Claude Haiku 4.5

Tool callingStructured outputReasoningImage inputFile input

Model card Launch post Website Docs

Fast Claude lane for lightweight agents, office tasks, and responsive chat

Context: 200K
Released: 1y ago
Input / 1M tokens: $1.00
Output / 1M tokens: $5.00
Cached input / 1M tokens: $0.10
Cache write / 1M tokens: $1.25

Sources:models.devOpenRouter

Benchmarks

DeepSWE is the primary coding benchmark where an exact model evaluation exists. Other sourced evaluations appear below; missing scores are not zero.

Not evaluated in DeepSWE 1.1 as of 2026-09-22. Results are only shown for exact model versions in the official dataset. Official leaderboard.

No benchmark results have been matched to this model yet.

Specifications

Developer: Anthropic
Model family: Claude
Type: Language model
Predecessor: —
Successor: —
Released: October 15, 2025
Model ID: anthropic/claude-haiku-4.5
Openness: Closed
License: —
Input modalities: text, image, file
Output modalities: text
Modality: text+image+file->text
Tokenizer: Claude
Max output tokens: 64K
Knowledge cutoff: 2025-02-28
Hugging Face: —
Source freshness: Metadata synced Oct 8, 2026, 10:17 PM UTC

Additional source evidence

Source model: anthropic/claude-haiku-4-5
Source family: claude-haiku
Last updated: 2025-10-15
Knowledge cutoff: 2025-02-28
Model context: 200K
Model output limit: 64K
Open weights: No
File attachments: Yes
Reasoning: Yes
Tool calling: Yes
Temperature control: Yes

Published benchmarks

Benchmark	Score	Evaluation details	Evidence
SWE-Bench Pro	39.45 · resolve rate	public	Source

Complete source record (JSON)

{
  "id": "anthropic/claude-haiku-4-5",
  "name": "Claude Haiku 4.5 (latest)",
  "description": "Fast Claude lane for lightweight agents, office tasks, and responsive chat",
  "family": "claude-haiku",
  "last_updated": "2025-10-15",
  "knowledge": "2025-02-28",
  "attachment": true,
  "reasoning": true,
  "tool_call": true,
  "temperature": true,
  "modalities": {
    "input": [
      "text",
      "image",
      "pdf"
    ],
    "output": [
      "text"
    ]
  },
  "limit": {
    "context": 200000,
    "output": 64000
  },
  "benchmarks": [
    {
      "name": "SWE-Bench Pro",
      "score": 39.45,
      "source": "https://labs.scale.com/leaderboard/swe_bench_pro_public",
      "metric": "resolve rate",
      "dataset": "public"
    }
  ],
  "release_date": "2025-10-15",
  "open_weights": false
}

Infrastructure

Provider availability

All providers

Provider	Endpoint	Context	Input /M tokens	Output /M tokens	Cached input /M tokens	Cache write /M tokens	Uptime 1d	Data handling
Amazon Bedrock	amazon-bedrock/global	200K	$1.00	$5.00	$0.10	$1.25	100.00%	ZDR: Yes Training: Unknown Prompt logging: Unknown Retention: Unknown ZDR source Privacy policy Checked 2026-10-15
Amazon Bedrock	amazon-bedrock/globalBatch pricing	200K	$1.00	$5.00	$0.10	$1.25	100.00%	ZDR: No Training: Unknown Prompt logging: Unknown Retention: Unknown ZDR source Privacy policy Checked 2026-10-15
Anthropic	anthropic	200K	$1.00	$5.00	$0.10	$1.25	100.00%	ZDR: No Training: Unknown Prompt logging: Unknown Retention: Unknown ZDR source Privacy policy Checked 2026-10-15
Anthropic	anthropicBatch pricing	200K	$1.00	$5.00	$0.10	$1.25	100.00%	ZDR: No Training: Unknown Prompt logging: Unknown Retention: Unknown ZDR source Privacy policy Checked 2026-10-15
Azure	azure/global	200K	$1.00	$5.00	$0.10	$1.25	97.02%	ZDR: No Training: Unknown Prompt logging: Unknown Retention: Unknown ZDR source Privacy policy Checked 2026-10-15
Azure	azure/globalBatch pricing	200K	$1.00	$5.00	$0.10	$1.25	97.02%	ZDR: No Training: Unknown Prompt logging: Unknown Retention: Unknown ZDR source Privacy policy Checked 2026-10-15
Google	google-vertex/global	200K	$1.00	$5.00	$0.10	$1.25	99.55%	ZDR: Yes Training: Unknown Prompt logging: Unknown Retention: Unknown ZDR source Privacy policy Checked 2026-10-15
Google	google-vertex/globalBatch pricing	200K	$1.00	$5.00	$0.10	$1.25	99.55%	ZDR: No Training: Unknown Prompt logging: Unknown Retention: Unknown ZDR source Privacy policy Checked 2026-10-15
Amazon Bedrock	amazon-bedrock/us	200K	$1.10	$5.50	$0.11	$1.38	100.00%	ZDR: Yes Training: Unknown Prompt logging: Unknown Retention: Unknown ZDR source Privacy policy Checked 2026-10-15
Amazon Bedrock	amazon-bedrock/eu-west-1	200K	$1.10	$5.50	$0.11	$1.38	99.85%	ZDR: Yes Training: Unknown Prompt logging: Unknown Retention: Unknown ZDR source Privacy policy Checked 2026-10-15
Amazon Bedrock	amazon-bedrock/usBatch pricing	200K	$1.10	$5.50	$0.11	$1.38	100.00%	ZDR: No Training: Unknown Prompt logging: Unknown Retention: Unknown ZDR source Privacy policy Checked 2026-10-15
Amazon Bedrock	amazon-bedrock/eu-west-1Batch pricing	200K	$1.10	$5.50	$0.11	$1.38	99.85%	ZDR: No Training: Unknown Prompt logging: Unknown Retention: Unknown ZDR source Privacy policy Checked 2026-10-15
Google	google-vertex/us-east5	200K	$1.10	$5.50	$0.11	$1.38	100.00%	ZDR: Yes Training: Unknown Prompt logging: Unknown Retention: Unknown ZDR source Privacy policy Checked 2026-10-15
Google	google-vertex/europe	200K	$1.10	$5.50	$0.11	$1.38	100.00%	ZDR: Yes Training: Unknown Prompt logging: Unknown Retention: Unknown ZDR source Privacy policy Checked 2026-10-15
Google	google-vertex/us-east5Batch pricing	200K	$1.10	$5.50	$0.11	$1.38	100.00%	ZDR: No Training: Unknown Prompt logging: Unknown Retention: Unknown ZDR source Privacy policy Checked 2026-10-15
Google	google-vertex/europeBatch pricing	200K	$1.10	$5.50	$0.11	$1.38	100.00%	ZDR: No Training: Unknown Prompt logging: Unknown Retention: Unknown ZDR source Privacy policy Checked 2026-10-15

Provider data:OpenRouter

Text provenance

Transitioning

Claude text watermarking

Anthropic says Claude models launched before August 2, 2026 have a transition period and are being moved to the same watermarking system over time.

Official explanation