Claude Fable 5 vs Mercury 2

API pricing, context window and capabilities for Claude Fable 5 and Mercury 2, side by side. Prices are the cheapest serving route per 1M tokens, verified against LiteLLM and OpenRouter.

Verdict

computed from the published numbers

Claude Fable 5 wins on intelligence and on context window. Mercury 2 wins on price. Benchmark data is unavailable for one or both models.

Price
Mercury 2
Coding
Not called
Intelligence
Claude Fable 5
Context window
Claude Fable 5

Key takeaways

who wins on what, from the published numbers

Claude Fable 5 wins

  • Larger context window (1M vs 128K)
  • Higher max output (128K vs 50K)
  • More serving providers (4 vs 1)
  • Supports vision
  • Has reasoning mode

Mercury 2 wins

  • Cheaper input ($10.00 vs $0.25 /1M)
  • Cheaper output ($50.00 vs $0.75 /1M)
Cheaper overall
Mercury 2
$0.25 + $0.75 /1M
Larger context
Claude Fable 5
1M
More providers
Claude Fable 5
4 providers

Pricing & specs

cheapest serving route · per 1M tokens
Claude Fable 5Mercury 2
Input $/1M$10.00 $0.25 best
Output $/1M$50.00 $0.75 best
Context window1M best128K
Max output128K best50K
Serving providers4 best1
Released2026-06-09 2026-02-24

Benchmarks

Artificial Analysis indices, side by side
Claude Fable 5Mercury 2
Intelligence59.9 best25.3
Coding76.5 Not available
GPQA Diamond93% best77%
Output speed46 t/s 602 t/s best
Latency (TTFT)29.29s 2.73s best

Cost calculator

choose a serving route for each side
Input tokens / month
Output tokens / month
Claude Fable 5
via Amazon Bedrock
$100
Mercury 2
via Inception
$2.00

Capabilities

feature support, side by side
FeatureClaude Fable 5Mercury 2
Vision
Tool use
Reasoning
Audio
Prompt caching
Structured output
Web search

Related comparisons

Frequently asked questions

Which is cheaper, Claude Fable 5 or Mercury 2?
Mercury 2 is cheaper for input ($10.00 vs $0.25 per 1M tokens). Mercury 2 is cheaper for output ($50.00 vs $0.75 per 1M tokens).
What is the context window difference between Claude Fable 5 and Mercury 2?
Claude Fable 5 has a 1M-token context window and Mercury 2 has 128K tokens, so Claude Fable 5 can take a larger prompt.
How do Claude Fable 5 and Mercury 2 compare on benchmarks?
On the tracked Artificial Analysis indices, Claude Fable 5 leads on intelligence.
Pricing verified against LiteLLM + OpenRouter + provider pages · refreshed daily

Every weekday

AI moves fast. Here's your debrief.

News, analysis, tools, and more.

For people who build with AI