← Model list

Claude Haiku 4.5

anthropic·anthropic/claude-haiku-4-5-20251001·GA·Closed·claude-haiku series

Fast Claude model for responsive assistance, classification, and lightweight agents

At a glance
Official price$1.00 / $5.00 per 1M
Cache read $0.10 · Anthropic
Lowest paid$0.14 / $0.71
QiHang Gateway · 8.6× spread
Context200,000
⚠ Providers report 192,000–200,000; the table below is authoritative
Output limit64,000
Capabilities
ReasoningTool useStructured outputTemperatureAttachments
⚠ Providers report capability flags inconsistently
Modalities
TextImagePDF
Knowledge cutoff2025-02-28
Released / updated2025-10-15 / 2025-10-15

Quality & performance

Artificial Analysis doesn't cover this model (267 of 2059 have data). Quality data comes from independent evals covering widely used models.

Available at 21 providers21 with public prices

ProviderTierInputOutputCache readCache writeContextOutput limitStatus
QiHangGateway$0.14$0.71200,00064,000
Poe
anthropic/claude-haiku-4.5
Gateway$0.85$4.30$0.085$1.10192,00064,000
NanoGPTGateway$1.00$5.00$0.10200,00064,000
Vertex
claude-haiku-4-5@20251001
First-party$1.00$5.00$0.10$1.25200,00064,000
Vertex (Anthropic)
claude-haiku-4-5@20251001
Cloud$1.00$5.00$0.10$1.25200,00064,000
DaoXEGateway$1.00$5.00$0.10$5.00200,00064,000
AnthropicOfficialFirst-party$1.00$5.00$0.10$1.25200,00064,000
Amazon Bedrock
anthropic.claude-haiku-4-5-20251001-v1:0
Cloud$1.00$5.00$0.10$1.25200,00064,000
DigitalOcean
anthropic-claude-4.5-haiku
Cloud$1.00$5.00$1.00$1.25200,00064,000
ZenMux
anthropic/claude-haiku-4.5
Gateway$1.00$5.00$0.10$1.25200,00064,000

Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.

Your usage cost

1QiHang$63.50
2Poe$293.20
3NanoGPT$342.00
4Vertex$342.00
5Vertex (Anthropic)$342.00
6DaoXE$342.00
7Anthropic · Official$342.00
Switch to QiHang to save $278.50/mo (81%)
Note: this is a gateway; verify availability and rate limits yourself.

Benchmark

No upstream benchmark data for this model. For quality, see the Artificial Analysis intelligence score above.

Reasoning control

budget_tokens ≥ 1,024effort = loweffort = mediumeffort = higheffort = xhigheffort = maxToggle (on / off)

3 / 21 providers expose no reasoning control (reasoning_options: []).

Related models

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$5.00$02026-08-052026-08-132026-08-05 · Input list $1.002026-08-06 · Input list $1.002026-08-07 · Input list $1.002026-08-08 · Input list $1.002026-08-09 · Input list $1.002026-08-10 · Input list $1.002026-08-11 · Input list $1.002026-08-12 · Input list $1.002026-08-13 · Input list $1.002026-08-05 · Output list $5.002026-08-06 · Output list $5.002026-08-07 · Output list $5.002026-08-08 · Output list $5.002026-08-09 · Output list $5.002026-08-10 · Output list $5.002026-08-11 · Output list $5.002026-08-12 · Output list $5.002026-08-13 · Output list $5.002026-08-05 · Min blended $0.2822026-08-06 · Min blended $0.2822026-08-07 · Min blended $0.2822026-08-08 · Min blended $0.2822026-08-09 · Min blended $0.2822026-08-10 · Min blended $0.2822026-08-11 · Min blended $0.2822026-08-12 · Min blended $0.2822026-08-13 · Min blended $0.282