Claude Haiku 5.5 vs Granite 4.2 8B

Price, context window & benchmark comparison

Anthropic

Claude Haiku 5.5

Anthropic
$0.10 / $0.50
Input / Output · per 1M tokens
VS
IBM Granite

Granite 4.2 8B

IBM Granite
$0.06 / $0.15
Input / Output · per 1M tokens
Compare different models
Anthropic
IBM Granite
Verdict: Granite 4.2 8B is 2.4× cheaper than Claude Haiku 5.5 on a typical 3:1 input/output mix. Claude Haiku 5.5 scores higher on the Artificial Analysis Intelligence Index (36.5 vs 5.1). Claude Haiku 5.5 has the larger context window (1M vs 131K).
Claude Haiku 5.5Granite 4.2 8B
Input price / 1M$0.10$0.06
Output price / 1M$0.50$0.15
Blended price (3:1)$0.20$0.0825
Cached input / 1M$0.01$0.015
Context window1M131K
Max output128K118K
Intelligence index36.55.1
Coding index—22.4
Providers10—
Best provider uptime (30m)100.0%—
Vision inputYesNo
ReasoningYesYes
Tool callingYesYes
Released2026-10-072026-08-31
Retirement——

Cost calculator

FAQ

Which is cheaper, Claude Haiku 5.5 or Granite 4.2 8B?

Granite 4.2 8B is 2.4× cheaper than Claude Haiku 5.5 on a typical 3:1 input/output mix.

Claude Haiku 5.5 vs Granite 4.2 8B: which has a bigger context window?

Claude Haiku 5.5: 1,000,000 tokens. Granite 4.2 8B: 131,072 tokens.

How much would 1 million requests cost?

At 2,000 input + 500 output tokens per request: Claude Haiku 5.5 ≈ $450.00, Granite 4.2 8B ≈ $195.00.

More comparisons