Kimi K2.8 Preview vs Kimi K2.7 Code vs North Small Translate
Kimi K2.8 Preview comes out ahead, 66 to 63 and 0 on our weighted score.
- Our pick
Moonshot AIKimi K2.8 Preview
66/100- ECI—
- Price—
- Context1.05M
- Moonshot AI
Kimi K2.7 Code
63/100- ECI150.0
- Price$0.95 / $4.00
- Context262K
CohereNorth Small Translate
0/100- ECI—
- PriceFree / Free
- Context16K
Kimi K2.8 Preview is our pick
Kimi K2.8 Preview is the better all-round choice, scoring 66/100 against Kimi K2.7 Code (63) and North Small Translate (0). It leads on context window. Kimi K2.7 Code wins on inputs & features. The score weighs inputs & features 60%, context window 40%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
- CapabilityNot enough dataNo independent benchmark covers every model here yet
- Lowest priceNorth Small TranslateNorth Small Translate Free · Kimi K2.7 Code $1.71 per 1M tokens (3:1 blend) · Kimi K2.8 Preview unpriced
- Longest contextKimi K2.8 PreviewKimi K2.8 Preview 1,048,576 · Kimi K2.7 Code 262,144 · North Small Translate 16,000 tokens
- Widest inputsKimi K2.8 Preview and Kimi K2.7 CodeKimi K2.8 Preview: Text, Images, Video · Kimi K2.7 Code: Text, Images, Video · North Small Translate: Text
- Self-hostingKimi K2.7 Code and North Small TranslatePublishes downloadable weights (CC-BY-NC-4.0)
| Measure | Weight | Kimi K2.8 Preview | Kimi K2.7 Code | North Small Translate |
|---|---|---|---|---|
| Inputs & features | 60% | 70 | 80 | 0 |
| Context window | 40% | 61 | 37 | 0 |
| Overall | 100% | 66/100 | 63/100 | 0/100 |
Left out because at least one model lacks the data: capability and price. The remaining weights were rescaled.
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | Kimi K2.8 PreviewMoonshot AI | Kimi K2.7 CodeMoonshot AI | North Small TranslateCohere |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | 150.0 | — |
| ECI rank | — | #49 of 148 | — |
| GPQA DiamondGraduate-level science questions | — | 87.9% | — |
| FrontierMath Tiers 1–3Research-level mathematics | — | 54.0% | — |
| OTIS Mock AIME 2024–2025Competition mathematics | — | 95.6% | — |
| SimpleQA VerifiedShort factual questions | — | 36.5% | — |
| Price per million tokens | |||
| Input | — | $0.95 | Free (best) |
| Output | — | $4.00 | Free (best) |
| Cached input | — | $0.19 | — |
| Blended (3:1) | — | $1.71 | Free (best) |
| Long-context rate | — | Same rate | Same rate |
| Price source | — | Official Moonshot AI API | Official Cohere API |
| Limits | |||
| Context window | 1,048,576 tokens (best) | 262,144 tokens | 16,000 tokens |
| Max output | — | 262,144 tokens (best) | 16,000 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | Yes | No |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | Yes | Yes | No |
| Reasoning | Yes | Yes | No |
| Tool calling | Yes | Yes | No |
| Structured output | No | Yes | No |
| Availability | |||
| Weights | Proprietary | Open | OpenCC-BY-NC-4.0 |
| API model ID | — | kimi-k2.7-code | north-small-translate-09-2026 |
| API providers | — | 51 (best) | 1 |
| Released | Sep 11, 2026 | Jun 12, 2026 | Sep 9, 2026 |
| 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 K2.8 Preview—
- Kimi K2.7 Code$17.50
- North Small TranslateFree
Which should you choose?
Which is better: Kimi K2.8 Preview, Kimi K2.7 Code or North Small Translate?
Kimi K2.8 Preview is the better all-round choice, scoring 66/100 against Kimi K2.7 Code (63) and North Small Translate (0). It leads on context window. Kimi K2.7 Code wins on inputs & features. The score weighs inputs & features 60%, context window 40%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
Which is cheaper, Kimi K2.8 Preview, Kimi K2.7 Code or North Small Translate?
North Small Translate is cheaper at Free input / Free output per million tokens (official Cohere API price). Kimi K2.7 Code costs $0.95 input / $4.00 output per million tokens (official Moonshot AI API price). North Small Translate is listed as free. Kimi K2.8 Preview has no published per-token price.
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Kimi K2.8 Preview has not been scored yet, Kimi K2.7 Code has an ECI of 150.0 and North Small Translate has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Kimi K2.8 Preview, Kimi K2.7 Code and North Small Translate yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that North Small Translate does not support tool calling, which most coding agents need.
Which has the bigger context window?
Kimi K2.8 Preview has the largest context window at 1,048,576 tokens, against 262,144 for Kimi K2.7 Code and 16,000 for North Small Translate. Maximum output per response: Kimi K2.7 Code up to 262,144, North Small Translate up to 16,000 tokens.
Which can read images, PDFs, audio or video?
Kimi K2.8 Preview accepts text, images and video; Kimi K2.7 Code accepts text, images and video; North Small Translate accepts text. Kimi K2.8 Preview handles the widest range of inputs.
Are any of these open source?
Kimi K2.7 Code and North Small Translate publishes its weights (CC-BY-NC-4.0) and can be self-hosted; Kimi K2.8 Preview is proprietary.
Which is newer?
Kimi K2.8 Preview is the newest, released Sep 11, 2026. North Small Translate came out Sep 9, 2026; Kimi K2.7 Code came out Jun 12, 2026. Knowledge cutoff: Kimi K2.7 Code 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 Oct 4, 2026.
