目前暂不开放使用!
apis.soys.site
Xuanhuang provides an API relay for accessing AI models including GPT, Claude, and open-source LLMs.
Payment methods
Billing types
https://apis.soys.site/Verify ownership to unlock provider management features:
https://apis.soys.siteRankings are based on community-submitted tests and periodic health probes. Advisory only, not official data.
目前暂不开放使用!
Compare 37 model rows across audit recency, latest speed tests, throughput, latency, and per-token pricing.
| Model | Input ($/M) | Output ($/M) | Audit | Speed | Latency |
|---|---|---|---|---|---|
grokimage-质量kelivo生图 | $0.040/request | - | - | - | - |
grokimage-质量cherry stuido生图 | $0.040/request | - | - | - | - |
grok-4.5cherry stuido生图 | $2.00/M | $6.00/M | - | - | - |
grok-4.5kelivo生图 | $2.00/M | $6.00/M | - | - | - |
claude-opus-4-6 | - | - | - | - | - |
gemini-2.5-flash-lite | - | - | - | - | - |
gpt-5.4 | - | - | - | - | - |
agnes-2.0-flash | - | - | - | - | - |
claude-opus-4-7 | - | - | - | - | - |
claude-opus-4-8 | - | - | - | - | - |
deepseek-v4-flash | - | - | - | - | - |
deepseek-v4-pro | - | - | - | - | - |
gemma-4-31b-多模态模型 | - | - | 727284100 | 1197.5 t/s | 0.23 s |
glm-5.2 | - | - | 726863100 | - | - |
gpt-5.5 | - | - | - | - | - |
Showing 15 of 37 model rows
| Time | Model | Speed | Latency |
|---|---|---|---|
| Jul 4, 05:21 PM | gemma-4-31b-多模态模型 | 1197.53 tok/s | 0.23s |
| Mar 31, 06:19 PM | qwen-3-235b | 686.99 tok/s | 1.62s |
| Mar 31, 06:19 PM | gpt-oss-120b-medium | 244.47 tok/s | 1.16s |
| Mar 31, 06:16 PM | gpt-5.3-codex | 47.55 tok/s | 3.21s |
| Feb 16, 03:43 AM | 翻译/标题/OCR模型 | 260.68 tok/s | 0.91s |
| Feb 16, 03:41 AM | claude-opus-4-6-thinking | 43.24 tok/s | 1.65s |
| Feb 16, 03:39 AM | kimi-k2-instruct | 32.90 tok/s | 1.10s |
| Feb 16, 03:26 AM | gpt-oss-120b | 1796.31 tok/s | 0.49s |
| Feb 16, 03:22 AM | grok-4.1-fast | 72.98 tok/s | 4.71s |
| Feb 16, 03:17 AM | gemini-3-flash | 155.96 tok/s | 4.01s |
Compare 玄黄 alternatives against 6 nearby API providers using 331 LMSpeed signals across shared model coverage, pricing, benchmark speed, uptime, and free-model availability.
| Provider | Why compare | Models | Free | Avg price | Speed | 30d uptime |
|---|---|---|---|---|---|---|
| 玄黄 apis-soys-site Xuanhuang provides an API relay for accessing AI models including GPT, Claude, and open-source LLMs. | Current provider baseline | 48 | 0 | $1.06/M | 429 tok/s | 98.1% |
naapi-cc Na API (naapi.cc) is an OpenAI-compatible LLM API gateway with competitive pricing and stable access to 100+ models from OpenAI, Anthropic, Google, and more. |
| 96 | 0 | $0.630/M | ||
ai-071129-xyz MapleLeaf API runs a New API-powered gateway on ai.071129.xyz for aggregated access to multiple AI models. |
| 263 | 292 | N/A | 38 tok/s | 99.3% |
ai-chuyel-top A free, community-supported API service providing access to various AI models for developers and users. |
| 257 | 152 | $0.133/M | 171 tok/s | 77.5% |
vsllm-com VSLLM runs a New API-powered AI gateway on vsllm.com for aggregated model access through a single endpoint. |
| 124 | 2 | $255.70/M | 174 tok/s | 99.7% |
ipv4-beta-lm-studio ChooseC API is a unified AI model aggregation gateway supporting 260+ mainstream models including Claude, GPT, Qwen, DeepSeek, Kimi, and GLM with OpenAI, Claude, and Gemini compatibility. |
| 96 | 9 | $25.69/M | 138 tok/s | |
www-catclawai-top CatClaw API provides an AI model relay with access to GPT, Claude, and other large language models. |
| 48 | 2 | $0/M | 83 tok/s | 99.5% |
| 649 tok/s |
| 99.8% |
| 99.6% |