The Open-Source AI Stack
RSS
All models

Models · claude

Claude 3 Haiku

Proprietary Anthropic · 2024-03-13 · Proprietary

The fast, low-cost tier of the Claude 3 family. Anthropic claimed throughput of roughly 21K tokens per second on prompts under 32K tokens at launch, and the $0.25 input / $1.25 output price point made it competitive with GPT-3.5-class small models while carrying the 200K context and vision capabilities of its larger siblings.

Cost

$0.25 / Mtok input
$1.25 / Mtok output

Anthropic API · as of 2026-05-21

source ↗

Speed

0 tok/sec output
0 ms TTFT

· as of 2026-05-21

source ↗

Architecture

tokens in Embedding vocab not disclosed × N layers Architecture not disclosed (proprietary or undocumented) Output projection tokens out
Schema-generated from data/models.yaml. Every label is auditable against the model's sources.

Specs

Architecture
unknown
Total params
not disclosed
Active params
not disclosed
Context window
200K tokens
Attention
unknown
Position encoding
unknown
Post-training
rlhf, constitutional
OSI-approved
no
Data released
no
Training code
not released

Benchmarks

Each score carries the date it was published; we never infer or interpolate missing scores.

General reasoning

GPQA-Diamond 37.4 as of 2026-05-21 source ↗

Code

LiveCodeBench 15.4 as of 2026-05-21 source ↗

Math

MATH 39.4 as of 2026-05-21 source ↗
AIME 2024 1.0 as of 2026-05-21 source ↗

Available quantizations

None. The weights are not distributed, so there are no public quantizations.

Notable innovations

  • · Tier 1 small-model pricing with frontier-family context window
  • · Vision input at Haiku price tier

Lineage

Direct predecessor to Claude 3.5 Haiku.

Derivatives

Sources