Skip to content

model alias support for provider variations #526

Description

@nijave

Some providers like opencode go have slightly different model names. For these cases, it'd be nice if the hard coded names can be remapped to the provider-specific name through an env var or similar config

https://opencode.ai/zen/go/v1/models

deepseek/deepseek-v4-flash -> deepseek-v4-flash
deepseek/deepseek-v4-pro   -> deepseek-v4-pro
moonshotai/kimi-k2.6       -> kimi-k2.6
xiaomi/mimo-v2.5-pro       -> mimo-v2.5-pro
z-ai/glm-5.2               -> glm-5.2

Bedrock is another example where it has proprietary names (I know this is already supported however it may be behind an openai compatible proxy and not directly accessible--we're using original Bedrock "runtime" behind an OpenAI-compatible proxy)

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Fields

    No fields configured for issues without a type.

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions