Provides API access to a wide range of AI models including text, image, and video generation from multiple providers.
Categories
Newagiai offers 5 LLM API models.
API pricing per token ranges from $0.0001 to $350.00/M (input).
Speed benchmark average: 48 tok/s.
Newagiai is an API aggregator, offering models from multiple vendors.
api.newagiai.com| Model | Speed | Latency | Tests |
|---|---|---|---|
86.04 tok/s | 1.27s | 5 | |
54.37 tok/s | 6.92s | 5 | |
49.76 tok/s | 1.90s | 5 | |
31.96 tok/s | 4.10s | 5 | |
20.36 tok/s | 1.64s | 5 |
| Model | Input ($/M) | Output ($/M) |
|---|---|---|
| $0.0000 | $0.0000 | |
| $0.0000 | $0.0000 | |
| $0.0000 | $0.0000 | |
| $0.0000 | $0.0000 | |
| $0.0000 | $0.0000 | |
| $0.0000 | $0.0000 | |
| $0.0001 | $0.0001 | |
| $0.0001 | $0.0001 | |
| $0.0001 | $0.0001 | |
| $0.0001 | $0.0001 |
| Time | Model | Speed | Latency |
|---|---|---|---|
| 03/27/2025, 09:45 | grok-3 | 49.76 tok/s | 1.90s |
| 03/27/2025, 09:38 | deepseek-v3-0324 | 20.36 tok/s | 1.64s |
| 03/27/2025, 09:38 | gpt-4o-mini | 86.04 tok/s | 1.27s |
| 03/27/2025, 09:35 | o3-mini | 31.96 tok/s | 4.10s |
| 03/27/2025, 09:33 | claude-3-7-sonnet-20250219 | 54.37 tok/s | 6.92s |
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.
719 shared modelsXiaodoubao API is a Chinese AI API relay platform hosted at api.linkapi.org, advertising low-cost and high-concurrency access to OpenAI, Claude, Gemini, Grok, Flux, and agent workflows.
719 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.
719 shared modelsProvides AI-generated content APIs for various applications, including text and image generation.
359 shared models
Provides access to over 500 AI models via OpenAI protocol with pay-as-you-go pricing, fast response times, and transparent billing.
251 shared modelsAPI provider for AI services accessible via dedicated endpoints.
249 shared models