Side-by-side comparison
Claude 3.5 Haiku vs Kimi K2.6
Anthropic
Claude 3.5 Haiku
👁 Vision
🔧 Tools
Input / 1M
$0.8000
Output / 1M
$4.0000
MoonshotAI
Kimi K2.6
👁 Vision
🔧 Tools
{} JSON
Input / 1M
$0.7300
Output / 1M
$3.4900
| Claude 3.5 Haiku | Kimi K2.6 | |
|---|---|---|
| Provider | Anthropic | MoonshotAI |
| Context window Maximum tokens (input + output) the model can process in a single request. Glossary → | 200,000 | 262,142 |
| Capabilities Optional capabilities the model advertises: vision (images), tools (function calling), json_mode (structured output). | vision, tools | vision, tools, json_mode |
| Input $ / 1M tokens Cost for tokens you send (prompt + context). Cheaper side highlighted. Glossary → | 0.8000 | 0.7300 |
| Output $ / 1M tokens Cost for tokens the model generates. Output is normally 3–5× pricier than input. Glossary → | 4.0000 | 3.4900 |
Frequently asked questions
Which is cheaper, Claude 3.5 Haiku or Kimi K2.6?
Kimi K2.6 is cheaper than Claude 3.5 Haiku on a 50/50 input/output blend by about $0.29 per 1M tokens. Exact savings depend on your input-vs-output ratio — use the cost calculator on this page for a workload-specific estimate.
Which has a larger context window, Claude 3.5 Haiku or Kimi K2.6?
Kimi K2.6 has the larger context window at 262k tokens versus 200k tokens for Claude 3.5 Haiku. That means Kimi K2.6 can ingest about 1.3x as much text per request.
What is the difference between Claude 3.5 Haiku and Kimi K2.6?
Claude 3.5 Haiku comes from Anthropic; Kimi K2.6 comes from MoonshotAI. They differ in pricing, context window, and supported capabilities — see the side-by-side table on this page for the exact figures, refreshed nightly.