Model comparison
Gemini 3.8 Flash vs Kimi K2.7 Code
Gemini
KimiCompare published specifications, vendor API list prices and measured Borg performance. Both models are included in Borg.
Gemini 3.8 Flash
Kimi K2.7 Code
Included in Borg
At a glance
| Specification | Gemini 3.8 Flash | Kimi K2.7 Code |
|---|---|---|
| Provider | Moonshot AI | |
| Release | 2026-09-02 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 | $0.75 input / $3.75 output Introductory rates through December 31, 2026. From January 1, 2027: $1.50 input / $7.50 output / $0.15 cached input per 1M tokens. | $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 3.8 Flash | Kimi K2.7 Code |
|---|---|---|
| Time to first token (gateway proxy) p50 | 2510 ms (1147 samples) | 4780 ms (119 samples) |
| Tokens per second (end to end) p50 | 29.2 output tokens per second (85551 samples) | 24.2 output tokens per second (1894 samples) |
| Request success rate | Not published | 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 3.8 Flash: Measured on Borg: SearchAtlas AI Gateway production request logs. 30-day window ending 2026-10-08; 92815 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 3.8 Flash is listed for long-horizon coding agents, whereas Kimi K2.7 Code is listed for multi-file coding with iterative test runs. Choosing between Gemini 3.8 Flash and Kimi K2.7 Code requires checking published specifications against observed Borg traffic for your workflow.
Key differences
| Spec | Gemini 3.8 Flash | 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 | 2026-09-02 Vendor source | Not published |
| API price input / 1M | 0.75 Introductory rates through December 31, 2026. From January 1, 2027: $1.50 input / $7.50 output / $0.15 cached input per 1M tokens. Lower listed rate | 0.95 |
| API price output / 1M | 3.75 Introductory rates through December 31, 2026. From January 1, 2027: $1.50 input / $7.50 output / $0.15 cached input per 1M tokens. Lower listed rate | 4 |
| Time to first token (gateway proxy) | 2510 ms (1147 samples) Lower median | 4780 ms (119 samples) |
| Output tokens per second (whole turn) | 29.2 output tokens/s (whole turn) (85551 samples) Higher measured rate | 24.2 output tokens/s (whole turn) (1894 samples) |
| Request success | Not published | Not published |
| Coding bench | Not published | Not published |
FAQ
How do Gemini 3.8 Flash and Kimi K2.7 Code compare for coding?
Gemini 3.8 Flash has a Borg coding benchmark of not published; Kimi K2.7 Code has not published. The Gemini 3.8 Flash–Kimi K2.7 Code coding comparison cannot establish an overall winner from this small test alone.
How quickly do Gemini 3.8 Flash and Kimi K2.7 Code start responding on Borg?
Borg median first response for Gemini 3.8 Flash is 2,510 ms; for Kimi K2.7 Code it is 4,780 ms. The Gemini 3.8 Flash–Kimi K2.7 Code gateway medians are observations, not guaranteed latency for individual requests.
What are the API prices for Gemini 3.8 Flash and Kimi K2.7 Code?
The listed API rate for Gemini 3.8 Flash is $0.75 input / $3.75 output per 1M tokens; for Kimi K2.7 Code it is $0.95 input / $4 output per 1M tokens. Neither Gemini 3.8 Flash nor Kimi K2.7 Code has its Borg subscription charge represented by those provider API rates. Gemini 3.8 Flash vendor source · Kimi K2.7 Code vendor source
Claude