All AI models · LLM benchmarks · Methodology

Anthropic

Claude Haiku 4.5

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

Model facts

Context window
2K tokens
Maximum output
64K tokens
Cheapest paid input
$0.14 per 1M tokens
Cheapest paid output
$0.71 per 1M tokens
Open weights
no
Providers
57

Capabilities and modalities

reasoning, tool calling, structured output, attachments, temperature control, text, image, pdf.

Artificial Analysis benchmarks

Compare this model on the full LLM benchmark leaderboard.

ConfigurationAAICodingMathOutput tokens/s
Reasoning29.943.983.7100.2
Non-reasoning24.1not measured39.093.1

Observed price history

  • 2026-08-24: $0.14 input / $0.71 output per 1M tokens

API providers

  • GitLab Duo (Agentic Chat) — model id duo-chat-haiku-4-5; free input / free output per 1M tokens; provider documentation
  • QiHang — model id claude-haiku-4-5-20251001; $0.14 input / $0.71 output per 1M tokens; provider documentation
  • OpenRouter (batch) — model id anthropic/claude-haiku-4.5:batch; $0.5 input / $2.5 output per 1M tokens; provider documentation
  • Xpersona (latest) — model id claude-haiku-4-5; $0.6 input / $3.7 output per 1M tokens; provider documentation
  • Poe — model id anthropic/claude-haiku-4.5; $0.85 input / $4.3 output per 1M tokens; provider documentation
  • Cortecs (latest) — model id claude-haiku-4-5; $0.996 input / $4.98 output per 1M tokens; provider documentation
  • 302.AI — model id claude-haiku-4-5; $1 input / $5 output per 1M tokens; provider documentation
  • Abacus — model id claude-haiku-4-5-20251001; $1 input / $5 output per 1M tokens; provider documentation
  • Amazon Bedrock — model id anthropic.claude-haiku-4-5-20251001-v1:0; $1 input / $5 output per 1M tokens; provider documentation
  • Amazon Bedrock (AU) — model id au.anthropic.claude-haiku-4-5-20251001-v1:0; $1 input / $5 output per 1M tokens; provider documentation
  • Amazon Bedrock (Global) — model id global.anthropic.claude-haiku-4-5-20251001-v1:0; $1 input / $5 output per 1M tokens; provider documentation
  • Amazon Bedrock (JP) — model id jp.anthropic.claude-haiku-4-5-20251001-v1:0; $1 input / $5 output per 1M tokens; provider documentation
  • Amazon Bedrock (US) — model id us.anthropic.claude-haiku-4-5-20251001-v1:0; $1 input / $5 output per 1M tokens; provider documentation
  • Anthropic (latest) — model id claude-haiku-4-5; $1 input / $5 output per 1M tokens; provider documentation
  • Anthropic — model id claude-haiku-4-5-20251001; $1 input / $5 output per 1M tokens; provider documentation
  • Azure — model id claude-haiku-4-5; $1 input / $5 output per 1M tokens; provider documentation
  • Azure Cognitive Services — model id claude-haiku-4-5; $1 input / $5 output per 1M tokens; provider documentation
  • Cloudflare AI Gateway (latest) — model id anthropic/claude-haiku-4.5; $1 input / $5 output per 1M tokens; provider documentation
  • CrossModel (latest) — model id anthropic/claude-haiku-4-5; $1 input / $5 output per 1M tokens; provider documentation
  • DaoXE — model id claude-haiku-4-5-20251001; $1 input / $5 output per 1M tokens; provider documentation
  • Databricks (latest) — model id databricks-claude-haiku-4-5; $1 input / $5 output per 1M tokens; provider documentation
  • DevPass (LLM Gateway) (latest) — model id claude-haiku-4-5; $1 input / $5 output per 1M tokens; provider documentation
  • DevPass (LLM Gateway) — model id claude-haiku-4-5-20251001; $1 input / $5 output per 1M tokens; provider documentation
  • DigitalOcean — model id anthropic-claude-4.5-haiku; $1 input / $5 output per 1M tokens; provider documentation
  • DigitalOcean (Anthropic) — model id anthropic-claude-haiku-4.5; $1 input / $5 output per 1M tokens; provider documentation
  • FreeModel — model id claude-haiku-4-5-20251001; $1 input / $5 output per 1M tokens; provider documentation
  • FrogBot — model id claude-haiku-4-5; $1 input / $5 output per 1M tokens; provider documentation
  • GitHub Copilot (latest) — model id claude-haiku-4.5; $1 input / $5 output per 1M tokens; provider documentation
  • Helicone — model id claude-4.5-haiku; $1 input / $5 output per 1M tokens; provider documentation
  • Impossibl (latest) — model id anthropic/claude-haiku-4-5; $1 input / $5 output per 1M tokens; provider documentation
  • Kilo Gateway (latest) — model id anthropic/claude-haiku-4.5; $1 input / $5 output per 1M tokens; provider documentation
  • LLM Gateway (Anthropic) — model id anthropic/claude-haiku-4-5; $1 input / $5 output per 1M tokens; provider documentation
  • LLM Gateway (AWS Bedrock) — model id aws-bedrock/claude-haiku-4-5; $1 input / $5 output per 1M tokens; provider documentation
  • LLM Gateway (Vertex AI (Anthropic)) — model id vertex-anthropic/claude-haiku-4-5; $1 input / $5 output per 1M tokens; provider documentation
  • NEAR AI Cloud (latest) — model id anthropic/claude-haiku-4-5; $1 input / $5 output per 1M tokens; provider documentation
  • NanoGPT — model id claude-haiku-4-5-20251001; $1 input / $5 output per 1M tokens; provider documentation
  • Neon (latest) — model id claude-haiku-4-5; $1 input / $5 output per 1M tokens; provider documentation
  • Ofox (latest) — model id anthropic/claude-haiku-4.5; $1 input / $5 output per 1M tokens; provider documentation
  • OpenCode Zen — model id claude-haiku-4-5; $1 input / $5 output per 1M tokens; provider documentation
  • OpenRouter (latest) — model id anthropic/claude-haiku-4.5; $1 input / $5 output per 1M tokens; provider documentation
  • Opper (latest) — model id anthropic/claude-haiku-4-5; $1 input / $5 output per 1M tokens; provider documentation
  • OrcaRouter (latest) — model id anthropic/claude-haiku-4.5; $1 input / $5 output per 1M tokens; provider documentation
  • Perplexity Agent — model id anthropic/claude-haiku-4-5; $1 input / $5 output per 1M tokens; provider documentation
  • Pioneer (latest) — model id claude-haiku-4-5; $1 input / $5 output per 1M tokens; provider documentation
  • Requesty (latest) — model id claude-haiku-4-5; $1 input / $5 output per 1M tokens; provider documentation
  • SAP AI Core — model id anthropic--claude-4.5-haiku; $1 input / $5 output per 1M tokens; provider documentation
  • Vercel AI Gateway — model id anthropic/claude-haiku-4.5; $1 input / $5 output per 1M tokens; provider documentation
  • Vertex — model id claude-haiku-4-5@20251001; $1 input / $5 output per 1M tokens; provider documentation
  • Vertex (Anthropic) — model id claude-haiku-4-5@20251001; $1 input / $5 output per 1M tokens; provider documentation
  • ZenMux — model id anthropic/claude-haiku-4.5; $1 input / $5 output per 1M tokens; provider documentation
  • Amazon Bedrock (EU) — model id eu.anthropic.claude-haiku-4-5-20251001-v1:0; $1.1 input / $5.5 output per 1M tokens; provider documentation
  • Requesty (latest) (EU) — model id claude-haiku-4-5@eu; $1.1 input / $5.5 output per 1M tokens; provider documentation
  • UnoRouter — model id claude-haiku-4-5-20251001; $1.2 input / $6 output per 1M tokens; provider documentation
  • AnyAPI (latest) — model id anthropic/claude-haiku-4-5; not published input / not published output per 1M tokens; provider documentation
  • Model Oracle AI (latest) — model id claude-haiku-4.5; not published input / not published output per 1M tokens; provider documentation
  • Qiniu — model id claude-4.5-haiku; not published input / not published output per 1M tokens; provider documentation
  • Snowflake Cortex (latest) — model id claude-haiku-4-5; not published input / not published output per 1M tokens; provider documentation