Claude Haiku 4.5
anthropic/claude-haiku-4-5
fastest & most compact, great for quick tasks.
cmd --model claude-haiku-4-5
Intelligence index
24.1
Output speed
96.3 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 | 63.1◆ | 78◆ | 52.6◆ | $5◆ | $25◆ | $10◆ | 1M◆ |
| Claude Fable 5 | 62.1◆ | 76.5◆ | 66.8◆ | $10◆ | $50◆ | $20◆ | 1M◆ |
| Claude Opus 4.8 | 57.3◆ | 74.3◆ | —◆ | $5◆ | $25◆ | $10◆ | 1M◆ |
| Claude Sonnet 5 | 55.3◆ | 71.5◆ | 82.8◆ | $2◆ | $10◆ | $4◆ | 1M◆ |
| Claude Sonnet 4.6 | 48.4◆ | 63◆ | —◆ | $3◆ | $15◆ | $6◆ | 1M◆ |
| Claude Haiku 4.5 ◆ | 24.1◆ | —◆ | 96.3◆ | $1◆ | $5◆ | $2◆ | 200K◆ |
| DeepSeek V4 Pro (latest)pinned | 45.3◆ | 59.4◆ | 63.3◆ | $0.43◆ | $0.87◆ | $0.54◆ | 1M◆ |
| DeepSeek V4 Flash (latest)pinned | 52◆ | 69.1◆ | 115.9◆ | $0.14◆ | $0.28◆ | $0.18◆ | 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
24.1
#46 of 46 scored
Long-context reasoning
48.3
reasoning across a long context
SciCode
34.4
scientific coding
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 1.2 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
What is Claude Haiku 4.5 best for?+
Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4’s performance across reasoning, coding, and computer-use tasks, Haiku 4.5 brings frontier-level capability to real-time and high-volume applications. It introduces extended thinking to the Haiku line; enabling controllable reasoning depth, summarized or interleaved thought output, and tool-assisted workflows with full support for coding, bash, web search, and computer-use tools. Scoring >73% on SWE-bench Verified, Haiku 4.5 ranks among the world’s best coding models while maintaining exceptional responsiveness for sub-agents, parallelized execution, and scaled deployment.
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 (v4.1)commandcode.ai/models/claude-haiku-4-5