Model comparison
Claude Haiku 4.5 vs Kimi K2.7 Code
Claude
KimiCompare published specifications, vendor API list prices and measured Borg performance. Both models are included in Borg.
Claude Haiku 4.5
Kimi K2.7 Code
Included in Borg
At a glance
| Specification | Claude Haiku 4.5 | Kimi K2.7 Code |
|---|---|---|
| Provider | Anthropic | Moonshot AI |
| Release | 2025-10-15 Vendor source | — |
| Context | 200,000 tokens Vendor source | 262,144 tokens Vendor source |
| Modalities | Input: text, image; 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 | $1 input / $5 output | $0.95 input / $4 output |
| Borg | Included in Borg subscription | Included in Borg subscription |
Anthropic
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 | Claude Haiku 4.5 | Kimi K2.7 Code |
|---|---|---|
| Time to first token (gateway proxy) p50 | 889 ms (6197 samples) | 4780 ms (119 samples) |
| Tokens per second (end to end) p50 | 64.9 output tokens per second (226302 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.
Claude Haiku 4.5: Measured on Borg: SearchAtlas AI Gateway production request logs. 30-day window ending 2026-10-08; 289125 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
Claude Haiku 4.5 is listed for high-volume classification and tagging, whereas Kimi K2.7 Code is listed for multi-file coding with iterative test runs. Choosing between Claude Haiku 4.5 and Kimi K2.7 Code requires checking published specifications against observed Borg traffic for your workflow.
Key differences
| Spec | Claude Haiku 4.5 | Kimi K2.7 Code |
|---|---|---|
| Context window | 200,000 tokens Vendor source | 262,144 tokens Vendor source Larger context |
| Reasoning modes | Yes / Not published | Yes / Not published |
| Release date | 2025-10-15 Vendor source | Not published |
| API price input / 1M | 1 | 0.95 Lower listed rate |
| API price output / 1M | 5 | 4 Lower listed rate |
| Time to first token (gateway proxy) | 889 ms (6197 samples) Lower median | 4780 ms (119 samples) |
| Output tokens per second (whole turn) | 64.9 output tokens/s (whole turn) (226302 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 Claude Haiku 4.5 and Kimi K2.7 Code compare for coding?
Claude Haiku 4.5 has a Borg coding benchmark of not published; Kimi K2.7 Code has not published. The Claude Haiku 4.5–Kimi K2.7 Code coding comparison cannot establish an overall winner from this small test alone.
How quickly do Claude Haiku 4.5 and Kimi K2.7 Code start responding on Borg?
Borg median first response for Claude Haiku 4.5 is 889 ms; for Kimi K2.7 Code it is 4,780 ms. The Claude Haiku 4.5–Kimi K2.7 Code gateway medians are observations, not guaranteed latency for individual requests.
What are the API prices for Claude Haiku 4.5 and Kimi K2.7 Code?
The listed API rate for Claude Haiku 4.5 is $1 input / $5 output per 1M tokens; for Kimi K2.7 Code it is $0.95 input / $4 output per 1M tokens. Neither Claude Haiku 4.5 nor Kimi K2.7 Code has its Borg subscription charge represented by those provider API rates. Claude Haiku 4.5 vendor source · Kimi K2.7 Code vendor source
Gemini