Update Umans AI Coding Plan + add Umans AI (pay-per-token) provider#2265
Merged
Conversation
Umans AI Coding Plan (subscription): - Add umans-kimi-k2.7 (Kimi K2.7 Code) model - Add umans-flash-beta (deprecated alias for umans-flash) - Fix umans-glm-5.1: add vision modality (via handoff) and interleaved reasoning - Fix umans-flash: add interleaved reasoning field - Fix umans-qwen3.6-35b-a3b: add interleaved reasoning field - Add reasoning_options to all models - Add explicit name field to models using base_model Umans AI (new provider - pay-per-token for orgs): - New provider for organization service-account usage - Per-token pricing from the org billing page: - Kimi K2.6: /bin/bash.95/.00 (input/output), /bin/bash.20 cache read - Kimi K2.7 Code: /bin/bash.95/.00, /bin/bash.19 cache read - GLM 5.1: .40/.40, /bin/bash.29 cache read - Umans Flash (Qwen3.6-35B-A3B): /bin/bash.15/.00, /bin/bash.05 cache read - Umans Coder: routes to Kimi K2.6 rates - Same endpoint (api.code.umans.ai), different billing model
Contributor
Author
|
@aredridel just submitted my first PR here :) |
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Two changes to the Umans provider listings:
1. Update Umans AI Coding Plan (subscription)
umans-kimi-k2.7— Kimi K2.7 Code, Moonshot's newest coding modelumans-flash-beta— deprecated alias forumans-flash(sunset 2026-06-07)umans-glm-5.1— addimageto input modalities (vision via handoff) and[interleaved]reasoningumans-flash— add[interleaved]reasoning field (Qwen3.6 supportsreasoning_content)umans-qwen3.6-35b-a3b— add[interleaved]reasoning fieldreasoning_optionsand explicitnameto all models usingbase_model2. Add Umans AI provider (pay-per-token)
New provider for organization service-account usage with per-token pricing:
Same endpoint (
api.code.umans.ai), different billing model. Subscription plans are flat-rate (hence $0 costs on the Coding Plan); token billing is available to orgs via service-account keys. Pricing source: https://app.umans.ai/offers/code/docs/orgsNotes
base_modelfields on all provider models link to the canonical model entries (e.g.moonshotai/kimi-k2.6,zhipuai/glm-5.1,alibaba/qwen3.6-35b-a3b,moonshotai/kimi-k2.7-code), so Umans will now appear as a provider option on those model pagesimagein input modalities because Umans serves it with a vision handoff (text generation via GLM 5.1, image preprocessing via Kimi), matching the same pattern as Kimi For Coding's listingrecommended_max_tokensfrom our/v1/models/infoendpoint), but the Coding Plan does not enforce a hard output limit so we omit the output limit override there; the pay-per-token provider setsoutput = 32_768as a practical default