Skip to content
RankShark

Skyfall 36B V2

Skyfall 36B v2 is an enhanced iteration of Mistral Small 2501, specifically fine-tuned for improved creativity, nuanced writing, role-playin

ModelOpen sourceby TheDrummersince 2025
22.7

SharkScore

#515 in Models

Why it scores 22.7

Skyfall 36B V2 has a SharkScore of 22.7/100, ranked #515 of 608 in Models (updated 2026-11-19).

Each part compares Skyfall 36B V2 with other listings in Models. Evidence covers 87% of the score's weight.

Adoption
0 · 30%
User reviews
no data · 25%
Maintenance
0 · 20%
Trust & transparency
80 · 15%
Momentum
no data · 10%

Paying never changes this score. How ranking works · method v2026-11-18.2

RankShark review of Skyfall 36B V2

Automated evaluation by RankShark · 18 Nov 2026 · method v1.0 · How we review

We were not paid for this review.

As of 2026-11-18, Skyfall 36B V2 is a text-only model tuned for creative writing and role-play, with a 32,768-token context window. [E1, E2]

Skyfall 36B V2 is a text-to-text model. Its creator describes it as an upscaled version of Mistral Small 2501 with continued training for creativity and role-play; OpenRouter lists it for text input and output. [E1, E2]

Best for

  • People seeking a model for creative writing, role-play, or coherent storytelling. · model card, OpenRouter
  • Text-only applications that can use a 32,768-token context window. · OpenRouter

Not for

  • Workflows that require image, audio, or other non-text input or output; the listing specifies text only. · OpenRouter

Key features

  • Creative writing and role-play tuning. The vendor describes Skyfall v2 as an upscaled version of Mistral Small 2501 with continued training for creativity and role-play. · model card
  • Text-to-text. The vendor listing identifies text as both the input and output modality. · OpenRouter
  • Chat templates. The vendor lists Mistral v7 Tekken as highly recommended, Metharme as not recommended, and Alpaca as a possible fit for CYOA or story use. · model card
  • Context window. The listing gives a 32,768-token context window; RankShark measured the same figure on 2026-11-18. · OpenRouter
  • Generation parameters. OpenRouter lists support for parameters including temperature, top_p, top_k, stop, seed, and structured_outputs. · OpenRouter

Pros

  • Its stated focus is creative writing and role-play, with storytelling also named in the OpenRouter description. · model card, OpenRouter
  • The model page lists three chat templates and indicates which ones are recommended or not recommended. · model card
  • OpenRouter lists a 32,768-token context window. · OpenRouter

Cons

  • The listing specifies text input and output only, not multimodal support. · OpenRouter
  • No free plan or free trial stated on the pages we checked.
  • Whether customer data is used for model training is not stated on the pages we checked.

Pricing

PlanPriceLimits
OpenRouter API$0.55 per million input tokens; $0.80 per million output tokens32,768-token context window

Checked 18 Nov 2026

Free plan
Not stated (checked 18 Nov 2026)
Free trial
Not stated (checked 18 Nov 2026)
Trains on customer data
Not stated (checked 18 Nov 2026)
Data retention
Not stated (checked 18 Nov 2026)
Data regions
Not stated (checked 18 Nov 2026)
Data processing agreement
Not stated (checked 18 Nov 2026)
AI models used
Skyfall 36B V2; the creator describes it as an upscaled version of Mistral Small 2501. · model card, OpenRouter
API
OpenRouter lists chat completions, completions, messages, and responses endpoints. · OpenRouter
SDKs
Not stated (checked 18 Nov 2026)
Webhooks
Not stated (checked 18 Nov 2026)
Platforms
OpenRouter listing and Hugging Face model page. · model card, OpenRouter
Security claims
No security certification stated (checked 18 Nov 2026)

What we measured

Context window (OpenRouter listing) · now
32,768 tokens
Price per million tokens (OpenRouter listing) · now
$0.55 in, $0.8 out
Package downloads · 30 days
3,802
How we tested · sources
  • Hourly uptime and response-time checks of the product's URL.
  • Repository, release and download data from GitHub, npm, PyPI and Hugging Face where they exist.
  • We did not sign up, pay, or use the product as a customer.
  • 18 Nov 2026: Plans or prices changed on the pricing page.
  • 18 Nov 2026: Plans or prices changed on the pricing page.

Something wrong? Report an error with a public link that shows it; corrections re-run the review.

Top alternatives to Skyfall 36B V2

See all
  • 67.1

    Qwen3.8 27B is an open-weight dense vision-language model from Qwen.

    ModelOpen source
  • 65.5

    Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per t

    ModelOpen source
  • 64.7

    Qwen3.8 Flash is a multimodal reasoning model from Alibaba.

    ModelOpen source
  • 64.3

    Qwen3.6 27B is a dense 27-billion-parameter language model from the Qwen Team at Alibaba, released in April 2026.

    ModelOpen source