Retired on Feb 19, 2026.
No longer served on the endpoint we price — the figures below are kept for historical
reference only. Replaced by Claude Haiku 4.5.
Availability: Retired from the Claude API 2026-02-19. Partner platforms (Bedrock, Vertex) set their own schedules and may still serve it.
Today's price · per 1M tokens
Input
$0.800
per 1M tokens
Output
$4.00
per 1M tokens
Blended
$2.40
avg of input & output $/1M
Cached input
$0.080
10% of input — prompt caching
Source: official Anthropic pricing · read Jun 25, 2026
MODELPRICEWATCH.COM · 2026-08-01
Overview
Retired on Anthropic API (still available via Bedrock/Vertex). $0.80/$4 per 1M tokens.
Capabilities
struck through = not supportedInput 2/5
Text ✓
Image ✓
Audio
Video
PDF
Output 1/5
Text ✓
Image
Audio
Video
Embedding
Features 3/9
Prompt caching ✓
Reasoning
Coding
Fast inference
Long context ✓
Open weights
Multimodal ✓
Web search
Realtime
Benchmark performance
accuracy % · higher is betterAvg benchmark score78.8%
Perf per $/Mtok32.8
MMMLU
81%
HumanEval
84.1%
MATH 500
71.2%
How it stacks up
- Ranks #15 of 68 benchmarked models by average score
- Ranks #36 of 133 comparably-measured models by percentile score, across 3 independent measurements
- Ranks #60 of 133 comparably-tested models by normalized performance per dollar
- Strongest at HumanEval — 84.1%, #13 of 45
Source: Kaggle LLM Benchmark Wars 2025-2026 · updated Mar 2, 2026 · See full rankings →
Specifications
- Provider
- Anthropic
- Context window
- 200K tokens
- Modality
- text, image
- Parameters
- Proprietary
- Open source
- No — proprietary
- Released
- Oct 15, 2024
- Status
- Retired ended Feb 19, 2026
- Last updated
- Jun 25, 2026
- Tags
Availability verified: Jul 25, 2026 — per Anthropic's own deprecation notice