Skip to content

feat(aiand): add GLM 5.3 and Qwen 3.8 27B - #5805

Open
fenilmodi00 wants to merge 1 commit into
anomalyco:devfrom
fenilmodi00:feat/aiand-glm-5.3-qwen-3.8-27b
Open

feat(aiand): add GLM 5.3 and Qwen 3.8 27B#5805
fenilmodi00 wants to merge 1 commit into
anomalyco:devfrom
fenilmodi00:feat/aiand-glm-5.3-qwen-3.8-27b

Conversation

@fenilmodi00

Copy link
Copy Markdown
Contributor

Summary

Adds two new models served by the ai& (aiand) provider at https://api.aiand.com/v1:

  • zai-org/glm-5.3 (GLM 5.3)
  • qwen/qwen3.8-27b (Qwen 3.8 27B)

Details

providers/aiand/models/zai-org/glm-5.3.toml

  • Base model: zhipuai/glm-5.3
  • Pricing: $1.00 input / $4.00 output per 1M tokens (USD), cached input $0.30 / 1M tokens
  • Context window: 1,048,576 tokens
  • Reasoning options: reasoning_effort probed live on 2026-08-29; accepts ["none", "low", "xhigh", "max"] (rejects minimal, medium, high with 400)
  • Modalities: Inherits ["text"] from base

providers/aiand/models/qwen/qwen3.8-27b.toml

  • Base model: alibaba/qwen3.8-27b
  • Pricing: $0.40 input / $3.00 output per 1M tokens (USD), cached input $0.20 / 1M tokens
  • Context window: 262,144 tokens
  • Reasoning options: reasoning_effort probed live on 2026-08-29; accepts ["none", "low", "medium", "xhigh"] (rejects minimal, high, max with 400)
  • Modalities: ["text", "image", "video", "pdf"] (PDF supported via Files API / document conversion per catalog & live probe)

Verification

  • Verified against live https://api.aiand.com/v1/models catalog endpoint
  • Live chat completions probed with each reasoning_effort value and input modality
  • Inherits cleanly from existing lab base models (models/zhipuai/glm-5.3.toml and models/alibaba/qwen3.8-27b.toml)
  • Validated against catalog schema

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant