Kimi K2.7 Code vs Step 5 Preview
Moonshot AI · China | StepFun · China · Updated June 2026
Quick verdict
Pick Kimi K2.7 Code for long-horizon agentic software engineering or token-efficient reasoning (~30% fewer than k2.6). 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. Choose Kimi K2.7 Code if you need self-hosting or data privacy; Step 5 Preview if you want a managed API.
Kimi K2.7 Code (Moonshot AI) and Step 5 Preview (StepFun) are two of the models people most often weigh against each other in 2026. Kimi K2.7 Code is moonshot AI's open-weight 1T-parameter MoE model (32B active) tuned for long-horizon agentic coding, always reasoning yet ~30% more token-efficient than K2.6. 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, context window and open vs. closed weights — each quantified below from the models' real specs.
Key differences at a glance
- ▸Price: nearly identical — $0.95/$4 per 1M tokens vs $1/$2.7 per 1M tokens. Cost will not be the deciding factor here.
- ▸Context window: Step 5 Preview holds 3.8× more — 1M tokens (~1,500 pages) vs 256K (~393 pages). But effective recall usually fades long before the advertised ceiling, so the bigger number only helps if the model reasons over it.
- ▸Recency: Step 5 Preview is the newer model by about 3 months (released September 20, 2026), usually meaning fresher training data and capabilities.
Side-by-side specs
| Spec | Kimi K2.7 Code | Step 5 Preview |
|---|---|---|
| Provider | Moonshot AI (China) | StepFun (China) |
| Released | June 12, 2026 | September 20, 2026 |
| Context window | 256K (~393 pages) | 1M tokens (~1,500 pages) |
| Price (in/out) | $0.95/$4 per 1M tokens | $1/$2.7 per 1M tokens |
| Open weight? | Yes — self-hostable | No — API only |
| Modalities | text, image, video, code | text, image, code |
| SWE-Bench Verified | Not published | Not published |
| MRCR v2 @ 1M | Not published | Not published |
Who wins what
Long-horizon agentic software engineering
Kimi K2.7 Code
Moonshot AI's open-weight 1T-parameter MoE model (32B active) tuned for long-horizon agentic coding, always reasoning yet ~30% more token-efficient than K2.6 — and it runs cheaper at $0.95/$4 per 1M tokens.
Token-efficient reasoning (~30% fewer than K2.6)
Kimi K2.7 Code
Moonshot AI's open-weight 1T-parameter MoE model (32B active) tuned for long-horizon agentic coding, always reasoning yet ~30% more token-efficient than K2.6 — and its weights are open while Step 5 Preview is API-only.
Open-weight 1T MoE, self-hostable
Kimi K2.7 Code
Open weights make this possible at all — Step 5 Preview is API-only, so it cannot leave the vendor's servers.
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
Its 1M tokens window holds about 3.8× more than Kimi K2.7 Code's 256K in a single prompt.
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
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 — and it carries the larger 1M tokens context.
67.7% on DeepSWE v1.1, ahead of open-weight rivals Kimi K3 (67.5%) and GLM-5.3 (66.9%)
Step 5 Preview
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 — and it is the newer of the two.
Lowest cost at scale
Kimi K2.7 Code
At $0.95/$4 per 1M tokens, it is the cheaper of the two — the gap dominates the bill on high-volume workloads.
Largest single-prompt input
Step 5 Preview
Its 1M tokens window is about 3.8× larger than Kimi K2.7 Code's 256K, fitting roughly 1,500 pages in one prompt.
Which should you pick?
A cost-sensitive startup shipping high volume
→ Kimi K2.7 Code
At $0.95/$4 per 1M tokens it undercuts Step 5 Preview, and on millions of tokens that margin decides the monthly bill.
Someone analysing very long documents or codebases
→ Step 5 Preview
Larger 1M tokens window fits more in one prompt.
A team with data-privacy or self-hosting needs
→ Kimi K2.7 Code
Open weights let you run it on your own hardware; Step 5 Preview is API-only.
Anyone whose priority is long-horizon agentic software engineering
→ Kimi K2.7 Code
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 K2.7 Code: where it fits
Moonshot AI's open-weight 1T-parameter MoE model (32B active) tuned for long-horizon agentic coding, always reasoning yet ~30% more token-efficient than K2.6. Released June 12, 2026 by Moonshot AI, it is built for long-horizon agentic software engineering, token-efficient reasoning (~30% fewer than K2.6), open-weight 1T MoE, self-hostable, and multi-turn tool use with preserved reasoning.
Its trade-offs are real: only self-reported benchmarks; no SWE-Bench Verified, and thinking mode and sampling params can't be disabled. At $0.95 in / $4 out per million tokens, it sits in the budget 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
The defining split here is open vs. closed. Kimi K2.7 Code gives you weights you control — self-host it, fine-tune it, keep data in-house, pay only for hardware. Step 5 Preview gives you a managed, always-updated API with no infrastructure to run. Teams with GPUs, privacy requirements, or huge volume often favour the open model; teams that want zero ops and the latest capabilities favour the closed one. Capability is close enough that this operational question, not the benchmark, usually decides it.
Want both Kimi K2.7 Code 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 K2.7 Code 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 K2.7 Code leans toward long-horizon agentic software engineering 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 K2.7 Code or Step 5 Preview?
Kimi K2.7 Code is open-weight, so self-hosting means no per-token fee (you pay for hardware instead), while Step 5 Preview is API-metered at $1/$2.7 per 1M tokens. For most teams without GPUs, the API model is cheaper to start; at very high volume, self-hosting can win.
Which has the bigger context window?
Step 5 Preview — 1M tokens vs 256K, about 3.8× larger. Useful only if the model actually reasons over the full window, which not all do.
Can I use both Kimi K2.7 Code and Step 5 Preview together?
Yes — a multi-model platform like LumiChats gives you Kimi K2.7 Code, 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 K2.7 Code or Step 5 Preview?
Step 5 Preview — released September 20, 2026, about 3 months after Kimi K2.7 Code.
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.