modelgrep

Small & Fast Anthropic Models

Quick answer · Updated June 2026

The small, fast Anthropic model is Claude Haiku 4.5 — the efficient tier at 82 tokens/sec and $1.00 per million input tokens. It trades a few points of raw intelligence for speed and cost, the right call for high-volume, latency-sensitive work. Claude 3 Haiku (68 t/s) and Claude 3.5 Haiku (35 t/s) round out the top three.

82 t/sSpeed
31.0Intelligence
$1.00Input /M
200KContext

Compact, efficient models — the small/mini/flash/haiku tier — ranked by output speed. These trade a little raw intelligence for low cost and high throughput, which is the right tradeoff for chat, classification, extraction and other high-volume work.

  1. 1A
    claude-haiku-4.5
    ReasoningToolsJSON+131.0 intel · $1.00/M · 521ms ttft
    82 t/s
    Speed
  2. 2A
    claude-3-haiku
    ToolsVision12.3 intel · $0.250/M · 542ms ttft
    68 t/s
    Speed
  3. 3A
    claude-3.5-haiku
    ToolsVision18.7 intel · $0.800/M · 832ms ttft
    35 t/s
    Speed

Frequently asked

What is the smallest, fastest Anthropic model?

The small, fast Anthropic model is Claude Haiku 4.5 — the efficient tier at 82 tokens/sec and $1.00 per million input tokens. It trades a few points of raw intelligence for speed and cost, the right call for high-volume, latency-sensitive work. Claude 3 Haiku (68 t/s) and Claude 3.5 Haiku (35 t/s) round out the top three.

What's a good alternative to Claude Haiku 4.5?

Claude 3 Haiku (68 t/s) is the closest alternative on this metric, followed by Claude 3.5 Haiku (35 t/s). See the full ranking above for the tradeoffs.

How many Anthropic models are there?

modelgrep tracks 16 Anthropic models with live benchmarks, speed, latency and per-provider pricing, led on intelligence by Claude Fable 5. 3 of them qualify for this ranking.

More Anthropic rankings

All rankings