New on CompanyFabric: Claude Fable 5.2, Gemini 4 Argon, Muse Wonder, MiMo V2.6, Kimi K3.1 and decision models
Five frontier model families from Anthropic, Google, Meta, Xiaomi and Moonshot, plus decision models from TypeSafe, Perplexity and Microsoft. One key for all of them.
CompanyFabric [blocked] is one API key for every model. It works with any OpenAI SDK: change the base URL, keep your code. Prices are listed per million tokens, exactly as the providers charge them, plus a small, published fee.
In the last few weeks we added five new frontier model families and a new kind of model: decision models, which return typed answers with probabilities instead of text. Here is what's new and how to use each one.
One setup for every model below
Every chat model in this post uses the same code. Only the model string changes.
Get a key at your dashboard [blocked]. New accounts get a welcome credit.
1. Anthropic: Claude Fable 5.2 and the Claude 5.5 family
[Image blocked: Claude Fable 5.2 on CompanyFabric]
Claude Fable 5.2 (released Nov 9, 2026) is Anthropic's most capable generally available model, built for demanding reasoning and long-horizon agentic work. It costs $8 input / $40 output per 1M tokens, 20% below Fable 5.1. It has a 1M-token context window and 128K output, and cache reads cost $0.20 per 1M tokens.
- Use it for: multi-hour coding agents, research that spans many documents, and hard planning problems where a cheaper model's evals still fall short.
- Model id:
anthropic/claude-fable-5-2 - Learn more: Claude Fable 5.2 API: pricing, context and code samples [blocked]
The rest of the Claude 5.5 generation is also live:
| Model | Best for | Price (in / out per 1M) | Page |
|---|---|---|---|
| Claude Opus 5.5 | Fable-class agentic coding and computer use at a lower price | $4 / $20 | Opus 5.5 API [blocked] |
| Claude Sonnet 5.5 | Fast, near-Opus coding and knowledge work | $2 / $10 | Sonnet 5.5 API [blocked] |
| Claude Haiku 5.5 | High-volume classification, routing and sub-agents | $0.10 / $0.50 (prompts up to 100K) | Haiku 5.5 API [blocked] |
Using Claude Code? CompanyFabric also speaks Anthropic's own /v1/messages format. Point Claude Code at it and prompt caching works and is billed at the cache rate.
2. Google: Gemini 4 Argon
[Image blocked: Gemini 4 Argon on CompanyFabric]
Gemini 4 Argon is Google DeepMind's frontier model for long-horizon coding, legal, finance and science work. It ranked #1 on the Vals Index at launch. Until November 30 it has an introductory price of $2 / $10 per 1M tokens. After that it moves to Google's standard $4 / $20.
- Use it for: contract review, financial analysis and long-context coding tasks with a 1M-token window.
- Model id:
google/gemini-4-argon - Learn more: Gemini 4 Argon API [blocked]
3. Meta: Muse Wonder
[Image blocked: Meta Muse Wonder on CompanyFabric]
Muse Wonder is Meta's first frontier model family. It is built for long-running personal and professional agent work and served by Meta directly. It costs $4 / $20 per 1M tokens, has a 1M context window, and supports tools, vision and prompt caching.
- Use it for: assistants that run for many steps, such as booking, research or inbox triage. It is also a strong second opinion next to Claude and Gemini.
- Model id:
meta/muse-wonder - Learn more: Muse Wonder API [blocked]
4. Xiaomi: MiMo V2.6 Pro Ultraspeed and Flash
[Image blocked: Xiaomi MiMo V2.6 Pro Ultraspeed on CompanyFabric]
Xiaomi's MiMo line added two speed tiers:
- MiMo-V2.6-Pro-Ultraspeed: MiMo-V2.6-Pro's flagship quality with output up to 20x faster, for real-time, latency-sensitive work. $4.35 / $8.70 per 1M tokens. Model id
xiaomi/mimo-v2-6-pro-ultraspeed. Learn more [blocked] - MiMo-V2.6-Flash: a low-cost, full-modality reasoning model for high-frequency calls, at just $0.14 / $0.28 per 1M tokens. Model id
xiaomi/mimo-v2-6-flash. Learn more [blocked]
Both have a 1M-token context window.
5. Moonshot AI: Kimi K3.1 Pro and Highspeed
[Image blocked: Kimi K3.1 Pro on CompanyFabric]
Kimi K3.1 Pro is Moonshot's 3T-class open-weight flagship. It has a 1M context window and is built for coding, 3D and financial agents. It costs $2 / $10 per 1M tokens, with cache reads at $0.20.
Kimi K3.1 Pro Highspeed runs the same model 2–3x faster for responsive, interactive agents, at $4 / $20.
- Model ids:
moonshotai/kimi-k3.1-pro,moonshotai/kimi-k3.1-pro-highspeed - Learn more: Kimi K3.1 Pro API [blocked]
New: decision models (Jev, Perplexity Decider 27B, Microsoft-Decision-1)
Chat models write text that you then have to parse. A decision model never writes text. You send it the situation and a set of typed questions, and it returns one typed answer per question, each with a calibrated probability, in a single fast pass.
| Model | By | Price per 1M input tokens | Try it |
|---|---|---|---|
typesafe/jev-latest | TypeSafe | $0.042, output free | Jev [blocked] |
perplexity/decider-27b | Perplexity | $0.04, output free, reads images | Decider 27B [blocked] |
microsoft/microsoft-decision-1 | Microsoft | $0.042, output free | Microsoft-Decision-1 [blocked] |
All three take the exact same request on POST /v1/decisions, so you can compare them on your own data by changing one field. The full walkthrough, with a request, a response and when to pick which, is in Decision models, explained [blocked].
Get started
- Create a key at your dashboard [blocked]. The welcome credit covers your first calls.
- Set
base_urltohttps://api.companyfabric.com/v1in any OpenAI SDK. - Pick a model id from this post, or use
companyfabric/autoand let the router choose the cheapest model that fits the request.
See everything we've shipped on the CompanyFabric changelog [blocked].
- Release notes
- Claude
- Gemini
- Meta
- Xiaomi
- Kimi
- Decision models
Every model in this post is behind one key and one balance. Free starter credits on signup.
Get API KeyKeep reading
Decision models, explained: typed answers instead of JSON you have to parse
Jev, Perplexity Decider 27B, Microsoft-Decision-1 and Gemini Decision 1 return probabilities, not prose. How they work, what they cost and which one to pick.
Kimi K3.1 Pro in Europe: run Moonshot's flagship on Verda GPUs in Germany
Bring your own Verda key and Kimi K3.1 Pro runs on GPUs in Germany instead of Moonshot's servers in China, at a 0% fee. Same model id, same code.
Claude Code with any model: GPT, Gemini, DeepSeek and Kimi on one key
Set two environment variables and Claude Code runs on any model in the CompanyFabric library, with prompt caching intact on Claude and a budget cap on every key.