VSLLM runs a New API-powered AI gateway on vsllm.com for aggregated model access through a single endpoint.
https://vsllm.comVerify ownership to unlock provider management features:
https://api.vsllm.comhttps://for.shuo.barRankings are based on community-submitted tests and periodic health probes. Advisory only, not official data.
VSLLM currently presents a New API-based gateway on vsllm.com. A live review on 2026-04-27 showed the default New API title and the standard /logo.png icon path, so LMSpeed keeps the provider copy conservative: VSLLM appears to operate a unified AI gateway for routing requests to multiple model families through one endpoint and management panel rather than the broader marketplace positioning previously listed.
Compare 32 model rows across audit recency, latest speed tests, throughput, latency, and per-token pricing.
| Model | Input ($/M) | Output ($/M) | Audit | Speed | Latency |
|---|---|---|---|---|---|
gpt-5.6-lunadefault | $0.029/request | - | — | — | — |
gpt-5.6-terradefault | $0.036/request | - | — | — | — |
gpt-5.6-soldefault | $0.146/request | - | — | — | — |
| $1.90/request | - | — | — | — | |
gemini-3-pro-image-previewdefault | $3.21/request | - | — | — | — |
glm-5.2default | $0.073/request | - | — | — | — |
kimi-k2.7-codedefault | $0.073/request | - | — | — | — |
claude-fable-5default | $438.00/M | $2190.00/M | — | — | — |
qwen3.7-plusdefault | $0.015/request | - | — | — | — |
claude-opus-4-8 | - | - | — | 28.2 t/s | 26.33 s |
claude-opus-4-8-free | - | - | — | 44.9 t/s | 4.15 s |
qwen3.7-maxdefault | $1095.00/M | $1095.00/M | 807284100 | — | — |
gemini-3.5-flash-antigravity | - | - | — | 320.4 t/s | 7.77 s |
gpt-5.5-pro20x | - | - | — | 50.3 t/s | 1.52 s |
gemini-3-flash-preview-request-antigravity | - | - | — | 240.0 t/s | 12.83 s |
| - | - | — | 32.3 t/s | 4.93 s | |
claude-opus-4-7-request | - | - | — | 38.2 t/s | 1.84 s |
gpt-5.5-free | - | - | — | 60.3 t/s | 5.28 s |
| - | - | — | 256.5 t/s | 4.45 s | |
| - | - | — | 99.3 t/s | 9.74 s | |
glm-5.1-code-plan | - | - | — | 39.0 t/s | 22.39 s |
gpt-5.4[codex] | - | - | — | 48.9 t/s | 1.91 s |
self-deepseek-v3.2 | - | - | — | 82.7 t/s | 8.39 s |
self-kimi-k2.5 | - | - | — | 35.0 t/s | 19.58 s |
glm-5-code-plan | - | - | — | 35.2 t/s | 26.30 s |
| - | - | — | 59.9 t/s | 2.48 s | |
| - | - | — | 98.7 t/s | 8.55 s | |
| - | - | — | 242.3 t/s | 2.95 s | |
| - | - | — | 40.6 t/s | 21.30 s | |
| - | - | — | 166.3 t/s | 4.34 s | |
| - | - | — | 22.5 t/s | 17.09 s | |
| - | - | — | 1319.0 t/s | 0.61 s |
Showing 32 of 32 model rows
| Time | Model | Speed | Latency |
|---|---|---|---|
| Jun 10, 01:26 AM | claude-opus-4-7 | 32.27 tok/s | 4.93s |
| May 30, 05:43 AM | claude-opus-4-8 | 28.20 tok/s | 26.33s |
| May 30, 05:42 AM | claude-opus-4-8-free | 44.93 tok/s | 4.15s |
| May 21, 01:44 AM | gpt-5.5-pro20x | 50.29 tok/s | 1.52s |
| May 21, 01:42 AM | claude-opus-4-7-request | 38.20 tok/s | 1.84s |
| May 21, 01:40 AM | gemini-3.5-flash-antigravity | 320.41 tok/s | 7.77s |
| May 19, 08:11 AM | gemini-3-flash-preview-request-antigravity | 193.61 tok/s | 12.37s |
| May 19, 08:10 AM | gemini-3-flash-preview-request-antigravity | 286.43 tok/s | 13.28s |
| May 13, 07:04 AM | gpt-5.5-free | 60.25 tok/s | 5.28s |
| Apr 20, 04:18 PM | kimi-k2.6 | 99.35 tok/s | 9.74s |
Compare VSLLM alternatives against 6 nearby API providers using 417 LMSpeed signals across shared model coverage, pricing, benchmark speed, uptime, and free-model availability.
| Provider | Why compare | Models | Free | Avg price | Speed | 30d uptime |
|---|---|---|---|---|---|---|
| VSLLM vsllm-com VSLLM runs a New API-powered AI gateway on vsllm.com for aggregated model access through a single endpoint. | Current provider baseline | 120 | 8 | $172.10/M | 184 tok/s | 99.7% |
ai-dext-top Dext API is an OpenAI-compatible API relay offering access to 500+ LLM models at competitive prices, with multi-channel routing and broad model coverage. |
| 343 | 228 | $111.69/M | 19 tok/s | 99.8% |
91vip-futureppo-top 91VIP is a non-profit API service providing access to various AI models including Codex, Claude Code, and Open Code, with specific unlimited-use groups. |
| 234 | 10 | $9.30/M | ||
llm-whitedream-top RenRen API runs a New API-powered gateway on llm.whitedream.top for aggregated access to multiple AI models. |
| 269 | 0 | $14.94/M | 271 tok/s | 99.5% |
ai-chuyel-top A free, community-supported API service providing access to various AI models for developers and users. |
| 237 | 187 | $0.646/M | 171 tok/s | 85.1% |
ai-cuz-lab-space Cuz AI runs an OpenAI-compatible relay at ai.cuz-lab.space with broad model coverage, public pricing, and stable throughput for chat and coding workloads. |
| 143 | 0 | $62.07/M | 280 tok/s | 47% |
api-6345ywz-cn 6345ywz API is an OpenAI-compatible API relay providing access to multiple AI models with competitive pricing. |
| 105 | 0 | $0.335/M | 241 tok/s | 99.8% |
| 301 tok/s |
| 0.7% |
