Repository navigation
feat(cheapaimodel): add cheapaimodel provider - #11684
Merged
Merged
Conversation
Add cheapaimodel, an OpenAI-compatible multi-model relay, with base_model entries for deepseek-v4-1-flash, glm-5.3, glm-5.3-flash, grok-4.7 and kimi-k3. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Contributor
|
No actionable findings. |
github-actions
Bot
added
the
reviewer: ready
The gateway re-derives its USD prices from a monthly fixed exchange rate; the November rate raises every price by about 0.32%. Values match https://cheapaimodel.ai/api/models as of 2026-11-02.
github-actions
Bot
removed
the
reviewer: ready
Contributor
|
No actionable findings. |
github-actions
Bot
added
the
reviewer: ready
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
providers/cheapaimodel), withbase_modelfor all 5 API IDs:deepseek-v4-1-flash,glm-5.3,glm-5.3-flash,grok-4.7,kimi-k3.listPricing) for comparison. DeepSeek V4.1 Flash bills a 2x peak multiplier on weekdays 01:00–04:00 and 06:00–10:00 UTC (no holiday exemption on this host); the other four are flat.AGENTS.md); requests are passed through to the lab.Disclosure: I work on cheapaimodel, and we'll keep this entry up to date when models or prices change.
Test plan
bun validatebun run v1:check: only additions (the new provider and its 5 models), no existing fields changedOPENCODE_MODELS_PATH=packages/web/dist/_api.json opencode models cheapaimodellists 5 models (opencode 1.19.4)opencode run -m cheapaimodel/<id>returns a chat completion for all 5 models/v1/chat/completions: DeepSeek V4.1 Flash, GLM-5.3, GLM-5.3-Flash and Kimi K3 return reasoning inreasoning_content; DeepSeek withthinking.type = disabledreports 0 reasoning tokens. Grok 4.7 returns no reasoning text, onlyreasoning_tokens(which rise withreasoning_effort), so its file sets noreasoning_fieldSources
🤖 Generated with Claude Code