Kimi K2.5 vs Kimi K2 Instruct
Kimi K2.5 comes out ahead, 62 to 50 on our weighted score, though Kimi K2 Instruct is 16% cheaper per token.
- Our pick
Moonshot AIKimi K2.5
62/100- ECI148.1
- Price$0.60 / $3.00
- Context262K
- Moonshot AI
Kimi K2 Instruct
50/100- ECI139.9
- Price$0.57 / $2.30
- Context131K
Add a model
Make it a three-way comparison.
Kimi K2.5 is our pick
Kimi K2.5 is the better all-round choice, scoring 62/100 against Kimi K2 Instruct (50). It leads on capability, inputs & features and context window. Kimi K2 Instruct wins on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
- CapabilityKimi K2.5Capabilities Index (ECI): Kimi K2.5 148.1 · Kimi K2 Instruct 139.9
- Lowest priceKimi K2 InstructKimi K2 Instruct $1.00 · Kimi K2.5 $1.20 per 1M tokens (3:1 blend)
- Longest contextKimi K2.5Kimi K2.5 262,144 · Kimi K2 Instruct 131,072 tokens
- Widest inputsKimi K2.5Kimi K2.5: Text, Images, Video · Kimi K2 Instruct: Text
- Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
| Measure | Weight | Kimi K2.5 | Kimi K2 Instruct |
|---|---|---|---|
| CapabilityCapabilities Index (ECI) | 50% | 74 | 64 |
| Price | 25% | 44 | 48 |
| Inputs & features | 15% | 70 | 25 |
| Context window | 10% | 37 | 25 |
| Overall | 100% | 62/100 | 50/100 |
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | Kimi K2.5Moonshot AI | Kimi K2 InstructMoonshot AI |
|---|---|---|
| Capability | ||
| Capabilities Index (ECI) | 148.1 (best) | 139.9 |
| ECI rank | #68 of 165 (best) | #112 of 165 |
| GPQA DiamondGraduate-level science questions | 87.6% | — |
| OTIS Mock AIME 2024–2025Competition mathematics | 92.2% | — |
| SWE-bench VerifiedFixing real GitHub issues | 73.8% | — |
| SimpleQA VerifiedShort factual questions | 34.3% | — |
| Price per million tokens | ||
| Input | $0.60 | $0.57 (best) |
| Output | $3.00 | $2.30 (best) |
| Cached input | — | — |
| Blended (3:1) | $1.20 | $1.00 (best) |
| Long-context rate | Same rate | Same rate |
| Price source | Median of 33 providers | Median of 11 providers |
| Limits | ||
| Context window | 262,144 tokens (best) | 131,072 tokens |
| Max output | 262,144 tokens (best) | 32,768 tokens |
| Inputs and features | ||
| Text | Yes | Yes |
| Images | Yes | No |
| PDFs | No | No |
| Audio | No | No |
| Video | Yes | No |
| Reasoning | Yes | No |
| Tool calling | Yes | Yes |
| Structured output | No | No |
| Availability | ||
| Weights | Open | OpenModified MIT |
| API model ID | — | — |
| API providers | 33 (best) | 11 |
| Released | Jan 27, 2026 | Jul 11, 2025 |
| Knowledge cutoff | Jan 2025 | — |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- Kimi K2.5$12.00
- Kimi K2 Instruct$10.30
Which should you choose?
Which is better: Kimi K2.5 or Kimi K2 Instruct?
Kimi K2.5 is the better all-round choice, scoring 62/100 against Kimi K2 Instruct (50). It leads on capability, inputs & features and context window. Kimi K2 Instruct wins on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
Which is cheaper, Kimi K2.5 or Kimi K2 Instruct?
Kimi K2 Instruct is cheaper at $0.57 input / $2.30 output per million tokens (median across 11 API providers). Kimi K2.5 costs $0.60 input / $3.00 output per million tokens (median across 33 API providers). At a typical mix of three input tokens to one output token, that is $1.00 per million tokens for Kimi K2 Instruct versus $1.20 for Kimi K2.5 (1.2× as much).
Which scores higher on benchmarks?
Kimi K2.5 scores higher on the Capabilities Index (ECI): Kimi K2.5 148.1 (#68 of 165) and Kimi K2 Instruct 139.9 (#112 of 165). Their confidence ranges do not overlap (146.3–149.5 vs 136.3–141.6), so the gap is a real one.
Which is better for coding?
There are no published SWE-bench Verified results for Kimi K2 Instruct yet, so there is no like-for-like coding score. On overall capability, Kimi K2.5 leads, which tends to carry over to coding, but test on your own codebase. Both support tool calling for agent workflows.
Which has the bigger context window?
Kimi K2.5 has the largest context window at 262,144 tokens, against 131,072 for Kimi K2 Instruct. Maximum output per response: Kimi K2.5 up to 262,144, Kimi K2 Instruct up to 32,768 tokens.
Which can read images, PDFs, audio or video?
Kimi K2.5 accepts text, images and video; Kimi K2 Instruct accepts text. Kimi K2.5 handles the widest range of inputs.
Are any of these open source?
Yes, both publish their weights (Modified MIT), so you can self-host them.
Which is newer?
Kimi K2.5 is the newest, released Jan 27, 2026. Kimi K2 Instruct came out Jul 11, 2025. Knowledge cutoff: Kimi K2.5 Jan 2025.
How do you decide the winner?
Each model gets a 0–100 score on capability (50%, independent benchmark results); price (25%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (15%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (10%, maximum tokens per request, log scale). Dimensions missing for any model are dropped and the remaining weights rescaled, so every model is judged on the same evidence. Specs and prices come from public model listings and the labs’ own API pages; capability scores come from independent benchmark runs. Data updated Nov 2, 2026.
Related comparisons
- Add Qwen3.6 PlusThree-way comparison
- Kimi K2.5 vs Qwen3.6 PlusAlibaba (Qwen) · ECI 147.8
- Kimi K2.5 vs GPT-5.4 miniOpenAI · ECI 148.8
- Kimi K2.5 vs Grok 4.3xAI · ECI 149.0
- Kimi K2.5 vs GLM-5Z.ai (Zhipu) · ECI 145.8
- Kimi K2 Instruct vs Gemini 2.5 FlashGoogle · ECI 140.6
- Kimi K2 Instruct vs DeepSeek R1 0528DeepSeek · ECI 141.2
