The Open-Source AI Stack
RSS
All models

Models · claude

Claude Opus 4

Proprietary Anthropic · 2025-05-22 · Proprietary

Flagship of the May 22 2025 Claude 4 launch. Returned to the Opus name after the Claude 3.5 and 3.7 lines skipped Opus entirely. Held the same $15 / $75 input/output price ceiling as Claude 3 Opus, and like Sonnet 4 carried hybrid reasoning with extended thinking and parallel tool execution.

Cost

$15.00 / Mtok input
$75.00 / Mtok output

Anthropic API · as of 2026-05-21

source ↗

Speed

38.1 tok/sec output
1652 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
not verified
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

MMLU-Pro 86.0 as of 2026-05-21 source ↗
GPQA-Diamond 74.9 as of 2025-05-22 source ↗

Code

SWE-Bench Verified 72.5 as of 2025-05-22 source ↗
LiveCodeBench 54.2 as of 2026-05-21 source ↗

Math

MATH 94.1 as of 2026-05-21 source ↗
AIME 2024 56.3 as of 2026-05-21 source ↗
AIME 2025 33.9 as of 2025-05-22 source ↗

Available quantizations

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

Notable innovations

  • · Flagship hybrid-reasoning Opus return
  • · Extended thinking with tool use
  • · Memory features for local file access during long tasks

Lineage

Successor flagship Opus after the 3.5 and 3.7 lines shipped Sonnet-only at the top end.

Derived from

Claude 3 Opus 2024-03-04

Sources