ERNIE 4.5 VL 424B A47B vs Inkling Small

ERNIE 4.5 VL 424B A47B at $0.483 in and $1.44 out and Inkling Small at $0.517 in and $1.38 out — per million tokens, from the same wallet.

ERNIE 4.5 VL 424B A47B

Baidu

0.36¢

for a client proposal

$0.483 in · $1.44 out / 1M

123K context · released June 2025

Full page →

Inkling Small

Thinkingmachines

0.37¢

for a client proposal

$0.517 in · $1.38 out / 1M

524K context · released 1 week ago

Full page →

Asking all both at once — identical prompt, identical context — costs about 0.73¢ for a typical client proposal.

At a glance

Cheapest input: ERNIE 4.5 VL 424B A47B at $0.483 per million tokens.
Cheapest output: Inkling Small at $1.38 per million tokens.
Largest context: Inkling Small at 524K tokens — about 750 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

ERNIE 4.5 VL 424B A47B

0.17¢

Inkling Small

0.17¢

Draft a client proposal from notes

5K in · 800 out

ERNIE 4.5 VL 424B A47B

0.36¢

Inkling Small

0.37¢

Context-heavy session (Alyph workspace)

155K in · 4K out

ERNIE 4.5 VL 424B A47B

needs 155K ctx

Inkling Small

$0.09

Analyze a 50-page legal contract

35K in · 1K out

ERNIE 4.5 VL 424B A47B

1.8¢

Inkling Small

1.9¢

Large architecture refactor

250K in · 3K out

ERNIE 4.5 VL 424B A47B

needs 250K ctx

Inkling Small

$0.13

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

ERNIE 4.5 VL 424B A47B

Inkling Small

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

Pricing

ERNIE 4.5 VL 424B A47B

Inkling Small

Input / 1M tokens

$0.483

$0.517

Output / 1M tokens

$1.44

$1.38

Cached input / 1M

—

$0.115

Specs

ERNIE 4.5 VL 424B A47B

Inkling Small

Provider

Baidu

Thinkingmachines

Released

June 2025

1 week ago

Context window

123K

524K

Max output

16K

262K

Input

Images and Text

Text, Images, and Audio

Output

Text

Reasoning

Shows its thinking

Knowledge cutoff

2025-03-31

—

Try it with real numbers

2K tokens in · 500 tokens out.

ERNIE 4.5 VL 424B A47B

Baidu

0.17¢

for this task

57% input · 43% output

Full pricing →

Inkling Small

Thinkingmachines

0.17¢

for this task

60% input · 40% output

Full pricing →

All 2, same prompt and context: 0.34¢. That is the entire cost of the comparison.

Your $5 welcome credit covers about 1,466 of these.

Which should you pick?

For long documents, Inkling Small has the largest context window here — 524K tokens.

On price, ERNIE 4.5 VL 424B A47B is the cheapest of the two on a typical task, at about 0.36¢.

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 →

ERNIE 4.5 VL 424B A47B pricing →Inkling Small pricing →Add Lyria 3 Clip Preview Add Grok 4.20

Questions, answered

Which is cheaper, ERNIE 4.5 VL 424B A47B or Inkling Small?

On a typical client proposal (5K tokens in, 800 out): ERNIE 4.5 VL 424B A47B at 0.36¢; Inkling Small at 0.37¢. Long prompts can change the order when long-context rates apply.

Which has the largest context window?

Inkling Small — 524K tokens, about 750 pages.

Can I run ERNIE 4.5 VL 424B A47B and Inkling Small 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 0.73¢ for a typical task.

Ask both at once

Identical prompt, identical context, answers side by side — about 0.73¢ for a typical client proposal. Free to start, with $5 of credit.