antigravity models #8945

Closed
opened 2026-02-16 18:11:14 -05:00 by yindo · 3 comments
Owner

Originally created by @iyang1016 on GitHub (Feb 9, 2026).

Originally assigned to: @fwang on GitHub.

Description

please add claude opus 4.6 in model selection for antigravity

Plugins

No response

OpenCode version

No response

Steps to reproduce

No response

Screenshot and/or share link

No response

Operating System

No response

Terminal

No response

Originally created by @iyang1016 on GitHub (Feb 9, 2026). Originally assigned to: @fwang on GitHub. ### Description please add claude opus 4.6 in model selection for antigravity ### Plugins _No response_ ### OpenCode version _No response_ ### Steps to reproduce _No response_ ### Screenshot and/or share link _No response_ ### Operating System _No response_ ### Terminal _No response_
yindo added the bugzenneeds:compliance labels 2026-02-16 18:11:14 -05:00
yindo closed this issue 2026-02-16 18:11:14 -05:00
Author
Owner

@github-actions[bot] commented on GitHub (Feb 9, 2026):

This issue doesn't fully meet our contributing guidelines.

What needs to be fixed:

  • This appears to be a feature request, but uses the Bug Report template. Please use the Feature Request template instead, which requires:
    • A verification checkbox that you've searched for existing requests
    • A title starting with [FEATURE]:
    • A detailed description explaining the problem or need (not just "please add")
  • The description lacks context about why this is needed or how it would be used. Please explain the use case or problem you're trying to solve.

Please edit this issue to address the above within 2 hours, or it will be automatically closed.

If you believe this was flagged incorrectly, please let a maintainer know.

@github-actions[bot] commented on GitHub (Feb 9, 2026): <!-- issue-compliance --> This issue doesn't fully meet our [contributing guidelines](../blob/dev/CONTRIBUTING.md). **What needs to be fixed:** - This appears to be a feature request, but uses the Bug Report template. Please use the **Feature Request** template instead, which requires: - A verification checkbox that you've searched for existing requests - A title starting with **[FEATURE]:** - A detailed description explaining the problem or need (not just "please add") - The description lacks context about why this is needed or how it would be used. Please explain the use case or problem you're trying to solve. Please edit this issue to address the above within **2 hours**, or it will be automatically closed. If you believe this was flagged incorrectly, please let a maintainer know.
Author
Owner

@DoraemonHugU commented on GitHub (Feb 10, 2026):

{ "provider": { "antigravity-gemini": { "name": "Antigravity", "npm": "@ai-sdk/google", "options": { "apiKey": "sk-xxxx", "baseURL": "http://127.0.0.1:8045/v1beta" }, "models": { "gemini-3-pro": { "name": "Gemini 3 Pro (Antigravity)", "limit": { "context": 1048576, "output": 65535 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "variants": { "low": { "includeThoughts": true, "thinkingLevel": "low" }, "high": { "includeThoughts": true, "thinkingLevel": "high" } } }, "gemini-3-flash": { "name": "Gemini 3 Flash (Antigravity)", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "variants": { "low": { "includeThoughts": true, "thinkingLevel": "low" }, "high": { "includeThoughts": true, "thinkingLevel": "high" } } } } }, "antigravity-claude": { "name": "Antigravity", "npm": "@ai-sdk/anthropic", "options": { "apiKey": "sk-xxxx", "baseURL": "http://127.0.0.1:8045/v1" }, "models": { "claude-sonnet-4-5": { "name": "Claude Sonnet 4.5 (Antigravity)", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] } }, "claude-sonnet-4-5-thinking": { "name": "Claude Sonnet 4.5 Thinking (Antigravity)", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "variants": { "low": { "thinking": { "type": "enabled", "thinkingBudget": 8192 } }, "high": { "thinking": { "type": "enabled", "budgetTokens": 16000 } }, "max": { "thinking": { "type": "enabled", "budgetTokens": 31999 } } } }, "claude-opus-4-5-thinking": { "name": "Claude Opus 4.5 Thinking (Antigravity)", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "variants": { "low": { "thinking": { "type": "enabled", "thinkingBudget": 8192 } }, "high": { "thinking": { "type": "enabled", "budgetTokens": 16000 } }, "max": { "thinking": { "type": "enabled", "budgetTokens": 31999 } } } }, "claude-opus-4-6-thinking": { "name": "Claude Opus 4.6 Thinking (Antigravity)", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "variants": { "low": { "thinking": { "type": "enabled", "thinkingBudget": 8192 } }, "high": { "thinking": { "type": "enabled", "budgetTokens": 16000 } }, "max": { "thinking": { "type": "enabled", "budgetTokens": 31999 } } } } } } }
English translation version:
I'm using the repository Antigravity-Manager for reverse proxying, and this repository is more active. Additionally, I've differentiated the models for different protocols, which ensures optimal performance of the models.
In my own usage, the Gemini model usually doesn't have any issues, and its performance (such as thinking level) is guaranteed.
I use Claude series models less frequently, but I haven't encountered any problems with them either. However, I'm not sure if the thinking levels are all correct.
If you want to optimize this, my technique is that you can run opencode auth login anthropic/google and input any mock apikey, then execute opencode models --verbose | sed -n '/^{/,/^}$/p' | jq -s '.' > models.json. This allows you to see how opencode configures these models, and then you can copy it over to opencode.jsonc for reference.

Original Chinese version:
我这是用的仓库Antigravity-Manager 进行的反代,这个仓库更加活跃,并且我对不同的协议的模型进行了区分,这保证了模型的最佳性能.
在我自己的使用中,gemini模型通常没有任何问题,且性能(如思考等级)有保障.
claude系列模型我用的较少,但应该也没有碰到过问题,但不确定思考等级是否都正确了.
如果你想对这个做优化,我的技巧是,你可以opencode auth login anthropic/google,随便输入mock apikey,然后调用opencode models --verbose | sed -n '/^{/,/^}$/p' | jq -s '.' > models.json 你就可以查看opencode对这些模型是如何进行的配置,然后你就可以复制过来到opencode.jsonc中进行参考.

@DoraemonHugU commented on GitHub (Feb 10, 2026): ` { "provider": { "antigravity-gemini": { "name": "Antigravity", "npm": "@ai-sdk/google", "options": { "apiKey": "sk-xxxx", "baseURL": "http://127.0.0.1:8045/v1beta" }, "models": { "gemini-3-pro": { "name": "Gemini 3 Pro (Antigravity)", "limit": { "context": 1048576, "output": 65535 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "variants": { "low": { "includeThoughts": true, "thinkingLevel": "low" }, "high": { "includeThoughts": true, "thinkingLevel": "high" } } }, "gemini-3-flash": { "name": "Gemini 3 Flash (Antigravity)", "limit": { "context": 1048576, "output": 65536 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "variants": { "low": { "includeThoughts": true, "thinkingLevel": "low" }, "high": { "includeThoughts": true, "thinkingLevel": "high" } } } } }, "antigravity-claude": { "name": "Antigravity", "npm": "@ai-sdk/anthropic", "options": { "apiKey": "sk-xxxx", "baseURL": "http://127.0.0.1:8045/v1" }, "models": { "claude-sonnet-4-5": { "name": "Claude Sonnet 4.5 (Antigravity)", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] } }, "claude-sonnet-4-5-thinking": { "name": "Claude Sonnet 4.5 Thinking (Antigravity)", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "variants": { "low": { "thinking": { "type": "enabled", "thinkingBudget": 8192 } }, "high": { "thinking": { "type": "enabled", "budgetTokens": 16000 } }, "max": { "thinking": { "type": "enabled", "budgetTokens": 31999 } } } }, "claude-opus-4-5-thinking": { "name": "Claude Opus 4.5 Thinking (Antigravity)", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "variants": { "low": { "thinking": { "type": "enabled", "thinkingBudget": 8192 } }, "high": { "thinking": { "type": "enabled", "budgetTokens": 16000 } }, "max": { "thinking": { "type": "enabled", "budgetTokens": 31999 } } } }, "claude-opus-4-6-thinking": { "name": "Claude Opus 4.6 Thinking (Antigravity)", "limit": { "context": 200000, "output": 64000 }, "modalities": { "input": [ "text", "image", "pdf" ], "output": [ "text" ] }, "variants": { "low": { "thinking": { "type": "enabled", "thinkingBudget": 8192 } }, "high": { "thinking": { "type": "enabled", "budgetTokens": 16000 } }, "max": { "thinking": { "type": "enabled", "budgetTokens": 31999 } } } } } } } ` English translation version: I'm using the repository [Antigravity-Manager](https://github.com/lbjlaq/Antigravity-Manager) for reverse proxying, and this repository is more active. Additionally, I've differentiated the models for different protocols, which ensures optimal performance of the models. In my own usage, the Gemini model usually doesn't have any issues, and its performance (such as thinking level) is guaranteed. I use Claude series models less frequently, but I haven't encountered any problems with them either. However, I'm not sure if the thinking levels are all correct. If you want to optimize this, my technique is that you can run `opencode auth login anthropic/google` and input any mock apikey, then execute `opencode models --verbose | sed -n '/^{/,/^}$/p' | jq -s '.' > models.json`. This allows you to see how opencode configures these models, and then you can copy it over to opencode.jsonc for reference. Original Chinese version: 我这是用的仓库[Antigravity-Manager](https://github.com/lbjlaq/Antigravity-Manager) 进行的反代,这个仓库更加活跃,并且我对不同的协议的模型进行了区分,这保证了模型的最佳性能. 在我自己的使用中,gemini模型通常没有任何问题,且性能(如思考等级)有保障. claude系列模型我用的较少,但应该也没有碰到过问题,但不确定思考等级是否都正确了. 如果你想对这个做优化,我的技巧是,你可以opencode auth login anthropic/google,随便输入mock apikey,然后调用`opencode models --verbose | sed -n '/^{/,/^}$/p' | jq -s '.' > models.json` 你就可以查看opencode对这些模型是如何进行的配置,然后你就可以复制过来到opencode.jsonc中进行参考.
Author
Owner

@github-actions[bot] commented on GitHub (Feb 10, 2026):

This issue has been automatically closed because it was not updated to meet our contributing guidelines within the 2-hour window.

Feel free to open a new issue that follows our issue templates.

@github-actions[bot] commented on GitHub (Feb 10, 2026): This issue has been automatically closed because it was not updated to meet our [contributing guidelines](../blob/dev/CONTRIBUTING.md) within the 2-hour window. Feel free to open a new issue that follows our issue templates.
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: anomalyco/opencode#8945