A free AI tool platform providing API access to multiple AI models for personal learning and research use.
Zero API offers 138 LLM API models.
API pricing per token ranges from $0.0007 to $5.14/M (input).
Speed benchmark average: 59 tok/s.
https://0api.qzz.io| Model | Speed | Latency | Tests |
|---|---|---|---|
59.01 tok/s | 2.72s | 5 |
| Model | Audit | Input ($/M) | Output ($/M) |
|---|---|---|---|
| — | Free | Free | |
longcat-flash-lite | — | Free | Free |
hunyuan-mt-7b | — | $0.0007 | $0.0007 |
grok-imagine-image-lite | — | $0.0014 | $0.0014 |
| — | $0.0034 | $0.014 | |
| — | $0.0034 | $0.027 | |
| — | $0.0062 | $0.036 | |
| — | $0.0066 | $0.020 | |
qwen3-30b-a3b-thinking-2507 | — | $0.0068 | $0.0068 |
| — | $0.0068 | $0.027 |
| Time | Model | Speed | Latency |
|---|---|---|---|
| May 18, 09:25 AM | claude-opus-4-7 | 59.01 tok/s | 2.72s |
api2.aigcbest.top
Provides AI-generated content APIs for various applications, including text and image generation.
napi.seaya.link
Seamee API provides an AI model relay for accessing multiple LLMs through OpenAI-compatible endpoints.
kfcv50.link
KFCV50 provides an OpenAI-compatible API relay for accessing AI models.
api.linkapi.org
Xiaodoubao 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.
api.holdai.top
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.
api.newagiai.com
Provides API access to a wide range of AI models including text, image, and video generation from multiple providers.
Limited-time launch of test group, stability not guaranteed, RPM:20
Recharge service has been fixed. If you cannot access it, please try refreshing the interface.
codex group limited-time 0.01 multiplier (ended)
gpt-5.3-codex and glm-5 are both online.
Note the usage issues with different group request endpoints! Generally, using /v1/chat/completions won't cause problems, but for the codex group, it's recommended to use /v1/responses, otherwise errors may occur; for the CC group, use /v1/message. Apart from these three endpoints, other endpoints are not recommended.
New Year's benefit: ① All models at 0.1 multiplier ② Recharge gets an extra 50% credit, e.g., recharge 100, get 100 + 100×50% = 150 credit (Recharge bonus credit will be given uniformly after the activity ends!!) Activity time: 2026.01.01 00:00~2026.01.01 23:59
Limited-time free CC, may expire at any time, remember to select the limited-time CC group, RPM tentatively set at 15, only tonight — ended
Rankings are based on community-submitted tests and periodic health probes. Advisory only, not official data.
