Model comparison
Kimi K2.7 Code vs Kimi K3
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 K2.7 Code
Budget
Moonshot AI
Kimi K3
Frontier · Open weights
| Specification | Kimi K2.7 Code | Kimi K3 |
|---|---|---|
| Provider | Moonshot AI | Moonshot AI |
| Tier | Budget | Frontier |
| Context window | 262K | Winner: 1.05M |
| Max output | Not verified | 1M |
| Input / 1M tokens | Winner: $0.95 | $3 |
| Output / 1M tokens | Winner: $4 | $15 |
| Weights | Closed | Open |
| Parameters | Not disclosed | 2.8T total / 104B active (MoE) |
| Reasoning levels | Not verified | low, high, max |
| Modalities | text | text, image, video |
| Released | July 22, 2026 | July 16, 2026 |
| Artificial Analysis Intelligence Index [max] (2026-08-14) | 43 | Winner: 60 |
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 K2.7 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 K3: Cache-miss input is $3 / MTok; cache-hit input is $0.30 / MTok; output $15 / MTok. API id `kimi-k3`. Default max_completion_tokens is 131,072; the 1,048,576 figure is the configurable cap (context minus prompt), not the default.
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.
Kimi K3
Open-weight frontier model scoring within a few points of the closed leaders on agentic coding.
Best for
- Agentic coding without vendor lock-in
- Self-hosting at frontier quality
- Long-context work
Watch out
2.8T parameters means self-hosting is a datacentre exercise, not a workstation one — open weights here mean provider choice, not local inference.
Benchmark
DeepSWE 1.1 in context
Both models 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
Kimi K2.7 Code is cheaper on output at $4 per million tokens against $15 for Kimi K3 — about 3.8×. Use the cheaper tier for classification, extraction, summarisation, and any task where the expensive model’s extra score does not change the accepted output. The expensive one only pays if your hardest task actually fails on the cheap tier. On DeepSWE 1.1, Kimi K2.7 Code is 30.5% Pass@1 at $2.82/task versus Kimi K3 at 68.5% / $4.65/task. These are standard-tier API rates, excluding batch and cache discounts.
Run the model pickerCommon questions
Kimi K2.7 Code vs Kimi K3
Answered from the verified figures on this page rather than general guidance.
Is Kimi K2.7 Code or Kimi K3 cheaper for input?
Kimi K2.7 Code is cheaper at $0.95 per million input tokens, against $3 for Kimi K3 — roughly 3.2× the price. Output tokens usually dominate a real bill, so weigh the output rate more heavily than the input rate. These are base rates; Kimi K2.7 Code has tiered pricing: 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 K3 has tiered pricing: Cache-miss input is $3 / MTok; cache-hit input is $0.30 / MTok; output $15 / MTok. API id `kimi-k3`. Default max_completion_tokens is 131,072; the 1,048,576 figure is the configurable cap (context minus prompt), not the default.
Is Kimi K2.7 Code or Kimi K3 cheaper for output?
Kimi K2.7 Code is cheaper at $4 per million output tokens, against $15 for Kimi K3 — roughly 3.8× the price. Output tokens usually dominate a real bill, so weigh the output rate more heavily than the input rate. These are base rates; Kimi K2.7 Code has tiered pricing: 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 K3 has tiered pricing: Cache-miss input is $3 / MTok; cache-hit input is $0.30 / MTok; output $15 / MTok. API id `kimi-k3`. Default max_completion_tokens is 131,072; the 1,048,576 figure is the configurable cap (context minus prompt), not the default.
Which has the larger context window, Kimi K2.7 Code or Kimi K3?
Kimi K3 accepts 1.05M tokens against 262K for Kimi K2.7 Code. This only matters if you routinely send very long documents or large codebases.
Should I use Kimi K2.7 Code or Kimi K3?
Kimi K2.7 Code is the budget tier and Kimi K3 the frontier tier. The useful question is whether your hardest task actually fails on the cheaper one — most production volume such as classification, extraction and summarisation does not.
Can I self-host Kimi K2.7 Code or Kimi K3?
Kimi K3 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.