duncanmcqueen wants Mike to add Synthetic to its model-router bench

The proposal would let users choose another subscription gateway for open-weights AI models without making the product's model selection more fragmented.

integrationworkflow

duncanmcqueen proposed making Synthetic, a subscription gateway for open-weights models, Mike's fourth route to AI models. The work was designed to fit the existing shared router approach, rather than bolt on a one-off connection.

Model access: teams could select Synthetic's tool-capable text models alongside existing choices.
Credentials: users could supply a shared environment key or save an encrypted personal key.
Consistent choice: Synthetic would appear in settings, the writing composer and the Word add-in.
Clearer pricing and names: the interface would correctly read currency-formatted prices and present both fixed models and floating aliases intelligibly.

One thoughtful detail: settings would show what a floating alias currently resolves to, while the composer keeps the shorter alias name. The pull request was closed without merging, so none of this is live in Mike.

So what Legal teams seeking more control over the models behind drafting and review workflows should watch this fork, but will need to inspect GitHub before treating Synthetic as an available option.

View this fork on GitHub →

Spotted something wrong? Or know the PR text has fresher detail than the writeup above?

Commits in this thread

1 commit from duncanmcqueen/mike, oldest first. Source extracted verbatim from the harvested git log.

SHA Subject Author Date

23b41c5a feat: add OpenCode Go as a third model router duncanmcqueen 2026-08-20 ↗ GitHub

SHA	Subject	Author	Date
`23b41c5a`	feat: add OpenCode Go as a third model router	duncanmcqueen	2026-08-20	↗ GitHub
commit body OpenCode Go (opencode.ai's low-cost hosted gateway for open coding models - GLM-5, Kimi K3, Qwen3.8 Max, MiniMax-M3, DeepSeek V4) joins OpenRouter and the Vercel AI Gateway as a router, reusing the existing router plumbing end to end rather than adding a parallel one: - opencode-go/<model> ids stream through the shared router adapter against https://opencode.ai/zen/go/v1, with OPENCODE_GO_BASE_URL as the usual proxy/test override. OpenRouter's attribution headers and reasoning payload stay OpenRouter-only. - New opencode-go user API key (OPENCODE_API_KEY env or encrypted per-user storage) with a Settings > API Keys field and a migration widening the user_api_keys provider CHECK. - GET /models/opencode-go returns the live catalog with the key kept server-side; Settings > Routers gains an OpenCode Go picker, and the saved selection gates requests through the same user_router_models choke point that stops a hand-crafted request from spending the operator's env key on an arbitrary gateway model. - Both model pickers and the Word add-in gain an "OpenCode Go" group. Router slugs, model-id prefixes and API-key provider names are one string per router, so routerForModelId, the selection lookups and the profile payload are now driven by ROUTER_SLUGS instead of a hard-coded pair. The one place the routers genuinely differ is catalog-id shape: OpenCode Go publishes bare model names ("glm-5"), so id validation is per-router. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

commit body

OpenCode Go (opencode.ai's low-cost hosted gateway for open coding models
- GLM-5, Kimi K3, Qwen3.8 Max, MiniMax-M3, DeepSeek V4) joins OpenRouter
and the Vercel AI Gateway as a router, reusing the existing router
plumbing end to end rather than adding a parallel one:

- opencode-go/<model> ids stream through the shared router adapter
  against https://opencode.ai/zen/go/v1, with OPENCODE_GO_BASE_URL as the
  usual proxy/test override. OpenRouter's attribution headers and
  reasoning payload stay OpenRouter-only.
- New opencode-go user API key (OPENCODE_API_KEY env or encrypted
  per-user storage) with a Settings > API Keys field and a migration
  widening the user_api_keys provider CHECK.
- GET /models/opencode-go returns the live catalog with the key kept
  server-side; Settings > Routers gains an OpenCode Go picker, and the
  saved selection gates requests through the same user_router_models
  choke point that stops a hand-crafted request from spending the
  operator's env key on an arbitrary gateway model.
- Both model pickers and the Word add-in gain an "OpenCode Go" group.

Router slugs, model-id prefixes and API-key provider names are one string
per router, so routerForModelId, the selection lookups and the profile
payload are now driven by ROUTER_SLUGS instead of a hard-coded pair. The
one place the routers genuinely differ is catalog-id shape: OpenCode Go
publishes bare model names ("glm-5"), so id validation is per-router.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>

Capture this thread into my fork

Download a single Markdown prompt that tells Claude how to port every commit above into your working tree — adapting paths and structure to match your repo. Run it via claude -p < capture-thread-1364.md from inside the repo you want the changes in.

⬇ Download capture-thread-1364.md