← Model list
Kimi K2.6
moonshotai·moonshotai/kimi-k2.6·BETA·Open weights·kimi-k2 series
Multimodal Kimi workhorse for agent loops, coding tasks, and visual context
At a glance
Official price$0.95 / $4.00 per 1M
Cache read $0.16 · Moonshot AI
Lowest paid$0.22 / $1.14
DevPass (LLM Gateway) Gateway · 8.1× spread
5 more $0 channels
Context262,144
⚠ Providers report 65,536–262,144; the table below is authoritative
Output limit262,144
Capabilities
✓ Reasoning✓ Tool use✓ Structured output✓ Temperature✓ Attachments
⚠ Providers report capability flags inconsistently
Modalities
TextImageVideoPDF
Knowledge cutoff2025-01
Released / updated2026-04-21 / 2026-04-21
Quality & performanceArtificial Analysis · Intelligence Index v4.1
Intelligence45.1
Value100
Coding61.8
Agentic31.2
Output speed46 tok/s
TTFT2.74 s
Cost per task$0.3653
Value formulaIQ 45.1 ÷ min blended $0.449 = 100
Reasoning tier → intelligence / speed (higher tier = stronger but slower)
Non-reasoningIQ 35.4 · 40 tok/s
defaultIQ 45.1 · 46 tok/s
Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.
Available at 65 providers59 with public prices · 2 free · 3 subscription-covered
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| Nvidia | First-party | Free | — | — | 262,144 | 262,144 | deprecated | |
| Alibaba Token Plan | Gateway | Subscription | $0 | $0 | 262,144 | 262,144 | ||
| Kenari kimi-k2-6 | Gateway | Free | — | — | 262,144 | 262,144 | ||
| SCNet Token Plan Kimi-K2.6 | Gateway | Subscription | $0 | — | 262,144 | 262,144 | ||
| Alibaba Token Plan (China) | Gateway | Subscription | $0 | $0 | 262,144 | 262,144 | ||
| DevPass (LLM Gateway) | Gateway | $0.22 | $1.14 | $0.048 | — | 262,144 | 262,144 | |
| routing.run | Gateway | $0.275 | $1.10 | — | — | 200,000 ⚠ | 32,000 | |
| Vultr moonshotai/Kimi-K2.6 | Cloud | $0.30 | $1.20 | — | — | 262,144 | 131,072 | |
| CrofAI | Gateway | $0.50 | $1.99 | $0.05 | — | 262,144 | 262,144 | |
| NanoGPT | Gateway | $0.50 | $2.60 | $0.125 | — | 256,000 ⚠ | 65,536 | |
| Moonshot AIOfficial | First-party | $0.95 | $4.00 | $0.16 | — | 262,144 | 262,144 | |
Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.
Your usage cost
1DevPass (LLM Gateway)$80.21
2routing.run$110.00
3Vultr$120.00
4CrofAI$145.50
5NanoGPT$185.00
6Neuralwatt$236.90
26Moonshot AI · Official$295.20
5 more channels offer $0 (Nvidia, Alibaba Token Plan, Kenari etc.); free tiers usually have rate limits and no SLA, excluded from ranking.
Switch to DevPass (LLM Gateway) to save $214.99/mo (73%)
Note: this is a gateway; verify availability and rate limits yourself.
Benchmark5 items
| Name | Conditions | Score | Metric | Source |
|---|---|---|---|---|
| SWE-Bench Verified | — | 80.2 | resolved | Source ↗ |
| Artificial Analysis Coding Agent Index | harness: Claude Code | 50.5 | average pass@1 | Source ↗ |
| SWE-Atlas Codebase QnA | harness: Claude Code | 59.8 | pass@1 | Source ↗ |
| SWE-Bench Pro | harness: Claude Code · dataset: hard-aa | 27.3 | pass@1 | Source ↗ |
| Terminal-Bench | harness: Claude Code · v2.1 | 64.3 | pass@1 | Source ↗ |
The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.
Reasoning control
effort = noneeffort = minimaleffort = loweffort = mediumeffort = higheffort = xhigheffort = maxToggle (on / off)budget_tokens
19 / 65 providers expose no reasoning control (reasoning_options: []).
Related models
Kimi K2.7 Code Fastsame series$1.90 / $8.00Kimi K2.7 Codesame series$0.95 / $4.00Kimi K2.7 Code Flexsame series$0.475 / $2.00DeepSeek V4 Procheaper alternative$0.435 / $0.87DeepSeek V4 Flashcheaper alternative$0.14 / $0.28MiniMax-M2.7cheaper alternative$0.30 / $1.20DeepSeek V4 Flash 0731cheaper alternative$0.479 / $1.44
Price historyone sample accumulated per data sync
Input listOutput listMin blended