Claude Opus 4 vs GPT-4

Claude Opus 4 at $17.25 in and $86.25 out and GPT-4 at $34.50 in and $69.00 out — per million tokens, from the same wallet.

Claude Opus 4

Anthropic

$0.16

for a client proposal

$17.25 in · $86.25 out / 1M

200K context · released May 2025

Full page →

GPT-4

OpenAI

$0.23

for a client proposal

$34.50 in · $69.00 out / 1M

8K context · released May 2023

Full page →

Asking all both at once — identical prompt, identical context — costs about $0.38 for a typical client proposal.

At a glance

Cheapest input: Claude Opus 4 at $17.25 per million tokens.
Cheapest output: GPT-4 at $69.00 per million tokens.
Largest context: Claude Opus 4 at 200K 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

Claude Opus 4

$0.08

GPT-4

$0.10

Draft a client proposal from notes

5K in · 800 out

Claude Opus 4

$0.16

GPT-4

$0.23

Context-heavy session (Alyph workspace)

155K in · 4K out

Claude Opus 4

$3.02

GPT-4

needs 155K ctx

Analyze a 50-page legal contract

35K in · 1K out

Claude Opus 4

$0.69

GPT-4

needs 35K ctx

Large architecture refactor

250K in · 3K out

Claude Opus 4

needs 250K ctx

GPT-4

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

Claude Opus 4

GPT-4

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

Pricing

Claude Opus 4

GPT-4

Input / 1M tokens

$17.25

$34.50

Output / 1M tokens

$86.25

$69.00

Cached input / 1M

$1.73

—

Web search

1.1¢ / search

—

Specs

Claude Opus 4

GPT-4

Provider

Anthropic

OpenAI

Released

May 2025

May 2023

Context window

200K

Max output

32K

Input

Images, Text, and Files

Text

Output

Text

Reasoning

Shows its thinking

Answers directly

Knowledge cutoff

2025-01-31

2021-09-30

Try it with real numbers

2K tokens in · 500 tokens out.

Claude Opus 4

Anthropic

$0.08

for this task

44% input · 56% output

Full pricing →

GPT-4

OpenAI

$0.10

for this task

67% input · 33% output

Full pricing →

All 2, same prompt and context: $0.18. That is the entire cost of the comparison.

Your $5 welcome credit covers about 27 of these.

Which should you pick?

For long documents, Claude Opus 4 has the largest context window here — 200K tokens.

On price, Claude Opus 4 is the cheapest of the two on a typical task, at about $0.16.

For images or files, Claude Opus 4 can read them directly; GPT-4 is text-only.

If you want to watch the model think, Claude Opus 4 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 →

Claude Opus 4 pricing →GPT-4 pricing →Add Lyria 3 Clip Preview Add Grok 4.20

Questions, answered

Which is cheaper, Claude Opus 4 or GPT-4?

On a typical client proposal (5K tokens in, 800 out): Claude Opus 4 at $0.16; GPT-4 at $0.23. Long prompts can change the order when long-context rates apply.

Which has the largest context window?

Claude Opus 4 — 200K tokens, about 290 pages.

Can I run Claude Opus 4 and GPT-4 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 $0.38 for a typical task.

Ask both at once

Identical prompt, identical context, answers side by side — about $0.38 for a typical client proposal. Free to start, with $5 of credit.