Claude Fable 5.2 vs Mercury 2
Price, context window & benchmark comparison
VS
Compare different models
Verdict: Mercury 2 is 42.7× cheaper than Claude Fable 5.2 on a typical 3:1 input/output mix. Claude Fable 5.2 has the larger context window (1M vs 128K).
| Claude Fable 5.2 | Mercury 2 | |
|---|---|---|
| Input price / 1M | $8.00 | $0.25 |
| Output price / 1M | $40.00 | $0.75 |
| Blended price (3:1) | $16.00 | $0.38 |
| Cached input / 1M | $0.20 | $0.025 |
| Context window | 1M | 128K |
| Max output | 128K | 50K |
| Intelligence index | 64.6 | — |
| Coding index | — | 31.1 |
| Providers | 5 | — |
| Best provider uptime (30m) | 100.0% | — |
| Vision input | Yes | No |
| Reasoning | Yes | Yes |
| Tool calling | Yes | Yes |
| Released | 2026-11-07 | 2026-03-04 |
| Retirement | — | 2026-11-08 |
Cost calculator
FAQ
Which is cheaper, Claude Fable 5.2 or Mercury 2?
Mercury 2 is 42.7× cheaper than Claude Fable 5.2 on a typical 3:1 input/output mix.
Claude Fable 5.2 vs Mercury 2: which has a bigger context window?
Claude Fable 5.2: 1,000,000 tokens. Mercury 2: 128,000 tokens.
How much would 1 million requests cost?
At 2,000 input + 500 output tokens per request: Claude Fable 5.2 ≈ $36,000, Mercury 2 ≈ $875.00.
More comparisons
Claude Fable 5.2 vs Gemini 4 CarbonClaude Fable 5.2 vs Gemini Omni 1.2 FlashClaude Fable 5.2 vs Gemini Omni 1.1 FlashClaude Fable 5.2 vs Hy4Claude Fable 5.2 vs GLM 5.3 FlashX LegalClaude Fable 5.2 vs GPT-6.1 TerraClaude Fable 5.2 vs GPT-6.1 Terra ProClaude Fable 5.2 vs Kimi K3.1 ProClaude Fable 5.2 vs MiniMax M3.1 FlashClaude Fable 5.2 vs DeepSeek V4.1 Flash 1017Claude Fable 5.2 vs Nemotron 3.5 Super VLClaude Fable 5.2 vs Gemini 4 ArgonClaude Fable 5.2 vs Claude Haiku 5.5Claude Fable 5.2 vs Nano Banana 2.1Claude Fable 5.2 vs Mistral Large 4Claude Fable 5.2 vs GPT-6.1 Sol ProMercury 2 vs Gemini 4 CarbonMercury 2 vs Gemini Omni 1.2 FlashMercury 2 vs Gemini Omni 1.1 FlashMercury 2 vs Hy4Mercury 2 vs GLM 5.3 FlashX LegalMercury 2 vs GPT-6.1 TerraMercury 2 vs GPT-6.1 Terra ProMercury 2 vs Kimi K3.1 Pro