the kimi k3 base or terminal-bench 4.0 of 65.7% (moonshot) and 67% as measured by artificial analysis. Pick Step 5 Preview for sparse moe architecture — 600b total parameters, only 27b active per token — built for long-horizon agentic work across large codebases and documents or 1m-token context window (64k max output) at $1/$2.70 per million tokens, among the cheapest frontier-scale context windows available. On a tight budget at scale, Step 5 Preview is the value pick.
Kimi K3.1 Pro (Moonshot AI) and Step 5 Preview (StepFun) are two of the models people most often weigh against each other in 2026. Kimi K3.1 Pro is moonshot's October 23, 2026 post-training upgrade to Kimi K3 - a 2.8T-parameter MoE at $2/$10 with open weights promised by November 4. Step 5 Preview is stepFun's September 20, 2026 flagship preview — a 600B-parameter sparse MoE model (27B active) with a 1M-token context window at $1/$2.70 per million tokens, open weights promised for mid-October. They diverge most on price and context window — each quantified below from the models' real specs.
Key differences at a glance
- ▸Price: Step 5 Preview is about 2× cheaper on input ($1/$2.7 per 1M tokens vs $2/$10 per 1M tokens) — meaningful once you are processing millions of tokens a month.
- ▸Context window: 1M tokens vs 1M tokens — within a few percent of each other, so treat this as a tie and test on your own long inputs, since usable recall varies by model.
- ▸Recency: Kimi K3.1 Pro is the newer model by about 33 days (released October 23, 2026), usually meaning fresher training data and capabilities.
Side-by-side specs
| Spec | Kimi K3.1 Pro | Step 5 Preview |
|---|---|---|
| Provider | Moonshot AI (China) | StepFun (China) |
| Released | October 23, 2026 | September 20, 2026 |
| Context window | 1M tokens (~1,573 pages) | 1M tokens (~1,500 pages) |
| Price (in/out) | $2/$10 per 1M tokens | $1/$2.7 per 1M tokens |
| Open weight? | No — API only | No — API only |
| Modalities | text, image, code | text, image, code |
| SWE-Bench Verified | Not published | Not published |
| MRCR v2 @ 1M | Not published | Not published |
Who wins what
Sparse MoE with 2.8T total and about 104B active parameters, post-trained from the Kimi K3 base
Kimi K3.1 Pro
Moonshot's October 23, 2026 post-training upgrade to Kimi K3 - a 2.8T-parameter MoE at $2/$10 with open weights promised by November 4 — and it is the newer of the two.
Terminal-Bench 4.0 of 65.7% (Moonshot) and 67% as measured by Artificial Analysis
Kimi K3.1 Pro
Step 5 Preview is comparatively weak here — stepCodeBench and DeepSWE figures are StepFun's own reported numbers, not yet independently reproduced at scale
Artificial Analysis Intelligence Index of 55, second only to Claude Opus 5.5 (58) among the models AI Weekly lists
Kimi K3.1 Pro
Step 5 Preview is comparatively weak here — trails closed frontier models on coding — 67.7% on DeepSWE v1.1 vs GPT-6 Astra's 74.1% and Claude Opus 5's 74.0%
Sparse MoE architecture — 600B total parameters, only 27B active per token — built for long-horizon agentic work across large codebases and documents
Step 5 Preview
Kimi K3.1 Pro is comparatively weak here — very high output-token use: roughly 150M output tokens across the Artificial Analysis index
1M-token context window (64K max output) at $1/$2.70 per million tokens, among the cheapest frontier-scale context windows available
Step 5 Preview
At $1/$2.7 per 1M tokens it undercuts Kimi K3.1 Pro ($2/$10 per 1M tokens), and that gap compounds at volume.
67.7% on DeepSWE v1.1, ahead of open-weight rivals Kimi K3 (67.5%) and GLM-5.3 (66.9%)
Step 5 Preview
Kimi K3.1 Pro is comparatively weak here — weights promised by November 4, 2026 and not confirmed public as of November 3; license terms not yet disclosed
Lowest cost at scale
Step 5 Preview
At $1/$2.7 per 1M tokens, it is the cheaper of the two — the gap dominates the bill on high-volume workloads.
Which should you pick?
A cost-sensitive startup shipping high volume
→ Step 5 Preview
At $1/$2.7 per 1M tokens it undercuts Kimi K3.1 Pro, and on millions of tokens that margin decides the monthly bill.
Someone analysing very long documents or codebases
→ Kimi K3.1 Pro
Larger 1M tokens window fits more in one prompt.
Anyone whose priority is sparse moe with 2.8t total and about 104b active parameters, post-trained from the kimi k3 base
→ Kimi K3.1 Pro
It is specifically built for that.
Anyone whose priority is sparse moe architecture — 600b total parameters, only 27b active per token — built for long-horizon agentic work across large codebases and documents
→ Step 5 Preview
That is its strongest area.
Kimi K3.1 Pro: where it fits
Moonshot's October 23, 2026 post-training upgrade to Kimi K3 - a 2.8T-parameter MoE at $2/$10 with open weights promised by November 4. Released October 23, 2026 by Moonshot AI, it is built for sparse MoE with 2.8T total and about 104B active parameters, post-trained from the Kimi K3 base, terminal-Bench 4.0 of 65.7% (Moonshot) and 67% as measured by Artificial Analysis, artificial Analysis Intelligence Index of 55, second only to Claude Opus 5.5 (58) among the models AI Weekly lists, and standard API price cut by a third versus K3 to $2/$10 per million tokens (Highspeed tier $4/$20).
Its trade-offs are real: weights promised by November 4, 2026 and not confirmed public as of November 3; license terms not yet disclosed, very high output-token use: roughly 150M output tokens across the Artificial Analysis index, self-hosting is impractical - about 1.4 TB of raw weights even at 4-bit, and most benchmarks are internal or use differing harnesses; no SWE-bench Verified figure published. At $2 in / $10 out per million tokens, it sits in the mid price band.
Step 5 Preview: where it fits
StepFun's September 20, 2026 flagship preview — a 600B-parameter sparse MoE model (27B active) with a 1M-token context window at $1/$2.70 per million tokens, open weights promised for mid-October. Released September 20, 2026 by StepFun, it is built for sparse MoE architecture — 600B total parameters, only 27B active per token — built for long-horizon agentic work across large codebases and documents, 1M-token context window (64K max output) at $1/$2.70 per million tokens, among the cheapest frontier-scale context windows available, 67.7% on DeepSWE v1.1, ahead of open-weight rivals Kimi K3 (67.5%) and GLM-5.3 (66.9%), and scores 44 on the Artificial Analysis Intelligence Index, ranking 27th of 653 models tracked.
Its trade-offs: trails closed frontier models on coding — 67.7% on DeepSWE v1.1 vs GPT-6 Astra's 74.1% and Claude Opus 5's 74.0%, open weights were promised for October 15, 2026 but hadn't shipped as of this writing — API-only for now despite the open-weight roadmap, a 'Preview' release, not StepFun's finished flagship — positioning and pricing may change once weights ship, and stepCodeBench and DeepSWE figures are StepFun's own reported numbers, not yet independently reproduced at scale. At $1 in / $2.7 out per million tokens, it sits in the budget price band.
The bottom line for this matchup
Kimi K3.1 Pro and Step 5 Preview overlap enough that the right pick depends on your specific job. Step 5 Preview costs less per token; Kimi K3.1 Pro holds the larger context; and each leads in its own area — Kimi K3.1 Pro for sparse moe with 2.8t total and about 104b active parameters, post-trained from the kimi k3 base, Step 5 Preview for sparse moe architecture — 600b total parameters, only 27b active per token — built for long-horizon agentic work across large codebases and documents. Rather than crowning one, run the same hard task through both once and let the results decide.
Want both Kimi K3.1 Pro and Step 5 Preview without two subscriptions? LumiChats gives you these plus 40+ models under one ₹69/day pass (about $1/day) — draft with one, cross-check with the other.
See pricingFrequently asked questions
Is Kimi K3.1 Pro or Step 5 Preview better for coding?
Public SWE-Bench figures are not available for either model, so the honest test is your own repository — run an identical real bug through both. By design, Kimi K3.1 Pro leans toward sparse moe with 2.8t total and about 104b active parameters, post-trained from the kimi k3 base while Step 5 Preview leans toward sparse moe architecture — 600b total parameters, only 27b active per token — built for long-horizon agentic work across large codebases and documents, and that positioning usually predicts which feels better on your codebase.
Which is cheaper, Kimi K3.1 Pro or Step 5 Preview?
Step 5 Preview is cheaper — $2/$10 per 1M tokens vs $1/$2.7 per 1M tokens, roughly 2× apart on input.
Which has the bigger context window?
Effectively neither — 1M tokens vs 1M tokens is a difference of a few percent. Remember advertised ≠ usable: recall typically degrades before the ceiling.
Can I use both Kimi K3.1 Pro and Step 5 Preview together?
Yes — a multi-model platform like LumiChats gives you Kimi K3.1 Pro, Step 5 Preview and 40+ others under one ₹69/day pass (about $1/day), so you can draft with one and cross-check with the other instead of buying two subscriptions.
Which is newer, Kimi K3.1 Pro or Step 5 Preview?
Kimi K3.1 Pro — released October 23, 2026, about 33 days after Step 5 Preview.
Related comparisons
Specifications and benchmarks reflect publicly reported figures as of June 2026 and may change as providers release updates. Always verify on your own workload.