Claude Haiku 4.5
Anthropic's October 2025 Haiku, now a legacy model replaced by the cheaper Haiku 5.5.
Anthropic has replaced this model with Claude Haiku 5.5.
Context window
200K
Input / 1M tokens
$1.00
Output / 1M tokens
$5.00
Provider
Anthropic
Pricing $1/$5 per 1M input/output tokens, with up to 90% savings via prompt caching and 50% via batch processing. Its successor, Claude Haiku 5.5, costs $0.10/$0.50 per 1M tokens. Anthropic removed Haiku 4.5 from the Claude.ai model selector for Free, Pro and Max users on October 29, 2026 (announced October 15) and switched those users to Haiku 5.5. On the API, Anthropic's deprecations page still lists it as active (retirement not sooner than October 15, 2026) with no retirement date announced. · Data verified 2026-11-08
Claude Haiku 4.5 (October 2025) was Anthropic's fast, low-cost model, matching roughly Sonnet 4-level performance on reasoning, coding, and computer use at a fraction of the cost of larger Claude models. It scored 73.3% on SWE-bench Verified and was the first Haiku with extended thinking, computer use, and context awareness. It has a 200K context window and 64K max output. Claude Haiku 5.5 replaced it in October 2026 at a 90% lower list price with a 1M context window; Haiku 4.5 stays in the API as a legacy model and still uses manual extended thinking with budget_tokens.
Capability index
Relative estimates (0-100) to place this model against its peers, grounded in published benchmarks.
How to access it
Available via the Claude API (alias claude-haiku-4-5, pinned snapshot claude-haiku-4-5-20251001), Amazon Bedrock, Google Cloud, and Microsoft Foundry, and in Claude Code and the Claude Team and Enterprise plans. Removed from the Claude.ai model selector for Free, Pro and Max users on October 29, 2026; older Haiku 4.5 chats now continue on Haiku 5.5. Ideal as a fast sub-agent or high-throughput worker.
Strengths
- ✓Low latency at $1/$5 per 1M tokens
- ✓Near-frontier coding for its class: 73.3% SWE-bench Verified
- ✓First Haiku with extended thinking, computer use, and context awareness
- ✓Excellent for sub-agents, parallelized execution, and scaled deployment
- ✓Handles both text and image input
Best for developers who...
When to choose it (and when not to)
Reach for Claude Haiku 4.5 when...
- →You have pipelines tuned to Haiku 4.5 and want stable behavior while you test Haiku 5.5
- →You rely on manual extended thinking with budget_tokens or on assistant prefill, which Haiku 5.5 rejects
- →You use it in Claude Code or on Team and Enterprise plans, where it is still offered
- →Your task fits comfortably within a 200K context window
Look elsewhere if...
- ✕New projects: Haiku 5.5 costs $0.10/$0.50 per 1M tokens (prompts up to 100K) versus $1/$5
- ✕You need frontier-level reasoning or the hardest coding tasks (use Sonnet 5.5 or Opus 5.5)
- ✕You need more than 200K context or more than 64K output tokens
- ✕You need recent knowledge (Haiku 4.5's reliable cutoff is Feb 2025)
How to use it
- ›Turn on extended thinking for harder reasoning/coding steps; leave it off for simple, latency-critical calls
- ›Use it as a fast sub-agent under an Opus/Sonnet orchestrator for cost-efficient fan-out
- ›Keep prompts tight and within 200K context; cache shared prefixes for repeated calls
- ›Batch non-interactive jobs for 50% savings
Quickstart
Pythonimport anthropic
client = anthropic.Anthropic()
response = client.messages.create(
model="claude-haiku-4-5",
max_tokens=2048,
messages=[
{"role": "user", "content": "Classify these support tickets by urgency."}
],
)
print(response.content[0].text)Alias claude-haiku-4-5 resolves to snapshot claude-haiku-4-5-20251001. Supports extended thinking via the thinking parameter.
API model id: claude-haiku-4-5-20251001
Benchmarks
| Benchmark | Score | Notes |
|---|---|---|
| SWE-bench Verified | 73.3% | Averaged over 50 trials with 128K thinking budget (Anthropic) |
| GPQA | 64.6% | Per Artificial Analysis |
| MMLU Pro | 80.0% | Per Artificial Analysis |
Tools powered by Claude Haiku 4.5
Compare Claude Haiku 4.5
Compare Claude Haiku 4.5 with any other model
Build a comparison →All model comparisons →