MODEL PROOF
Kimi K2.7 Code
NOT INDEPENDENTLY RATED
No independent LMArena score is published for this model.
Serving precision differs between offers.
- Independent LMArena score
- Not independently rated
- Context window
- 262.14K
- Maximum output
- 235.93K
- Input modalities
- text, image
- Output modalities
- text
- Published input price
- $0.671 / 1M tokens
- Published output price
- $3.35 / 1M tokens
- Pricing kind
- fixed
Inspect complete billing conditions and endpoint terms below.
Price from Inceptron: the cheapest offer that is serving, at standard delivery and at the maker’s precision or better, at its standard rate.
Cheaper right now: $1.28/M at StreamLake — promotion 25% · precision not disclosed It does not pass the like-for-like test, so it never sets a rank.
Every price dimension · USD per million tokens
| Input | $0.671/M |
|---|---|
| Output | $3.35/M |
| Cached input | $0.180/M |
| Cache write | Unknown/M |
| Cache write 1h | Unknown/M |
| Reasoning | Unknown/M |
Who sells it
The same weights, different shops. Cheapest is not like-for-like when serving precision differs.
Headline cheapest is a lower precision. Like-for-like at the best declared precision is $0.859/M from SiliconFlow.
12 provider offers · rates, limits and conditions
Rates are USD per million tokens. Endpoint terms can differ even when the quoted price and precision match. A listed parameter is a provider declaration, not a task-success test.
| Seller | Input | Output | Precision | Uptime (1d) |
|---|---|---|---|---|
| Inceptroninceptron/int4 Endpoint terms
| $0.671 | $3.35 | int4 | 99.90% |
| CoreWeavecoreweave/int4 Endpoint terms
| $0.710 | $3.50 | int4 | 99.99% |
| StreamLakestreamlake Endpoint terms
| $0.713 | $3.00 | undeclared | 99.89% |
| Venicevenice/int4 Endpoint terms
| $0.750 | $3.50 | int4 | 99.37% |
| SiliconFlowsiliconflow/fp8 Endpoint terms
| $0.859 | $3.80 | fp8 | 99.96% |
| Novitanovita/int4 Endpoint terms
| $0.912 | $3.84 | int4 | 99.87% |
| GMICloudgmicloud/fp8 Endpoint terms
| $0.950 | $4.00 | fp8 | 99.21% |
| Alibabaalibaba/fp8 Endpoint terms
| $0.950 | $4.00 | fp8 | 96.37% |
| Nebiusnebius/fp4 Endpoint terms
| $0.950 | $4.00 | fp4 | 99.03% |
| Moonshot AImoonshotai/int4 Endpoint terms
| $0.950 | $4.00 | int4 | 100.00% |
| Cloudflarecloudflare Endpoint terms
| $0.950 | $4.00 | undeclared | 99.59% |
| Moonshot AImoonshotai/highspeed Endpoint terms
| $1.90 | $8.00 | int4 | 99.93% |
Independent scores
No independent benchmark has measured this model. Unrated is not a score of zero.
Best rankings by task
- Htmlslides #7 1201
- Godot games #20 1147
- Agenticgamedev #21 1130
- Full-stack apps #22 1174
- Python pptxslides #22 1154
- ASCII art #24 1207
- Web apps #24 1169
- Native Android apps #25 1152
Per-task Elo and rank from Design Arena, via OpenRouter’s model feed. The rank is the feed’s, and it counts models OpenRouter does not list.
Capability
| Context window | 262K |
|---|---|
| Max output | 235K |
| Input modes | text, image |
| Tool use | yes |
| Reasoning | always on |
| Open weights | yes |
Provenance
| Price source | openrouter.ai |
|---|---|
| Fetched | 2026-10-06 |
| Quality data | unrated |
| Cross-checked | vendor page |
Our take
editorial — not a measurementEvaluate this coding-focused model on the same repository tasks as a hosted alternative. Compare current rates, generated output volume and completion quality. The accepted record lists open weights; private deployment still needs licence, serving and security review. Keep the recorded context and output ceilings separate.
Strengths
- The accepted source describes a coding-specialised open-weight model
- Text and image input are listed
Weaknesses
- A coding label does not replace benchmark evidence or repository evaluations
- Output limits can constrain a single-pass generation
Reach for it when
- Repository coding evaluations
- Private-deployment assessments within licence terms
Avoid it if
- You require a benchmark result not present in the current proof
- The required prompt or output exceeds the recorded limits
Sources: openrouter.ai
MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts. It uses a native multimodal mixture-of-experts...
Questions this page answers
What does Kimi K2.7 Code cost?
$0.671/M in, $3.35/M out in this catalogue, as of the fetch date on this page. That is the API row, not a subscription.
Does Kimi K2.7 Code have an independent quality score?
Kimi K2.7 Code has no independent quality score in this catalogue. Unrated is not a score of zero.
What beats Kimi K2.7 Code?
Kimi K2.7 Code has no independent quality score. Unrated is not a score of zero.
Does this page use Artificial Analysis scores for Kimi K2.7 Code?
No. Artificial Analysis figures are not published here. Quality on this page is LMArena Elo where a score exists; otherwise the row is unrated.
Does a missing score mean Kimi K2.7 Code scored zero?
Unrated is not a score of zero.
Is the cheapest Kimi K2.7 Code endpoint the same product?
Headline cheapest is a lower precision. Like-for-like at the best declared precision is $0.859/M from SiliconFlow.
MODEL MONUMENT
Save or share this proof
Badge
The verdict as one SVG, for a README or a docs page. It states this model's dominance status at the balanced workload on the LMArena lens, with the date it was computed, and it is rebuilt with the catalogue — so it changes when the verdict changes, including to one you would rather it did not.
[](https://undominated.ai/models/moonshotai__kimi-k2.7-code/)<a href="https://undominated.ai/models/moonshotai__kimi-k2.7-code/"><img src="https://undominated.ai/badge/moonshotai__kimi-k2.7-code.svg" alt="Kimi K2.7 Code — Undominated.ai dominance verdict" height="36"></a>Direct file: https://undominated.ai/badge/moonshotai__kimi-k2.7-code.svg — a static SVG, written by scripts/build-badges.mjs on every build, so the copy you embed is never
older than the last deploy.
