Model comparison
Claude Haiku 4.5 vs Claude Sonnet 5.5
ClaudeCompare published specifications, vendor API list prices and measured Borg performance. Both models are included in Borg.
Claude Haiku 4.5
Claude Sonnet 5.5
Included in Borg
At a glance
| Specification | Claude Haiku 4.5 | Claude Sonnet 5.5 |
|---|---|---|
| Provider | Anthropic | Anthropic |
| Release | 2025-10-15 Vendor source | 2026-09-28 Vendor source |
| Context | 200,000 tokens Vendor source | 1,000,000 tokens Vendor source |
| Modalities | Input: text, image; output: text | Input: text, image; output: text |
| Reasoning / thinking modes | Yes / Not published | Yes / Not published |
| Open weights | No | No |
| Vendor API list price / 1M tokens | $1 input / $5 output | $2 input / $10 output |
| Borg | Included in Borg subscription | Included in Borg subscription |
AnthropicMeasured 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 | Claude Sonnet 5.5 |
|---|---|---|
| Time to first token (gateway proxy) p50 | 889 ms (6197 samples) | 2640 ms (35971 samples) |
| Tokens per second (end to end) p50 | 64.9 output tokens per second (226302 samples) | 76.7 output tokens per second (86888 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.
Claude Sonnet 5.5: Measured on Borg: SearchAtlas AI Gateway production request logs. 30-day window ending 2026-10-08; 94296 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 Claude Sonnet 5.5 is listed for well-scoped bug fixes and code reviews. Choosing between Claude Haiku 4.5 and Claude Sonnet 5.5 requires checking published specifications against observed Borg traffic for your workflow.
Key differences
| Spec | Claude Haiku 4.5 | Claude Sonnet 5.5 |
|---|---|---|
| Context window | 200,000 tokens Vendor source | 1,000,000 tokens Vendor source Larger context |
| Reasoning modes | Yes / Not published | Yes / Not published |
| Release date | 2025-10-15 Vendor source | 2026-09-28 Vendor source |
| API price input / 1M | 1 Lower listed rate | 2 |
| API price output / 1M | 5 Lower listed rate | 10 |
| Time to first token (gateway proxy) | 889 ms (6197 samples) Lower median | 2640 ms (35971 samples) |
| Output tokens per second (whole turn) | 64.9 output tokens/s (whole turn) (226302 samples) | 76.7 output tokens/s (whole turn) (86888 samples) Higher measured rate |
| Request success | Not published | Not published |
| Coding bench | Not published | Not published |
FAQ
How do Claude Haiku 4.5 and Claude Sonnet 5.5 compare for coding?
Claude Haiku 4.5 has a Borg coding benchmark of not published; Claude Sonnet 5.5 has not published. The Claude Haiku 4.5–Claude Sonnet 5.5 coding comparison cannot establish an overall winner from this small test alone.
How quickly do Claude Haiku 4.5 and Claude Sonnet 5.5 start responding on Borg?
Borg median first response for Claude Haiku 4.5 is 889 ms; for Claude Sonnet 5.5 it is 2,640 ms. The Claude Haiku 4.5–Claude Sonnet 5.5 gateway medians are observations, not guaranteed latency for individual requests.
What are the API prices for Claude Haiku 4.5 and Claude Sonnet 5.5?
The listed API rate for Claude Haiku 4.5 is $1 input / $5 output per 1M tokens; for Claude Sonnet 5.5 it is $2 input / $10 output per 1M tokens. Neither Claude Haiku 4.5 nor Claude Sonnet 5.5 has its Borg subscription charge represented by those provider API rates. Claude Haiku 4.5 vendor source · Claude Sonnet 5.5 vendor source
Gemini