Model comparison
Gemini 3.5 Flash-Lite vs Kimi K2.7 Code
Gemini
KimiCompare published specifications, vendor API list prices and measured Borg performance. Both models are included in Borg.
Gemini 3.5 Flash-Lite
Kimi K2.7 Code
Included in Borg
At a glance
| Specification | Gemini 3.5 Flash-Lite | Kimi K2.7 Code |
|---|---|---|
| Provider | Moonshot AI | |
| Release | 2026-07-21 Vendor source | — |
| Context | 1,048,576 tokens Vendor source | 262,144 tokens Vendor source |
| Modalities | Input: text, image, video, audio, pdf; output: text | Input: text, image, video; output: Not published |
| Reasoning / thinking modes | Yes / Not published | Yes / Not published |
| Open weights | No | Yes |
| Vendor API list price / 1M tokens | $0.3 input / $2.5 output | $0.95 input / $4 output |
| Borg | Included in Borg subscription | Included in Borg subscription |
Google
Moonshot AINot published by the vendor: release.
Measured on Borg
Metrics are not directly comparable to vendor benchmark claims. Models served different requests; this is observed gateway traffic, not a controlled head-to-head test.
Time to first token (gateway proxy)
Output tokens per second (whole turn)
| Metric | Gemini 3.5 Flash-Lite | Kimi K2.7 Code |
|---|---|---|
| Time to first token (gateway proxy) p50 | 1572 ms (33554 samples) | 4780 ms (119 samples) |
| Tokens per second (end to end) p50 | 59.2 output tokens per second (197556 samples) | 24.2 output tokens per second (1894 samples) |
| Request success rate | 100% (38840 samples) | Not published |
| Coding bench pass rate | Not published | Not published |
Measurement window, samples and methodology
The fleet reference is the median of published model medians, not a request-weighted result. Prompt lengths, reasoning settings and traffic differ between models.
Gemini 3.5 Flash-Lite: Measured on Borg: SearchAtlas AI Gateway production request logs. 30-day window ending 2026-10-08; 216821 requests. Minimum 100 samples per published request metric.
Kimi K2.7 Code: Measured on Borg: SearchAtlas AI Gateway production request logs. 30-day window ending 2026-10-08; 2583 requests. Minimum 100 samples per published request metric.
Completion speed covers the whole turn including queueing and reasoning time; it is not a streaming tokens-per-second figure.
- Time to first token (gateway proxy): time until the first streamed response event reaches the gateway; our closest available measure of time to first token
- Tokens per second (end to end): tokens per second, end to end: provider-reported output tokens divided by the whole turn's elapsed time, including queueing and reasoning; not a streaming per-token rate
How to choose
Gemini 3.5 Flash-Lite is listed for high-throughput document parsing, whereas Kimi K2.7 Code is listed for multi-file coding with iterative test runs. Choosing between Gemini 3.5 Flash-Lite and Kimi K2.7 Code requires checking published specifications against observed Borg traffic for your workflow.
Key differences
| Spec | Gemini 3.5 Flash-Lite | Kimi K2.7 Code |
|---|---|---|
| Context window | 1,048,576 tokens Vendor source Larger context | 262,144 tokens Vendor source |
| Reasoning modes | Yes / Not published | Yes / Not published |
| Release date | 2026-07-21 Vendor source | Not published |
| API price input / 1M | 0.3 Lower listed rate | 0.95 |
| API price output / 1M | 2.5 Lower listed rate | 4 |
| Time to first token (gateway proxy) | 1572 ms (33554 samples) Lower median | 4780 ms (119 samples) |
| Output tokens per second (whole turn) | 59.2 output tokens/s (whole turn) (197556 samples) Higher measured rate | 24.2 output tokens/s (whole turn) (1894 samples) |
| Request success | 100% (38840 samples) | Not published |
| Coding bench | Not published | Not published |
FAQ
How do Gemini 3.5 Flash-Lite and Kimi K2.7 Code compare for coding?
Gemini 3.5 Flash-Lite has a Borg coding benchmark of not published; Kimi K2.7 Code has not published. The Gemini 3.5 Flash-Lite–Kimi K2.7 Code coding comparison cannot establish an overall winner from this small test alone.
How quickly do Gemini 3.5 Flash-Lite and Kimi K2.7 Code start responding on Borg?
Borg median first response for Gemini 3.5 Flash-Lite is 1,572 ms; for Kimi K2.7 Code it is 4,780 ms. The Gemini 3.5 Flash-Lite–Kimi K2.7 Code gateway medians are observations, not guaranteed latency for individual requests.
What are the API prices for Gemini 3.5 Flash-Lite and Kimi K2.7 Code?
The listed API rate for Gemini 3.5 Flash-Lite is $0.3 input / $2.5 output per 1M tokens; for Kimi K2.7 Code it is $0.95 input / $4 output per 1M tokens. Neither Gemini 3.5 Flash-Lite nor Kimi K2.7 Code has its Borg subscription charge represented by those provider API rates. Gemini 3.5 Flash-Lite vendor source · Kimi K2.7 Code vendor source
Claude