LLM Reference

Claude 3 Haiku

Released
2024-03-04
Last refreshed
2026-06-29
Status
Researched 60d ago
DeprecatedProprietaryCommercial use: conditionalMultimodalCodingRAGAgentsLong contextVisionJSON / Tool use

Claude 3 Haiku is a legacy integration reference; keep it only while you identify a current replacement.

Use it for

  • Teams maintaining an existing integration
  • Workloads that can use a 200k context window
  • Buyers comparing 4 tracked provider routes

Do not use it for

  • New production launches
Specifications
Family
Claude 3
Released
2024-03-04
Context
200k
Parameters
20B
Architecture
Decoder Only
Knowledge cutoff
2023-08
Specialization
general
Openness
Proprietary
License
ProprietaryCommercial use: conditional
Weights
Not released
Code
Unknown
Training
Fine-tuned
Created by

Developing safe and ethical AI systems.

San Francisco, California, United States
Founded 2021
Website
Pricing
Output / 1M
$1.25
Input / 1M
$0.250

Cheapest of 7 routes · AWS Bedrock · cache read $0.025

About

Claude 3 Haiku is Anthropic's Claude 3 model with multimodal text and image input and an optional reasoning mode. It is deprecated (originally released 2024-03-04); use it only for reproducing earlier results or evaluating drift over time.

Claude 3 Haiku is a proprietary model in the Claude 3 family. The structured metadata tracks a 200k-token context window, multimodal input, reasoning, structured outputs, and code execution. This page tracks provider routes through AWS Bedrock, GCP Vertex AI, Salesforce Einstein Generative AI, and 4 more, with the cheapest tracked route listed at $0.25 input and $1.25 output per 1M tokens. Headline tracked benchmarks include Massive Multi-discipline Multimodal Understanding 50.2.

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

Coding

Included by capability and metadata signals in the decision map.

RAG

Included by capability and metadata signals in the decision map.

Agents

Included by capability and metadata signals in the decision map.

Provider price ladder

Compare all 7

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

ProviderInput / 1MOutput / 1MCacheRoute
AWS Bedrock$0.250$1.25read $0.025
Serverless
GCP Vertex AI$0.250$1.25-
Serverless
OpenRouter$0.250$1.25-
Serverless
Replicate API$0.250$1.25-
Serverless

Available via routers & gateways(15)

Capabilities

VisionMultimodalReasoningStructured OutputsCode Execution

Benchmark peer barsfor Vision

Benchmark scores(1)

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
Massive Multi-discipline Multimodal Understanding50.2Observed 2026-04-14Source

Migration checks

No linked migration route is available for this model yet.

API versions

claude-3-haiku-20240307

Frequently asked questions

What is the context window of Claude 3 Haiku?

Claude 3 Haiku has a context window of 200k tokens.

How much does Claude 3 Haiku cost?

Claude 3 Haiku is available at $0.25/1M input tokens through AWS Bedrock.

When was Claude 3 Haiku released?

Claude 3 Haiku was released on 2024-03-04.

Which providers offer Claude 3 Haiku?

Claude 3 Haiku is available from 7 providers: AWS Bedrock, GCP Vertex AI, Salesforce Einstein Generative AI, Anthropic, OpenRouter, Replicate API, Vercel AI Gateway.

What benchmarks has Claude 3 Haiku been tested on?

Claude 3 Haiku has been evaluated on 1 benchmark, including Massive Multi-discipline Multimodal Understanding.