Qwen3 Embedding 0.6B vs Kimi K2.5
Qwen3 Embedding 0.6B is cheaper on output tokens, while Kimi K2.5 offers a larger context window. Choose Qwen3 Embedding 0.6B or Kimi K2.5 based on the trade-off between cost, context, and the benchmarks that matter for your use case.
| Spec | Qwen3 Embedding 0.6B | Kimi K2.5 |
|---|---|---|
| Provider | Cloudflare AI Gateway | Cloudflare AI Gateway |
| Input / 1M tokens | $0.01 | $0.60 |
| Output / 1M tokens | $0.00 | $3.00 |
| Context window | 128K | 256K |
| Parameters | — | 1T |
| Open weights | No | Yes |
| Released | Nov 2025 | Jan 2026 |
FAQ
Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.