← Model list
Kimi K2.5
moonshotai·moonshotai/kimi-k2.5·Deprecated·Open weights·kimi-k2 series
Earlier Kimi frontier model for long-context agents, coding, and multimodal work
At a glance
Official price$0.60 / $3.00 per 1M
Cache read $0.10 · Moonshot AI
Lowest paid$0.35 / $1.70
CrofAI Gateway · 2.1× spread
6 more $0 channels
Context262,144
⚠ Providers report 128,000–262,144; the table below is authoritative
Output limit262,144
Capabilities
✓ Reasoning✓ Tool use✓ Structured outputTemperature✓ Attachments
⚠ Providers report capability flags inconsistently
Modalities
TextImageVideo
Knowledge cutoff2025-01
Released / updated2026-01 / 2026-01
Quality & performanceArtificial Analysis · Intelligence Index v4.1 · rep. tier Reasoning
Intelligence36
Value52
Coding46.8
Agentic21.7
Output speed43 tok/s
TTFT2.84 s
Cost per task$0.0964
Value formulaIQ 36 ÷ min blended $0.688 = 52
Reasoning tier → intelligence / speed (higher tier = stronger but slower)
Non-reasoningIQ 30.1 · 45 tok/s
ReasoningIQ 36 · 43 tok/s
Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.
Available at 50 providers43 with public prices · 6 subscription-covered
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| Alibaba Token Plan | Gateway | Subscription | $0 | $0 | 262,144 | 98,304 | ||
| Alibaba Coding Plan (China) | Gateway | Subscription | $0 | $0 | 262,144 | 32,768 | ||
| Alibaba Coding Plan | Gateway | Subscription | $0 | $0 | 262,144 | 32,768 | ||
| Tencent Coding Plan (China) | Gateway | Subscription | $0 | $0 | 262,144 | 32,768 | ||
| SCNet Token Plan Kimi-K2.5 | Gateway | Subscription | $0 | — | 262,144 | 262,144 | ||
| Alibaba Token Plan (China) | Gateway | Subscription | $0 | $0 | 262,144 | 98,304 | ||
| CrofAI | Gateway | $0.35 | $1.70 | $0.07 | — | 262,144 | 262,144 | |
| NanoGPT | Gateway | $0.30 | $1.90 | $0.15 | — | 256,000 ⚠ | 65,536 | |
| DevPass (LLM Gateway) | Gateway | $0.405 | $1.98 | $0.225 | — | 262,144 | 262,144 | |
| Deep Infra moonshotai/Kimi-K2.5 | Cloud | $0.45 | $2.25 | $0.07 | — | 262,144 | 32,768 | |
| Moonshot AIOfficial | First-party | $0.60 | $3.00 | $0.10 | — | 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
1CrofAI$121.40
2NanoGPT$137.00
3Deep Infra$156.90
4OpenRouter$156.90
5Eden AI$156.90
6DevPass (LLM Gateway)$158.40
19Moonshot AI · Official$210.00
6 more channels offer $0 (Alibaba Token Plan, Alibaba Coding Plan (China), Alibaba Coding Plan etc.); free tiers usually have rate limits and no SLA, excluded from ranking.
Switch to CrofAI to save $88.60/mo (42%)
Note: this is a gateway; verify availability and rate limits yourself.
Benchmark4 items
| Name | Conditions | Score | Metric | Source |
|---|---|---|---|---|
| SWE-Bench Verified | — | 70.8 | resolved | Source ↗ |
| SWE-Atlas Codebase QnA | harness: Mini-SWE-Agent | 13.1 | score | Source ↗ |
| SWE-Atlas Refactoring | harness: Mini-SWE-Agent | 20.95 | score | Source ↗ |
| SWE-Atlas Test Writing | harness: Mini-SWE-Agent | 25.77 | score | Source ↗ |
The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.
Reasoning control
Toggle (on / off)budget_tokens ≥ 1 ≤ 262,144effort = noneeffort = loweffort = mediumeffort = higheffort = minimaleffort = xhigheffort = max
15 / 50 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