2026-03-18 CometAPI Adds GPT-5.4 mini/nano, GLM-5 Turbo, and Qwen3.5 Series!

CometAPI Update

Call test to see the page (models)

Affordable GPT-5.4 mini API | text-to-text | CometAPI

Affordable GPT-5.4 nano API | text-to-text | CometAPI

2026-03-18

cometapi Adds GPT-5.4 mini/nano, GLM-5 Turbo, and Qwen3.5 Series!

gpt-5.4-mini

gpt-5.4-mini-2026-03-17

gpt-5.4-nano

gpt-5.4-nano-2026-03-17

gpt-5.4-mini, gpt-5.4-mini-2026-03-17: OpenAI's most powerful small model to date. It brings the capabilities of GPT-5.4 to a faster, more efficient architecture, designed specifically for coding, computer operations, and high-volume workloads.

gpt-5.4-nano, gpt-5.4-nano-2026-03-17: The most affordable GPT-5.4 class model, designed specifically for simple, massive-scale tasks where speed and cost are prioritized (such as classification, data extraction, and sorting).

The above models follow the standard OpenAI chat format for calls. For details, refer to: https://apidoc.cometapi.com/chat

The above models support the OpenAI response format for calls. For details, refer to: https://apidoc.cometapi.com/responses

glm-5-turbo

glm-5-turbo: GLM-5-Turbo is a base model deeply optimized for OpenClaw Lobster scenarios, delivering excellent performance and precision in domain-specific tasks.

This model follows the standard OpenAI chat format for calls. For details, refer to: https://apidoc.cometapi.com/chat

qwen3.5-122b-a10b

qwen3.5-27b

qwen3.5-35b-a3b

qwen3.5-flash

qwen3.5 Series: The latest generation of model families from Alibaba Cloud Qwen (Tongyi Qianwen). The entire series features significant improvements in coding, mathematics, and logical reasoning capabilities. The Flash version offers ultimate inference speed, while the MoE architecture versions (122B-A10B/35B-A3B) significantly reduce computational overhead while maintaining flagship-level performance, perfectly balancing performance and cost.

The above models follow the standard OpenAI chat format for calls. For details, refer to: https://apidoc.cometapi.com/chat

Log Retention Notice

To ensure service stability and manage storage costs, logs on this site will only be retained for 3 months. Expired logs will be automatically deleted and cannot be recovered!

If you need long-term retention, please download or back up your logs within 3 months!

Effective Date: Immediately

Thank you for your understanding and support!