Model comparison
Kimi K2.6 vs Kimi K2.7 Code
Two Moonshot AI tiers compared on the figures that decide which one a workload actually needs.
Catalog record checked August 19, 2026; individual provider fields may change.
Moonshot AI
Kimi K2.6
Budget · Open weights
Moonshot AI
Kimi K2.7 Code
Budget
| Specification | Kimi K2.6 | Kimi K2.7 Code |
|---|---|---|
| Provider | Moonshot AI | Moonshot AI |
| Tier | Budget | Budget |
| Context window | 262K | 262K |
| Max output | Not verified | Not verified |
| Input / 1M tokens | $0.95 | $0.95 |
| Output / 1M tokens | $4 | $4 |
| Weights | Open | Closed |
| Parameters | 1T total / 32B active (MoE) | Not disclosed |
| Reasoning levels | Not verified | Not verified |
| Modalities | text, image, video | text |
| Released | April 21, 2026 | July 22, 2026 |
| Artificial Analysis Intelligence Index (2026-08-14) | Winner: 45 | 43 |
Prices are USD per million tokens at standard rates, excluding batch and caching discounts. Bold indicates the better figure where one is objectively better. Values we could not confirm from the provider are shown as “Not verified” rather than estimated.
Pricing tiers: Kimi K2.6: Cache-hit input is $0.16 / MTok; cache-miss input is $0.95 / MTok; output $4.00 / MTok (Moonshot list). · Kimi K2.7 Code: Moonshot coding SKU `kimi-k2.7-code`: cache-hit input $0.19 / MTok, cache-miss $0.95 / MTok, output $4.00 / MTok. Highspeed sibling `kimi-k2.7-code-highspeed` is $1.90 / $8.00 (cache-hit $0.38) — not this row.
Kimi K2.6
Open-weight mixture-of-experts model priced well below the closed frontier tiers.
Best for
- Cost-sensitive volume
- Self-hosting
- Avoiding vendor lock-in
Watch out
262K context is among the smaller windows here — a real constraint on long-document work.
Kimi K2.7 Code
Moonshot's dedicated coding API identity — same $0.95/$4.00 miss/output band as Kimi K2.6, but a distinct product buyers pick for coding agents.
Best for
- Hosted coding agents
- Moonshot coding workloads
- Cost-sensitive code completion
Watch out
Not a drop-in for Kimi K3 or K2.6 general chat. Highspeed is a separate, higher-priced id. Do not invent open-weight status — this row is the hosted coding API.
Benchmark
DeepSWE 1.1 in context
Only Kimi K2.7 Code has a published DeepSWE 1.1 result. It is shown against the wider field, with cost per completed task alongside the score.
Local leader
Claude Opus 5 [max]
74%
Rows shown
24
Highest published reasoning effort per model (not best Pass@1)
Snapshot date
2026-08-13
Mirrored from deepswe.datacurve.ai
Better is toward the top-right (higher pass rate, lower cost). X-axis is reversed to match DeepSWE’s public chart. v1.1 uses average cost / tokens / steps; v1 uses published medians.
| # | Model | Pass@1 | Cost / task | Tokens / task | Steps / task |
|---|---|---|---|---|---|
| 1 | Claude Opus 5 [max] | 74% | $11.84 | 118k | 99 |
| 2 | GPT-5.6 Sol [max] | 73% | $8.39 | 60k | 61 |
| 3 | Claude Fable 5 [max] | 70% | $21.63 | 119k | 88 |
| 4 | GPT-5.6 Terra [max] | 70% | $4.95 | 72k | 76 |
| 5 | Kimi K3 [max] | 69% | $4.65 | 82k | 98 |
| 6 | GPT-5.6 Luna [max] | 67% | $3.03 | 73k | 102 |
| 7 | GPT-5.5 [xhigh] | 67% | $7.23 | 46k | 82 |
| 8 | Grok 4.6 [xhigh] | 67% | $5.50 | 71k | 87 |
| 9 | Gemini 3.7 Flash [high] | 65% | $2.18 | 107k | 125 |
| 10 | DeepSeek V4-Pro [max] | 63% | $0.24 | 106k | 155 |
| 11 | Claude Opus 4.8 [max] | 59% | $13.22 | 135k | 120 |
| 12 | Qwen3.8-Max [xhigh] | 58% | $3.73 | 95k | 111 |
| 13 | Muse Spark 1.2 [xhigh] | 55% | $3.70 | 99k | 101 |
| 14 | Claude Sonnet 5 [max] | 54% | $26.40 | 214k | 268 |
| 15 | Grok 4.5 [high] | 54% | $2.42 | 36k | 61 |
| 16 | DeepSeek V4-Flash [max] | 53% | $0.10 | 108k | 153 |
| 17 | Muse Spark 1.1 [xhigh] | 53% | $2.36 | 74k | 96 |
| 18 | GPT-5.4 [xhigh] | 52% | $5.65 | 71k | 70 |
| 19 | Gemini 3.6 Flash [high] | 47% | $4.42 | 96k | 117 |
| 20 | GLM 5.2 [max] | 44% | $3.92 | 78k | 129 |
| 21 | Gemini 3.5 Flash [high] | 36% | $3.45 | 76k | 105 |
| 22 | Kimi K2.7 Code | 31% | $2.82 | 59k | 149 |
| 23 | Claude Sonnet 4.6 [high] | 30% | $5.52 | 76k | 134 |
| 24 | Gemini 3.1 Pro [high] | 12% | $2.14 | 28k | 76 |
DeepSWE “Best” picks the highest published reasoning effort per model (not the highest pass rate). Small gaps may not be statistically meaningful — confirm on deepswe.datacurve.ai.
When the cheaper one wins
Both charge $4 per million output tokens at standard rates, so output price is not the split. Prefer the row whose “best for” line matches the job, then confirm the live vendor rate.
Run the model pickerCommon questions
Kimi K2.6 vs Kimi K2.7 Code
Answered from the verified figures on this page rather than general guidance.
Is Kimi K2.6 or Kimi K2.7 Code cheaper for input?
Both cost $0.95 per million input tokens at standard rates, so input price is not a deciding factor between them.
Is Kimi K2.6 or Kimi K2.7 Code cheaper for output?
Both cost $4 per million output tokens at standard rates, so output price is not a deciding factor between them.
Which has the larger context window, Kimi K2.6 or Kimi K2.7 Code?
Both accept about 262K tokens of context, so document length will not decide between them.
Should I use Kimi K2.6 or Kimi K2.7 Code?
Both sit in the budget tier, so the choice usually comes down to price and context rather than capability. Kimi K2.6 suits cost-sensitive volume; Kimi K2.7 Code suits hosted coding agents.
Can I self-host Kimi K2.6 or Kimi K2.7 Code?
Kimi K2.6 publishes open weights, but self-hosting and third-party provider access depend on the licence, hardware, serving support, and availability. Kimi K2.7 Code is a closed model whose supported access paths are controlled by its provider.
Next step
Choosing between them
Tier and workload decide this more reliably than a leaderboard position does.
If both sit in the same tier, the decision usually comes down to context window and output price rather than headline capability — output tokens dominate real bills.
If one is a step up within the same provider, the useful question is whether your hardest task actually fails on the cheaper tier. Most production volume — classification, extraction, summarization — does not.
Choosing a harness rather than a model — Cursor, Copilot, Claude Code, Muse Code, or Lovable? Compare agentic harnesses · Latest releases.