LLM Reference

Claude Haiku 4.5

Released
2025-10-01
Last refreshed
2026-07-26
Status
Researched 119d ago
ProprietaryCommercial use: conditionalMultimodalCodingRAGAgentsLong contextVisionJSON / Tool use

Claude Haiku 4.5 is worth evaluating for coding, rag, and agents when its provider route and context window match the workload.

Use it for

  • Teams evaluating coding, rag, and agents
  • Workloads that can use a 200k context window
  • Buyers comparing 4 tracked provider routes

Do not use it for

  • Workloads where another current model has stronger sourced task evidence
Specifications
Released
2025-10-01
Context
200k
Max output
64,000
Architecture
Decoder Only
Knowledge cutoff
2025-02
Specialization
general
Openness
Proprietary
License
ProprietaryCommercial use: conditional
Weights
Not released
Code
Unknown
Training
Pretrained
Created by

Developing safe and ethical AI systems.

San Francisco, California, United States
Founded 2021
Website
Pricing
Output / 1M
$4.00
Input / 1M
$0.800

Cheapest of 9 routes · AWS Bedrock

About

Claude Haiku 4.5 is Anthropic's Claude 4.5 model with multimodal text and image input. It offers a 200K-token context window and scores 73.3 on SWE-bench Verified.

Top use-case fit: coding, agents, and build tasks

Coding

Q/$ D

1 relevant benchmark in the decision map.

RAG

Included by capability and metadata signals in the decision map.

Agents

Q/$ C

2 relevant benchmarks in the decision map.

Provider price ladder

Compare all 9

Compare API pricing across 4 providers for input and output tokens, batch, and cached reads when available.

ProviderInput / 1MOutput / 1MBatch in / outCacheRoute
AWS Bedrock$0.800$4.00--
Serverless
GCP Vertex AI$0.800$4.00--
Serverless
Anthropic$1.00$5.00$0.500 / $2.50-
Serverless
Microsoft Foundry$1.00$5.00-read $0.100 / 5m $1.25 / 1h $2.00
ServerlessProvisioned

Available via routers & gateways(16)

Capabilities

VisionMultimodalJSON / Tool useStructured OutputsCode Execution

Benchmark peer barsfor Coding

Benchmark scores(3)

Scores are benchmark-specific and are direction-aware: the same numeric gap can mean very different outcomes across suites. Use the leaderboard context and this model's provider route to decide whether the winning margin is meaningful for your workload.
BenchmarkScoreVersionEvaluationSource
BFCL68.7v4Observed 2026-04-19—Source
SWE-bench Verified73.3SWE-bench VerifiedObserved 2026-04-24—Source
MultiChallenge50.5MultiChallengeObserved 2026-04-26—Source

Migration checks

No linked migration route is available for this model yet.

Compare Claude Haiku 4.5 with other models

Show all 31 popular comparisonssorted by 7-day search impressions