Skyfall 36B V2 vs GLM 4.7

Skyfall 36B V2 at $0.632 in and $0.920 out and GLM 4.7 at $0.460 in and $2.01 out — per million tokens, from the same wallet.

Skyfall 36B V2

Thedrummer

0.39¢

for a client proposal

$0.632 in · $0.920 out / 1M

33K context · released March 2025

Full page →

GLM 4.7

Z.ai

0.39¢

for a client proposal

$0.460 in · $2.01 out / 1M

203K context · released December 2025

Full page →

Asking all both at once — identical prompt, identical context — costs about 0.78¢ for a typical client proposal.

At a glance

Cheapest input: GLM 4.7 at $0.460 per million tokens.
Cheapest output: Skyfall 36B V2 at $0.920 per million tokens.
Largest context: GLM 4.7 at 203K tokens — about 290 pages.

Cost per task

Estimated totals at the rates above. Solid bar is input, lighter bar is output.

Quick code fix

2K in · 500 out

Skyfall 36B V2

0.17¢

GLM 4.7

0.19¢

Draft a client proposal from notes

5K in · 800 out

Skyfall 36B V2

0.39¢

GLM 4.7

0.39¢

Context-heavy session (Alyph workspace)

155K in · 4K out

Skyfall 36B V2

needs 155K ctx

GLM 4.7

$0.08

Analyze a 50-page legal contract

35K in · 1K out

Skyfall 36B V2

needs 35K ctx

GLM 4.7

1.8¢

Large architecture refactor

250K in · 3K out

Skyfall 36B V2

needs 250K ctx

GLM 4.7

needs 250K ctx

Solid part of each bar is input tokens, the lighter part is output. Models that don’t fit a task are marked instead of priced.

Cost vs Token Amount

Drag the slider to adjust the split between input and output workload.

80% Input20% Output

Skyfall 36B V2

GLM 4.7

Adjust the ratio slider to change how output tokens influence the final price for equivalent workloads.

Pricing

Skyfall 36B V2

GLM 4.7

Input / 1M tokens

$0.632

$0.460

Output / 1M tokens

$0.920

$2.01

Cached input / 1M

$0.287

$0.092

Specs

Skyfall 36B V2

GLM 4.7

Provider

Thedrummer

Z.ai

Released

March 2025

December 2025

Context window

33K

203K

Max output

33K

131K

Input

Text

Output

Text

Reasoning

Answers directly

Shows its thinking

Knowledge cutoff

2024-06-30

—

Try it with real numbers

2K tokens in · 500 tokens out.

Skyfall 36B V2

Thedrummer

0.17¢

for this task

73% input · 27% output

Full pricing →

GLM 4.7

Z.ai

0.19¢

for this task

48% input · 52% output

Full pricing →

All 2, same prompt and context: 0.37¢. That is the entire cost of the comparison.

Your $5 welcome credit covers about 1,369 of these.

Which should you pick?

For long documents, GLM 4.7 has the largest context window here — 203K tokens.

On price, Skyfall 36B V2 is the cheapest of the two on a typical task, at about 0.39¢.

If you want to watch the model think, GLM 4.7 shows reasoning; the other answers directly.

Or don’t pick. Send the identical prompt to all both, read the answers side by side, and keep the winner. How to run a fair bake-off →

Skyfall 36B V2 pricing →GLM 4.7 pricing →Add Lyria 3 Clip Preview Add Grok 4.20

Questions, answered

Which is cheaper, Skyfall 36B V2 or GLM 4.7?

On a typical client proposal (5K tokens in, 800 out): Skyfall 36B V2 at 0.39¢; GLM 4.7 at 0.39¢. Long prompts can change the order when long-context rates apply.

Which has the largest context window?

GLM 4.7 — 203K tokens, about 290 pages.

Can I run Skyfall 36B V2 and GLM 4.7 side by side on Alyph?

Yes — that is what Alyph is built for: the identical prompt with identical context to all 2, answers rendered side by side, billed from one wallet. This exact combination costs about 0.78¢ for a typical task.

Ask both at once

Identical prompt, identical context, answers side by side — about 0.78¢ for a typical client proposal. Free to start, with $5 of credit.