A large model interface gateway providing proxy access to multiple AI models with free tiers and token incentives.
星见雅 API offers 314 LLM API models.
API pricing per token ranges from $0.100 to $7.50/M (input).
Speed benchmark average: 70 tok/s.
星见雅 API is an API aggregator, offering models from multiple vendors.
api.xinjianya.top| Model | Speed | Latency | Tests |
|---|---|---|---|
246.87 tok/s | 1.15s | 5 | |
227.95 tok/s | 1.47s | 5 | |
| Model | Input ($/M) | Output ($/M) |
|---|---|---|
李/google/gemma-3n-e4b-it | $0.0000 | $0.0000 |
| $0.0000 | $0.0000 | |
| $0.0000 | $0.0000 | |
| $0.0000 | $0.0000 | |
李/google/gemma-3n-e2b-it | $0.0000 |
| Time | Model | Speed | Latency |
|---|---|---|---|
| 04/13/2026, 10:19 | grok-4.20-0309 | 111.36 tok/s | 1.33s |
| 04/13/2026, 09:22 | GLM-5 | 23.06 tok/s | 39.70s |
| 04/12/2026, 15:40 |
223.30 tok/s |
3.41s |
| 5 |
221.17 tok/s | 0.55s | 5 |
213.18 tok/s | 0.52s | 10 |
200.27 tok/s | 0.42s | 15 |
183.01 tok/s | 8.28s | 5 |
149.05 tok/s | 5.26s | 10 |
144.01 tok/s | 0.94s | 5 |
142.72 tok/s | 1.29s | 10 |
| $0.0000 |
| $0.100 | $0.100 |
李/qwen/qwen3.5-397b-a17b | $0.100 | $0.100 |
| $0.100 | $0.100 |
| $0.100 | $0.100 |
| $0.100 | $0.100 |
159.61 tok/s |
1.24s |
| 04/12/2026, 10:51 | gpt-5.4 | 34.99 tok/s | 13.15s |
| 04/12/2026, 10:50 | deepseek-chat | 41.90 tok/s | 1.46s |