ElevenAgents: Agent models: Added gpt-6-sol, gpt-6-luna, glm-52, deepseek-v41-flash
By Steven Van ·
Agent builders can now pick from six new LLMs, and test runs can report credits and USD cost.
Six more language models can now run ElevenLabs agents: gpt-6-sol, gpt-6-luna, glm-52, deepseek-v41-flash, claude-opus-5 and claude-opus-5-5. They are added to the supported agent LLM options in ElevenAgents, and the September 28 changelog lists them in the API's LLM enum for creating, getting and updating agents.
The same ElevenAgents entry also covers agent testing:
- Test invocation summaries can include total credits and the USD price.
- Individual test runs can include credits used and a charging breakdown.
The JavaScript and Python SDKs (both v2.70.0) add the cost fields for test invocation summaries and the deepseek-v41-flash model.
ElevenLabs
AI audio platform for text to speech, voice cloning, and video dubbing across dozens of languages while preserving the original tone and emotion.
View ElevenLabs →