Claude Haiku 4.5
anthropic/claude-haiku-4-5
fastest & most compact, great for quick tasks.
cmd --model claude-haiku-4-5
Intelligence index
15.4
Output speed
98.4 tok/s
Input
$1 /M
Output
$5 /M
Cache read
$0.10 /M
Agent-loop cost
$0.37 /M in
Context window
200K tokens
Released
October 15, 2025
Modalities
→
vs. the lineup
Claude Haiku 4.5 beside its stablemates and nearest rivals. The ◆ marks the best value in each column across every row shown.
pin a rival:
| Model | Intelligence | Coding | Speed | Input $/M | Output $/M | Blended $/M | Context |
|---|---|---|---|---|---|---|---|
| Claude Opus 5.5 | 57.6◆ | —◆ | —◆ | $4◆ | $20◆ | $8◆ | 1M◆ |
| Claude Fable 5.1 | 53.4◆ | 81.6◆ | 66.8◆ | $10◆ | $50◆ | $20◆ | 1M◆ |
| Claude Fable 5 | 49.6◆ | 76.5◆ | —◆ | $10◆ | $50◆ | $20◆ | 1M◆ |
| Claude Sonnet 5 | 38.2◆ | 71.5◆ | 82.8◆ | $2◆ | $10◆ | $4◆ | 1M◆ |
| Claude Sonnet 4.6 | 30.1◆ | 63◆ | —◆ | $3◆ | $15◆ | $6◆ | 1M◆ |
| Claude Haiku 4.5 ◆ | 15.4◆ | —◆ | 98.4◆ | $1◆ | $5◆ | $2◆ | 200K◆ |
| DeepSeek V4 Pro (latest)pinned | 36◆ | 68.8◆ | 78.6◆ | $0.66◆ | $1.98◆ | $0.99◆ | 1M◆ |
| DeepSeek V4 Flash (latest)pinned | 34◆ | 69.1◆ | —◆ | $0.15◆ | $0.60◆ | $0.26◆ | 1M◆ |
coding performance
The Intelligence Index and its sub-scores, ranked against every scored model in the catalog. A metric that has not been measured for Claude Haiku 4.5 has been left empty.
IFBench
42
instruction following
Intelligence Index
15.4
#67 of 67 scored
Long-context reasoning
49.7
reasoning across a long context
GPQA Diamond
64.6
graduate-level QA
usage calculator
How far a month of credits goes on Claude Haiku 4.5.
Claude Haiku 4.5 runs on Pro and up — from $20/mo.
Input tokensfresh prompt
800Output tokensmodel reply
180Cache read tokensre-read context
50Kcost / request $0.0067 · in $1 · out $5 · cache $0.10 per M
fresh input 12%output 13%cache reads 75%
Requests / 30 days
3.0K
$20 credits ÷ $0.0067 per request
~597 quick fixes~119 bug fixes~20 feature PRs
what real work costs
Real coding tasks priced end to end on Claude Haiku 4.5, from a quick lookup to a full-repo agent run.
One agent task
$0.12
180K in at 75% cache hit, 12K out
What you pay
$0.62 /M
all-in across every token that task touched
Sticker input
$1 /M
cache reads bill at $0.10 /M instead
| Task | Tokens in · out | Claude Haiku 4.5 | Muse Spark 1.3 Contributor |
|---|---|---|---|
| Quick lookup / one-liner | 8K · 1K | $0.0065 | $0.0003 |
| Review a 500-line PR | 60K · 4K | $0.04 | $0.0027 |
| Fix a bug (agent loop) | 180K · 12K | $0.12 | $0.0072 |
| Refactor a module | 320K · 20K | $0.21 | $0.01 |
| Full-repo agent run | 900K · 45K | $0.49 | $0.03 |
frequently asked
How much does Claude Haiku 4.5 cost?
$1/M input and $5/M output, cache reads $0.10/M. In an agent loop most input is cache-read, so the effective input rate is about $0.37/M.Which plan do I need?
Available on Pro and above.
How do I switch to it?
Run
cmd --model claude-haiku-4-5, 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-4-5