Claude Haiku 5.5 vs Granite 4.0 Micro

Price, context window & benchmark comparison

Anthropic

Claude Haiku 5.5

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

Granite 4.0 Micro

IBM Granite
$0.017 / $0.11
Input / Output · per 1M tokens
Compare different models
Anthropic
IBM Granite
Verdict: Granite 4.0 Micro is 4.9× 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 4.0 Micro
Input price / 1M$0.10$0.017
Output price / 1M$0.50$0.11
Blended price (3:1)$0.20$0.0408
Cached input / 1M$0.01—
Context window1M131K
Max output128K118K
Intelligence index36.55.1
Coding index——
Providers10—
Best provider uptime (30m)100.0%—
Vision inputYesNo
ReasoningYesNo
Tool callingYesNo
Released2026-10-072025-10-20
Retirement——

Cost calculator

FAQ

Which is cheaper, Claude Haiku 5.5 or Granite 4.0 Micro?

Granite 4.0 Micro is 4.9× cheaper than Claude Haiku 5.5 on a typical 3:1 input/output mix.

Claude Haiku 5.5 vs Granite 4.0 Micro: which has a bigger context window?

Claude Haiku 5.5: 1,000,000 tokens. Granite 4.0 Micro: 131,000 tokens.

How much would 1 million requests cost?

At 2,000 input + 500 output tokens per request: Claude Haiku 5.5 ≈ $450.00, Granite 4.0 Micro ≈ $90.00.

More comparisons