[KongchangAI]
Company

Agnes AI

Agnes AI is an AI platform with self-developed text, image and video generation models. It offers a fully free API covering multimodal generation capabilities.

Core Facts

Timeline (last 90 days)

Oct 22

For production dependencies, it is recommended to also keep the official Claude Code subscription or another paid solution as a backup, to avoid free service fluctuations affecting work.

Unverified50%
Oct 22

The configuration process includes four steps: create a key on the Agnes API platform, add a Cloud Provider vendor in CC Switch and fill in the API Key and request address, obtain the model list and map it to Agnes 2.0 Flash, and enable the local routing and Claude routing switches.

Unverified50%
Oct 22

In the 35mm film-style portrait image generation tested by the uploader, flash highlights, skin texture, and pores were all reproduced; image-to-image can change outfits without changing the face, suitable for use on resumes or LinkedIn profiles.

Unverified50%
Oct 22

In the video generation test, the facial expression progression in a short video of a female singer singing was coherent, but a nighttime street video had a failure case where a passerby was "cloned" into two people.

Unverified50%
Oct 22

According to platform data cited by the uploader, in Agnes's first week of free access, text model calls exceeded 10,000, image generation exceeded 2 million images, and video generation exceeded 2 million seconds.

Unverified50%
Oct 22

Agnes AI's claim of "self-developed" currently lacks third-party verification; the original video only cited the platform's own data.

Unverified50%
Oct 21

When configuring a provider in CC Switch, select Cloud Provider as the type, then choose "Custom Provider", fill in the API Key, request URL, and API format, and click "Fetch Model List" to verify the connection.

Unverified50%
Oct 21

CC Switch requires enabling local routing and turning on the Claude routing switch; after enabling Agnes in the provider list, Claude Code's requests will be forwarded through CC Switch to the Agnes free gateway.

Unverified50%
Oct 21

Claude Code can only connect to text models and cannot directly call Agnes's image-generation models; image-generation capability must be invoked by creating a Skill.

Unverified50%
Oct 16

The default models of multiple Providers have changed: Cortecs, CrossModel, Eden AI, Google Gemini, GitHub Copilot, Google Vertex AI, LLM Gateway, Ofox, OpenCode Go, and Prime Inference now default to Gemini 4 Argon; Fireworks AI, Nebius Token Factory, and Requesty switch to Muse Spark Open; CoreWeave, DigitalOcean, NanoGPT, and Nvidia adopt Nemotron 3.5 Super VL; Aixy and Neon use Claude Haiku 5.5; Agnes AI, Ambient, IteraCompute, Poe, Scaleway, and SenseNova also have their own adjustments.

Partially Verified75%

All Facts (10)

Partially Verified

The default models of multiple Providers have changed: Cortecs, CrossModel, Eden AI, Google Gemini, GitHub Copilot, Google Vertex AI, LLM Gateway, Ofox, OpenCode Go, and Prime Inference now default to Gemini 4 Argon; Fireworks AI, Nebius Token Factory, and Requesty switch to Muse Spark Open; CoreWeave, DigitalOcean, NanoGPT, and Nvidia adopt Nemotron 3.5 Super VL; Aixy and Neon use Claude Haiku 5.5; Agnes AI, Ambient, IteraCompute, Poe, Scaleway, and SenseNova also have their own adjustments.

75%
Unverified

For production dependencies, it is recommended to also keep the official Claude Code subscription or another paid solution as a backup, to avoid free service fluctuations affecting work.

50%
Unverified

Agnes AI's claim of "self-developed" currently lacks third-party verification; the original video only cited the platform's own data.

50%
Unverified

The configuration process includes four steps: create a key on the Agnes API platform, add a Cloud Provider vendor in CC Switch and fill in the API Key and request address, obtain the model list and map it to Agnes 2.0 Flash, and enable the local routing and Claude routing switches.

50%
Unverified

According to platform data cited by the uploader, in Agnes's first week of free access, text model calls exceeded 10,000, image generation exceeded 2 million images, and video generation exceeded 2 million seconds.

50%
Unverified

When configuring a provider in CC Switch, select Cloud Provider as the type, then choose "Custom Provider", fill in the API Key, request URL, and API format, and click "Fetch Model List" to verify the connection.

50%
Unverified

CC Switch requires enabling local routing and turning on the Claude routing switch; after enabling Agnes in the provider list, Claude Code's requests will be forwarded through CC Switch to the Agnes free gateway.

50%
Unverified

Claude Code can only connect to text models and cannot directly call Agnes's image-generation models; image-generation capability must be invoked by creating a Skill.

50%
Unverified

In the 35mm film-style portrait image generation tested by the uploader, flash highlights, skin texture, and pores were all reproduced; image-to-image can change outfits without changing the face, suitable for use on resumes or LinkedIn profiles.

50%
Unverified

In the video generation test, the facial expression progression in a short video of a female singer singing was coherent, but a nighttime street video had a failure case where a passerby was "cloned" into two people.

50%

Source Articles