Data points: 82
The readout for Kimi K2.5 and Kimi K2 Thinking, before the detailed comparison sheet.
Decision read
Kimi K2.5
Kimi K2.5 currently has the stronger profile, with verified wins split 6 to 0.
Evidence depth
82 data points
Includes 8 benchmark rows, 0 audit samples, and 7 provider examples.
Selection signal
Start with Kimi K2.5
The charts below split 15 high-signal samples across speed, scores, and audit health.
Model compare Kimi K2.5 vs Kimi K2 Thinkingkimi-k2-5-vs-kimi-k2-thinking | Model A Kimi K2.5 | Model B Kimi K2 Thinking |
|---|---|---|
| Overall leader | Leading | Contender |
| Verified metric wins | 6 wins | 0 wins |
| Where it leads | Cheapest input price, Average speed, First-token latency, Free providers, Provider coverage, Recent tests |
Third-party benchmark profile synced into LMSpeed; only metrics available for both models are shown.
| Metric | Kimi K2.5 | Kimi K2 Thinking |
|---|---|---|
| HLE | 29.4%#14 |
Latest completed audits from shared providers, with four safety and integrity score groups plus report links.
| Provider | Kimi K2.5 | Kimi K2 Thinking |
|---|---|---|
| No completed audits are available from shared providers yet. | ||
Speed aggregates and input/output pricing share each provider row for real API selection and migration cost checks.
| Provider | Kimi K2.5 | Kimi K2 Thinking |
|---|---|---|
150 tests | Kimi K2.5 speed / latency 45 tok/s / 2058ms input / output No data |
This report only uses LMSpeed data for Kimi K2.5 and Kimi K2 Thinking: pricing, speed aggregates, third-party benchmark scores, and shared provider samples.
| Guidance | Kimi K2.5 | Kimi K2 Thinking |
|---|---|---|
| When to choose each model | Kimi K2.5 Kimi K2.5 is stronger when you prioritize Cheapest input price, Average speed, First-token latency, Free providers, Provider coverage, Recent tests. | Kimi K2 Thinking Kimi K2 Thinking does not clearly lead on the verified metrics here, so check provider-specific pricing before choosing. |
TL;DR: Kimi K2.5 leads across 82 verifiable data points, including pricing, speed, latency, benchmarks, and provider examples.
Continue from Kimi K2.5 vs Kimi K2 Thinking into nearby model comparisons with enough verified LMSpeed data.
| No data |
| Model metadata | Kimi K2.5 exposes 262.1K tokens; notable signals: Text input, Image input, Text output, Tool calling. | Kimi K2 Thinking exposes 262.1K tokens; notable signals: Text input, Text output, Tool calling, Structured outputs. |
|---|---|---|
| Developer | Moonshot AI | Moonshot AI |
| Context window | 262.1K tokens | 262.1K tokens |
| Max output | 262.1K tokens | 262.1K tokens |
| Released | Jan 2026 | Nov 2025 |
| Modalities | Input TextImage Output Text | Input Text Output Text |
| Features | Text inputImage inputText outputTool callingStructured outputsJSON modeReasoning | Text inputText outputTool callingStructured outputsJSON modeReasoning |
| Parameters | No data | No data |
| Tokenizer | Other | Other |
| Knowledge cutoff | No data | No data |
| OpenRouter ID | moonshotai/kimi-k2.5 | moonshotai/kimi-k2-thinking |
| References | No data | No data |
| SciCode | 49.0%#14 | 42.4%#35 |
|---|
| GPQA | 87.9%#16 | 83.8%#39 |
|---|
| Input price | $0.580/M#21 | $0.600/M#23 |
|---|
| Output price | $3.00/M#28 | $2.50/M#27 |
|---|
| Time to first token | 1.27 s#49 | 0.93 s#33 |
|---|
| Output speed | 47.1 tok/s#93 | 128.6 tok/s#38 |
|---|
| Blended price | $1.19/M#43 | $1.07/M#40 |
|---|
Kimi K2 Thinking
speed / latency
34 tok/s / 16242ms
input / output
No data
NVIDIA NIM85 tests | Kimi K2.5 speed / latency 48 tok/s / 18528ms input / output No data | Kimi K2 Thinking speed / latency 41 tok/s / 19451ms input / output No data |
|---|
火山引擎 Ark30 tests | Kimi K2.5 speed / latency 18 tok/s / 25450ms input / output No data | Kimi K2 Thinking speed / latency N/A / N/A input / output No data |
|---|
星见雅 API25 tests | Kimi K2.5 speed / latency 38 tok/s / 22910ms input / output No data | Kimi K2 Thinking speed / latency N/A / N/A input / output No data |
|---|
SiliconFlow10 tests | Kimi K2.5 speed / latency 45 tok/s / 14302ms input / output No data | Kimi K2 Thinking speed / latency N/A / N/A input / output No data |
|---|
Kimi K2.5 官网反代/kimi-k2.5 speed / latency No data input / output $75.00/M / $75.00/M | Kimi K2 Thinking moonshotai/kimi-k2-thinking speed / latency No data input / output $0/M / $0/M |
Kimi K2.5 moonshotai/kimi-k2.5 speed / latency No data input / output $0/M / $0/M | Kimi K2 Thinking moonshotai/kimi-k2-thinking speed / latency No data input / output $0/M / $0/M |
Rankings are based on community-submitted tests and periodic health probes. Advisory only, not official data.
