Claude 3 Haiku vs Claude Fable 5

Claude 3 Haiku at $0.287 in and $1.44 out and Claude Fable 5 at $11.50 in and $57.50 out — per million tokens, from the same wallet.

Claude 3 Haiku

Anthropic

0.26¢

for a client proposal

$0.287 in · $1.44 out / 1M

200K context · released March 2024

Full page →

Claude Fable 5

Anthropic

$0.10

for a client proposal

$11.50 in · $57.50 out / 1M

1M context · released 3 months ago

Full page →

Asking all both at once — identical prompt, identical context — costs about $0.11 for a typical client proposal.

At a glance

Cheapest input: Claude 3 Haiku at $0.287 per million tokens.
Cheapest output: Claude 3 Haiku at $1.44 per million tokens.
Largest context: Claude Fable 5 at 1M tokens — about 1,400 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 3 Haiku

0.13¢

Claude Fable 5

$0.05

Draft a client proposal from notes

5K in · 800 out

Claude 3 Haiku

0.26¢

Claude Fable 5

$0.10

Context-heavy session (Alyph workspace)

155K in · 4K out

Claude 3 Haiku

$0.05

Claude Fable 5

$2.01

Analyze a 50-page legal contract

35K in · 1K out

Claude 3 Haiku

1.1¢

Claude Fable 5

$0.46

Large architecture refactor

250K in · 3K out

Claude 3 Haiku

needs 250K ctx

Claude Fable 5

$3.05

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 3 Haiku

Claude Fable 5

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

Pricing

Claude 3 Haiku

Claude Fable 5

Input / 1M tokens

$0.287

$11.50

Output / 1M tokens

$1.44

$57.50

Cached input / 1M

$0.035

$1.15

Web search

1.1¢ / search

Specs

Claude 3 Haiku

Claude Fable 5

Provider

Anthropic

Released

March 2024

3 months ago

Context window

200K

Max output

128K

Input

Text and Images

Text, Images, and Files

Output

Text

Reasoning

Answers directly

Shows its thinking

Knowledge cutoff

2023-08-31

—

Try it with real numbers

2K tokens in · 500 tokens out.

Claude 3 Haiku

Anthropic

0.13¢

for this task

44% input · 56% output

Full pricing →

Claude Fable 5

Anthropic

$0.05

for this task

44% input · 56% output

Full pricing →

All 2, same prompt and context: $0.05. That is the entire cost of the comparison.

Your $5 welcome credit covers about 94 of these.

Which should you pick?

For long documents, Claude Fable 5 has the largest context window here — 1M tokens.

On price, Claude 3 Haiku is the cheapest of the two on a typical task, at about 0.26¢.

If you want to watch the model think, Claude Fable 5 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 3 Haiku pricing →Claude Fable 5 pricing →Add Lyria 3 Clip Preview Add Grok 4.20

Questions, answered

Which is cheaper, Claude 3 Haiku or Claude Fable 5?

On a typical client proposal (5K tokens in, 800 out): Claude 3 Haiku at 0.26¢; Claude Fable 5 at $0.10. Long prompts can change the order when long-context rates apply.

Which has the largest context window?

Claude Fable 5 — 1M tokens, about 1,400 pages.

Can I run Claude 3 Haiku and Claude Fable 5 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 $0.11 for a typical task.

Ask both at once

Identical prompt, identical context, answers side by side — about $0.11 for a typical client proposal. Free to start, with $5 of credit.