Claude Haiku 5.5
anthropic/claude-haiku-5-5
fastest & most compact, great for quick tasks.
cmd --model claude-haiku-5-5
Intelligence index
not yet scored
Coding index
not yet scored
Input
$0.10 /M
Output
$0.50 /M
Cache read
$0.01 /M
Agent-loop cost
$0.04 /M in
Context window
1M tokens
Released
October 7, 2026
Modalities
→
vs. the lineup
Claude Haiku 5.5 beside its stablemates and nearest rivals. The ◆ marks the best value in each column across every row shown.
pin a rival:
| Model | Intelligence | Coding | Input $/M | Output $/M | Blended $/M | Context |
|---|---|---|---|---|---|---|
| Claude Sonnet 5.5 | 56◆ | —◆ | $2◆ | $10◆ | $4◆ | 1M◆ |
| Claude Fable 5.1 | 53.4◆ | 81.6◆ | $10◆ | $50◆ | $20◆ | 1M◆ |
| Claude Fable 5 | 49.6◆ | 76.5◆ | $10◆ | $50◆ | $20◆ | 1M◆ |
| Claude Sonnet 5 | 38.2◆ | 71.5◆ | $2◆ | $10◆ | $4◆ | 1M◆ |
| Claude Sonnet 4.6 | 30.1◆ | 63◆ | $3◆ | $15◆ | $6◆ | 1M◆ |
| Claude Haiku 5.5 ◆ | —◆ | —◆ | $0.10◆ | $0.50◆ | $0.20◆ | 1M◆ |
| DeepSeek V4 Pro (latest)pinned | 36◆ | 68.8◆ | $0.66◆ | $1.98◆ | $0.99◆ | 1M◆ |
| DeepSeek V4 Flash (latest)pinned | 34◆ | 69.1◆ | $0.15◆ | $0.60◆ | $0.26◆ | 1M◆ |
price bands
Claude Haiku 5.5 is not billed at one flat rate — the price changes with how much context a request carries. The header quotes the standard band; here is every band.
| Band | Context | Input $/M | Output $/M | Cache read $/M |
|---|---|---|---|---|
| Standard | ≤ 100K | $0.10 | $0.50 | $0.01 |
| Long context | > 100K | $0.50 | $2.50 | $0.05 |
usage calculator
How far a month of credits goes on Claude Haiku 5.5.
Claude Haiku 5.5 runs on Pro and up — from $20/mo.
Input tokensfresh prompt
800Output tokensmodel reply
180Cache read tokensre-read context
50Kcost / request $0.0007 · in $0.10 · out $0.50 · cache $0.01 per M
fresh input 12%output 13%cache reads 75%
Requests / 30 days
30K
$20 credits ÷ $0.0007 per request
~6.0K quick fixes~1.2K bug fixes~199 feature PRs
what real work costs
Real coding tasks priced end to end on Claude Haiku 5.5, from a quick lookup to a full-repo agent run.
One agent task
$0.01
180K in at 75% cache hit, 12K out
What you pay
$0.06 /M
all-in across every token that task touched
Sticker input
$0.10 /M
cache reads bill at $0.01 /M instead
| Task | Tokens in · out | Claude Haiku 5.5 | MiMo V2.6 Flash | Claude Haiku 4.5 |
|---|---|---|---|---|
| Quick lookup / one-liner | 8K · 1K | $0.0007 | $0.0004 | $0.0065 |
| Review a 500-line PR | 60K · 4K | $0.0042 | $0.0038 | $0.04 |
| Fix a bug (agent loop) | 180K · 12K | $0.01 | $0.01 | $0.12 |
| Refactor a module | 320K · 20K | $0.02 | $0.02 | $0.21 |
| Full-repo agent run | 900K · 45K | $0.05 | $0.04 | $0.49 |
frequently asked
How much does Claude Haiku 5.5 cost?
$0.10/M input and $0.50/M output, cache reads $0.01/M. In an agent loop most input is cache-read, so the effective input rate is about $0.04/M.Which plan do I need?
Available on Pro and above.
How do I switch to it?
Run
cmd --model claude-haiku-5-5, or type /model in a session and pick it. You can switch mid-session without losing context.Ship code that matches your taste
Command Code is the AI coding agent that continuously learns your taste. Start for $1.
Benchmarks from Artificial Analysis (v4.3)commandcode.ai/models/claude-haiku-5-5