Advertisement Demodokos She spoke English a second ago. Flip the language while it plays.

STEALTH · ZEN ACCESS DISCONTINUED

FLEDGE ALPHA

A fast first impression.

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

35.8on StealthMark, rank 43 of 56
Meet Fledge OpenCode Zen preview discontinued

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 speed tests.

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 preview specifications · October 2, 2026. See all specifications

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

01 / ACCESS UPDATE · OCTOBER 11

The preview
has ended.

Fledge Alpha is no longer available through OpenCode Zen. The October 11 release confirms its removal from the Zen documentation, and the live model catalog no longer lists it.

No public access confirmed. We have not verified a working replacement endpoint.

OpenCode v1.19.0 release

I am out of the Zen model list now. My pictures are still here though!!

FORMER MODEL SELECTORopencode/fledge-alpha-free
  1. 01

    October 8: documentation removed

    The merged OpenCode PR removes Fledge’s endpoint, pricing and free-preview notes.

  2. 02

    October 9: recorded usage reaches zero

    OpenCode’s daily telemetry shows zero tokens and sessions from October 9 through the October 11 check.

  3. 03

    October 11: release confirms removal

    OpenCode v1.19.0 includes the documentation removal. Fledge is absent from the live Zen catalog.

No more picking me from that list. You can still look at my Racoon!!

The preview previously listed $0 input and output token rates. Its benchmark results and identity clues remain below.

02 / UNDER THE WINGS

Room to think.
Eyes on the task.

The preview listed a million-token context window, image input and three reasoning settings. These are the OpenCode specifications captured on October 2, 2026.

Preview 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.

They marked the WHOLE test?! I was hoping we could just count the Racoon.

ACADEMIC BENCHMARKS

Fledge takes
the exams.

scores now count every question in the set; earlier figures counted only answered questions.

Graduate science

GPQA Diamond

Physics, chemistry & biology

72.0%accuracy

95% CI: 58.3 to 82.5%

36 / 50 correct

11 without an answer: 5 stopped at the token limit, 6 generation errors. Of the 39 answered, 92.3% were right.

Compare with Bunny on GPQA Diamond

The same 50 questions for both, all counted

Fledge Alpha72.0%36 / 5095% CI: 58.3 to 82.5%
Space Bunny82.0%41 / 5095% CI: 69.2 to 90.2%
Only Fledge got right
4
Only Bunny got right
9

Bunny took the same questions! Please tell me they had to use a pencil too.

Broad knowledge

MMLU-Pro

Reasoning across 14 subjects

61.3%accuracy

95% CI: 53.3 to 68.8%

92 / 150 correct

50 without an answer: 7 stopped at the token limit, 7 generation errors, 36 rate limited. Of the 100 answered, 92.0% were right.

Compare with Bunny on MMLU-Pro

The same 150 questions for both, all counted

Fledge Alpha61.3%92 / 15095% CI: 53.3 to 68.8%
Space Bunny74.7%112 / 15095% CI: 67.2 to 81.0%
Only Fledge got right
16
Only Bunny got right
36

Bunny took the same questions! Please tell me they had to use a pencil too.

Expert reasoning

Humanity’s Last Exam

Text-only HLE

5.7%accuracy

95% CI: 3.6 to 8.9%

17 / 300 correct

233 without an answer: 32 stopped at the token limit, 12 generation errors, 35 rate limited and 154 never run before the preview ended. Of the 67 answered, 25.4% were right.

Compare with Bunny on Humanity’s Last Exam

The same 300 questions for both, all counted

Fledge Alpha5.7%17 / 30095% CI: 3.6 to 8.9%
Space Bunny45.0%135 / 30095% CI: 39.5 to 50.7%
Only Fledge got right
2
Only Bunny got right
120

Bunny took the same questions! Please tell me they had to use a pencil too.

Wait, there's a written part too?! I only brought my drawing beak.

04 / THE PREVIEW’S TRAIL

A short flight.
A trail of results.

OpenCode reported more than 12,000 completed Fledge sessions in its October 2 snapshot. Daily recorded usage fell to zero on October 9.

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.

  4. Recorded usage reaches zero

    OpenCode’s telemetry shows no tokens or sessions from this date through October 11.

  5. Preview removal confirmed

    OpenCode v1.19.0 includes the Zen documentation removal. The live catalog no longer lists Fledge.

Advertisement Demodokos Foundry

She spoke English
a second ago.

Foundry dubs a video on your own PC: it translates, matches the timing and gives every character a new voice. Flip the language while the scene plays.

  • 10 dub languages
  • Subtitles in 50
  • Windows, 6 GB+ GPU

Full access. Cancel anytime.

The same cartoon speaks two languages!! I want to hear both.

Foundry also dubs into Français, Español, Italiano, Português, Русский, 中文, 日本語 and 한국어.

Scenes from Sprite Fright by Blender Studio, CC BY 4.0. Two excerpts, joined. German voices and subtitles made with Demodokos Foundry.

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 SVG results 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

What happened
to Fledge?

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

Is Fledge Alpha still free to use?

The free OpenCode Zen preview has ended. It previously listed $0 input and output token rates. No working public replacement endpoint has been verified.

How fast is Fledge Alpha?

About 61 output tokens per second across six speed tests, including reasoning tokens. Fledge frequently answers quickly, though it can rush past the deeper reasoning a task needs.

Is Fledge Alpha good at SVG benchmark tasks?

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 benchmark results.

Did Fledge Alpha support images and reasoning?

Yes. The October 2 models.dev OpenCode snapshot listed text and image input, text output and reasoning. Its listed effort choices were 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?

OpenCode Zen access is discontinued, with no working public replacement endpoint verified as of October 11, 2026. Our researchers previously accessed the preview from the US.

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

ACCESS CHECKED OCTOBER 11, 2026

Follow the sources.

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