NEW STEALTH · OPENCODE ZEN

FLEDGE ALPHA

A fast first impression.

About 61 output tokens/s in our tests.
Likely a router. The models are still a mystery.

Meet Fledge Free preview on OpenCode Zen

Give Fledge
a running start

Get to know Fledge Alpha

Fledge Alpha specifications

1MListed context1,048,576 tokens

Text + images

Reasoning: low · high · max

Tool calls · 131,072-token output limit
OPENCODE ZENfledge-alpha-freeSpecifications · models.dev

OUTPUT~61tokens/s

STEALTH MODELS RESEARCH

Fast answers. Uneven effort.

Fledge often rushes to a simple answer. Its SVG results range from basic sketches to carefully composed scenes.

Six generation tests.

2,048 output tokens per run, low reasoning effort. The output rate includes reasoning tokens.

Meet the standout raccoon

MAKERunknown

OUR CURRENT HYPOTHESIS

Likely a router.

The same tokenizer prompts produced significantly different input-token counts. Together with uneven SVG results, that suggests changing underlying models behind this fast route.

Follow the identity clues

OpenCode specifications · October 2, 2026. See all specifications

A million tokens!! I could put soooo much stuff in there.

Advertisement · Demodokos

A little voice. A whole studio.

Make voices, songs and scenes on your own Windows PC with Demodokos Foundry.

See it in action

Demodokos has a whole audio studio!! I want to press something.

01 / GET ABOARD

Install OpenCode.
Pick Fledge.

The quickest way in is OpenCode’s terminal app. Install it with npm or grab a download, then choose Fledge Alpha from the model list.

US regions confirmed. Other regions may support Fledge, but we haven’t identified them yet.

OpenCode downloads

Our researchers got in from the US! The rest of my map has question marks.

TERMINAL · NPMnpm install -g @opencode/cliRequires Node.js and npm. Then run opencode.
YOUR MODEL SELECTORopencode/fledge-alpha-free
  1. 01

    Open your terminal

    Run opencode in the project you want to work on.

  2. 02

    Pick Fledge Alpha

    Run /models and choose Fledge Alpha Free under OpenCode Zen. Its exact selector is shown above.

  3. 03

    Give it a task

    Try a short coding question or an image. The catalog lists text and image input, reasoning and tool calls.

Pick me pick me!! I am in the OpenCode model list.

OpenCode includes free models without a personal Zen API key. Fledge’s current preview route lists $0 input and output token rates. To connect your own Zen account, run /connect.

02 / UNDER THE WINGS

Room to think.
Eyes on the task.

A million-token context window, image input and three reasoning settings, as listed by OpenCode on models.dev.

Specifications on models.dev
Context
1,048,576 tokens
Maximum output
131,072 tokens
Input / output
Text + images → text
Reasoning effort
Low · High · Max
Tool calls
Supported
Open weights
Not listed as open

I was going to count all those tokens but lunch happened.

04 / THE TRAIL SO FAR

A new route.
Already in use.

OpenCode reports more than 12,000 completed Fledge sessions in its October 2 snapshot.

12B

Reported tokens
OpenCode telemetry · October 2 snapshot

Unique users
471
Completed sessions
12,504
Input cache ratio
91%

Recorded spend in this snapshot: $0.

OpenCode’s telemetry record

Twelve billion!! I cannot count that high on my toes.

  1. First recorded usage

    The earliest day with token usage in OpenCode’s record.

  2. Listed on OpenCode Zen

    fledge-alpha-free appears in the catalog. Early discussions follow.

  3. Specifications listed

    models.dev lists vision, reasoning and a million-token context window.

Advertisement · Demodokos

Four ways to make a little noise.

Direct a voice. Make a song. Dub a scene. Hear a book. Meet Demodokos Foundry, the audio studio that runs on your own Windows PC.

Demodokos made these! I am doing the watching.

Voice · One voice, two deliveries. Hear how the same line changes.
Music · Create a song, split its stems and work on the timeline.
Dubbing · An English scene dubbed into German with Foundry.
Reader · Read aloud on your PC, then keep listening on your phone.

Demodokos made these! I am the important little audience.

Dubbing excerpt: Sprite Fright · Blender Studio, CC BY 4.0.

05 / FOLLOW THE FOOTPRINTS

One name.
A flock behind it?

Our current evidence points to Fledge Alpha being a router backed by very fast models. The developer and underlying models remain unknown.

Everyone wants to know who made me. I was hoping YOU knew.

OUR TOKENIZER TESTS

Same prompts.
Different token counts.

We sent the same request three times. Fledge counted 7,536 input tokens on the first two runs, then 6,499 on the third.

INFERENCE · LIKELY ROUTER

Fast models.
Different habits.

Quick generation, inconsistent artwork and shifting token counts fit a routed service. Token counts alone do not establish its architecture or identify the models.

Earlier identity guesses

DeepSeek V4.x came up in early community discussion, but no connection to Fledge has been confirmed.

Thinking Machines’ Inkling was another early guess because of its OpenCode demonstrations. A connection to Fledge remains unconfirmed.

A FEW USEFUL ANSWERS

Before you
take it for a spin.

Okay ask me! I know some of these. Quite a few actually!!

Is Fledge Alpha free?

Yes. The current OpenCode Zen preview, fledge-alpha-free, lists $0 input and output token rates on models.dev.

How fast is Fledge Alpha?

About 61 output tokens per second across six 2,048-token generation tests at low reasoning effort, including reasoning tokens. Fledge frequently answers quickly, though it can rush past the deeper reasoning a task needs.

Is Fledge Alpha good at SVG artwork?

It can produce charming, well-composed scenes, especially our raccoon riding on a dog’s back as the dog steers a jet ski. Quality was inconsistent across our tests, ranging from simple sketches to much stronger work. Browse the artwork and compare the alternate attempts.

Does Fledge Alpha support images and reasoning?

Yes, the current models.dev OpenCode catalog lists text and image input, text output and reasoning. The route’s listed effort choices are low, high and max.

Is Fledge Alpha a model or a router?

Our current evidence suggests a router backed by very fast models. Repeated tokenizer prompts returned significantly different input-token counts, and our SVG outputs varied markedly. The developer and underlying models have not been identified.

Who made Fledge Alpha?

The developer remains unknown. Our current working hypothesis is a routed service, with no confirmed identity for its underlying models.

Where is Fledge Alpha available?

Our researchers accessed Fledge from the US. We haven’t confirmed which other regions are supported.

The speed question is my favourite. I get to say a big number.

CHECKED OCTOBER 2, 2026

Follow the sources.

The receipts!! I kept them. Okay our researchers kept them.