Side by side
See the difference.
Scores, capabilities and costs for the models you’re considering.
Scroll to compare models →
| 3 models | tencentTencent: Hy-MT2-1.8BRemove × | respanRespan: Span-02Remove × | xingchen-agiXingChen: Xing4.0 29B A4B (free)Remove × |
|---|---|---|---|
| What’s different | Hy-MT2-1.8B is a compact 1.8B-parameter translation model from Tencent. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based,… | Set a thinking deadline in milliseconds; returns typed decisions or direct numbers with confidence, and accepts up to four images. | Apache-2.0 weights with switchable thinking; supports domain fine-tuning and vLLM, SGLang or KTransformers deployment. |
| Date | Aug 20, 2026Listed | Oct 16, 2026Listed | Oct 16, 2026Listed |
API prices USD · provider configuration shown below | |||
| Listed rate | $0.044 in / $0.177 out/ 1M tokensTencent · via OpenRouter · all routes ↗tencent/fp8 · quantization=fp8 | $0.01 in / $0.00 out/ 1M tokensOpenRouter · all routes ↗ | $0.00 in / $0.00 out/ 1M tokensPhala · via OpenRouter · all routes ↗phala |
| Provider endpoints | 2 endpoints → | 1 endpoint → | 2 endpoints → |
Specifications | |||
| Context window | 8.2K | 131.1K | 262.1K |
| Max output | 4.1K | 118K | 235.9K |
| Parameters | 1.8B | — | 29B |
| Tool calling | Not reported | Not reported | Supported |
| Structured output | Not reported | Not reported | Supported |
| Image input | Not reported | Supported | Not reported |
| Reasoning | Not reported | Not reported | Supported |
| Open weights | Supported | Not reported | Supported |