DNSHE provides an OpenAI-compatible API relay service for accessing AI language models.
Categories
DNSHE offers 4 LLM API models.
API pricing is $75.00/M per token (input).
Speed benchmark average: 90 tok/s.
imsnake.dart.us.ci| Model | Speed | Latency | Tests |
|---|---|---|---|
jimmy | 251.49 tok/s | 0.57s | 2 |
123.38 tok/s | 8.53s | 5 | |
51.44 tok/s | 5.46s | 5 | |
30.05 tok/s | 4.72s | 5 |
| Model | Input ($/M) | Output ($/M) |
|---|---|---|
qwen3-vl-plus-thinking | $0.0000 | $0.0000 |
qwen3.5-397b-a17b-thinking-search | $0.0000 | $0.0000 |
qwen3.5-122b-a10b-image | $0.0000 | $0.0000 |
qwen3-max-2026-01-23-video | $0.0000 | $0.0000 |
anthropic/claude-sonnet-4.6 | $0.0000 | $0.0000 |
gpt-5-codex | $0.0000 | $0.0000 |
qwen3-vl-plus-video | $0.0000 | $0.0000 |
qwen3-omni-flash-2025-12-01 | $0.0000 | $0.0000 |
gpt-5.1-codex-mini | $0.0000 | $0.0000 |
| $0.0000 | $0.0000 |
| Time | Model | Speed | Latency |
|---|---|---|---|
| 03/19/2026, 09:00 | jimmy | 320.70 tok/s | 0.68s |
| 03/19/2026, 08:58 | gpt-5.4-mini | 123.38 tok/s | 8.53s |
| 03/07/2026, 07:12 | gpt-5.4 | 51.44 tok/s | 5.46s |
| 03/07/2026, 07:11 | gpt-5.2-codex | 30.05 tok/s | 4.72s |
| 03/02/2026, 16:39 | jimmy | 182.28 tok/s | 0.47s |
毫秒API provides a stable, high-bandwidth API forwarding service for OpenAI-compatible models, including GPT, Claude, and Midjourney, with global server deployment and transparent pricing.
3 shared modelsAPI provider for AI services accessible via dedicated endpoints.
3 shared models
A cost-effective API gateway offering discounted access to various large language models.
3 shared models
Provides access to over 500 AI models via OpenAI protocol with pay-as-you-go pricing, fast response times, and transparent billing.
3 shared models
柏拉图AI (api.bltcy.cn) is a multi-dimensional API integration platform providing access to over 600 AI models, serving as an alternate endpoint.
3 shared models
An AI model aggregation API platform offering multi-model access with OpenAI-compatible interfaces at low cost.
3 shared models