[BOT ISSUE] Baseten: add missing thinkingmachines/inkling-small

Open Beginner friendly
#1,043 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Assessment

Difficulty
1/5
Estimated time
Under an hour
Newbie friendliness
85/100
Issue type
Feature
Clarity
Clearly specified
Activity status
Quiet
Tech stack
json
Domain
api, backend

Research direction

Open packages/proxy/schema/model_list.json and inspect the existing thinkingmachines/inkling entry around line 10620 and nearby model entries. Add the missing thinkingmachines/inkling-small catalog data using the values in the issue, then verify the model appears once with Baseten as its provider and the JSON remains valid.

Written by the indexing model from the issue text.

Description

autofix-blocked bot-issue

Summary

The Baseten model thinkingmachines/inkling-small (Thinking Machines Inkling Small) is not present in model_list.json. This is a smaller, more efficient variant of the Inkling model — 276B MoE with 12B active parameters vs. the original Inkling's 975B MoE with 41B active. The original thinkingmachines/inkling is already in the catalog.

Missing Model

Model ID Display Name Context Window Params Input $/1M Output $/1M Cached $/1M
thinkingmachines/inkling-small Inkling Small 1,000,000 276B MoE (12B active) $0.50 $1.20 $0.10

Context

  • The catalog already has thinkingmachines/inkling (line 10620) with available_providers: ["baseten", "openrouter"] and pricing $1.00/$4.05/$0.17
  • Inkling Small is a distinct, smaller model — not a variant or alias of the original Inkling
  • Currently available on Baseten only (not listed on Together, Fireworks, or OpenRouter)
  • Uses OpenAI-compatible API endpoint at https://inference.baseten.co/v1

Suggested Catalog Entry

"thinkingmachines/inkling-small": {
  "format": "openai",
  "flavor": "chat",
  "multimodal": true,
  "input_cost_per_mil_tokens": 0.5,
  "output_cost_per_mil_tokens": 1.2,
  "input_cache_read_cost_per_mil_tokens": 0.1,
  "displayName": "Inkling Small",
  "reasoning": true,
  "max_input_tokens": 1000000,
  "available_providers": ["baseten"]
}

Verification Checklist

Check Status Detail
Cross-source ✅ Verified on Baseten library page (model ID, specs, capabilities) AND Baseten pricing page (pricing $0.50/$1.20/$0.10) — two independent official Baseten pages
Already in catalog ✅ grep for inkling-small in model_list.json returns no matches
ID format ✅ Follows existing thinkingmachines/inkling convention in catalog
Duplicate issue ✅ No open or closed issue covers inkling-small. Issues #999 and #1011 cover the original Inkling on different providers
Not deprecated ✅ Actively listed on Baseten library and pricing pages
Not embedding/vision-only ✅ Chat model with multimodal input (text, image, audio → text output) and reasoning capabilities

Verification Notes

Field Source Notes
API ID thinkingmachines/inkling-small Baseten library page Shown in API example code
Pricing $0.50/$1.20/$0.10 Baseten pricing page Input / output / cached input per 1M tokens
Context 1,000,000 Baseten library page Listed as "1M" context window
Params 276B MoE (12B active) Baseten library page Sparse mixture-of-experts architecture
Multimodal Baseten library page "Native text, image, and audio support" — three input modalities
Reasoning Baseten library page reasoning_content field in API response; reasoning_tokens in usage
max_output_tokens Not published Omitted — not specified on Baseten library page
format: "openai" Catalog convention Existing thinkingmachines/inkling uses openai format; Baseten uses OpenAI-compatible API

Relationship to existing entries

Entry Providers Status
thinkingmachines/inkling baseten, openrouter Already in catalog (line 10620) — original 975B MoE model
thinkingmachines/inkling-small baseten Missing — this issue — smaller 276B MoE variant

Local Files Inspected

  • packages/proxy/schema/model_list.json — confirmed thinkingmachines/inkling-small absent; existing thinkingmachines/inkling at line 10620
{
  "kind": "missing_model",
  "provider": "baseten",
  "models": ["thinkingmachines/inkling-small"],
  "status": "active",
  "model_specs": {
    "thinkingmachines/inkling-small": {
      "format": "openai",
      "flavor": "chat",
      "multimodal": true,
      "input_cost_per_mil_tokens": 0.5,
      "output_cost_per_mil_tokens": 1.2,
      "input_cache_read_cost_per_mil_tokens": 0.1,
      "displayName": "Inkling Small",
      "reasoning": true,
      "max_input_tokens": 1000000,
      "available_providers": ["baseten"]
    }
  },
  "source_urls": [
    "https://www.baseten.co/library/inkling-small/",
    "https://www.baseten.co/pricing/"
  ]
}
Dominant language
TypeScript
Stars
410
Forks
65
Avg merge
18h 29m
Merged PRs (30d)
51

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

More from braintrustdata/braintrust-proxy

All issues in braintrustdata/braintrust-proxy

Similar issues

More TypeScript issues

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.