A

Anthropic

Major Foundation Lab28 Canonical Models

Anthropic foundation models, inference API endpoints, and pricing.

Official Provider Docs
•Package: @ai-sdk/anthropic•Env Key: ANTHROPIC_API_KEY

Models by Anthropic

Specifications, context windows, and pricing for Anthropic models

28 models
Claude Opus 4.7
anthropic/claude-opus-4-7•Anthropic
1M ctx

Stronger Opus tier for advanced software work and high-stakes reasoning

128K out maxVisionPDFSWE-Bench Pro: 64.3 resolve rate
In: $5.00 • Out: $25.00
Anthropic
Claude Opus 4.6
anthropic/claude-opus-4-6•Anthropic
1M ctx

High-end Claude for difficult coding, planning, and slower expert reasoning

128K out maxVisionPDFSWE-Bench Pro: 51.9 resolve rate
In: $5.00 • Out: $25.00
Anthropic
Claude Sonnet 5
anthropic/claude-sonnet-5•Anthropic
1M ctx

Everyday Claude agent model for coding, planning, browsing, and general work

128K out maxVisionPDFSWE-Bench Verified: 85.2 resolved
In: $2.00 • Out: $10.00
Anthropic
Claude Haiku 5.5
anthropic/claude-haiku-5-5•Anthropic
1M ctx

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

128K out maxVisionPDFGDPval-AA: 1620 Elo
In: $0.10 • Out: $0.50
Anthropic
Claude Opus 5
anthropic/claude-opus-5•Anthropic
1M ctx

Strongest Claude Opus model for coding, agents, and professional work

128K out maxVisionPDFSWE-Bench Verified: 96 resolved
In: $5.00 • Out: $25.00
Anthropic
Claude Opus 5.5
anthropic/claude-opus-5-5•Anthropic
1M ctx

Claude model for long-running agentic coding and knowledge work

128K out maxVisionPDFTerminal-Bench: 66.4 score
In: $4.00 • Out: $20.00
Anthropic
Claude Opus 4.8
anthropic/claude-opus-4-8•Anthropic
1M ctx

Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents

128K out maxVisionPDFSWE-Bench Pro: 69.2 resolve rate
In: $5.00 • Out: $25.00
Anthropic
Claude Mythos 5
anthropic/claude-mythos-5•Anthropic
1M ctx

Restricted Claude model for advanced cybersecurity and biology research workflows

128K out maxVisionPDF
In: $10.00 • Out: $50.00
Anthropic
Claude Sonnet 4.6
anthropic/claude-sonnet-4-6•Anthropic
1M ctx

Claude workhorse for coding agents, careful analysis, and production cost control

64K out maxVisionPDFSWE-Atlas Codebase QnA: 31.2 score
In: $3.00 • Out: $15.00
Anthropic
Claude Fable 5.1
anthropic/claude-fable-5-1•Anthropic
1M ctx

Claude model for demanding reasoning and long-horizon agentic work

128K out maxVisionPDFTerminal-Bench-Science: 52.6 score
In: $10.00 • Out: $50.00
Anthropic
Claude Sonnet 5.5
anthropic/claude-sonnet-5-5•Anthropic
1M ctx

Fast Claude model for everyday coding, agents, and knowledge work

128K out maxVisionPDFTerminal-Bench: 70.6 score
In: $2.00 • Out: $10.00
Anthropic
Claude Fable 5
anthropic/claude-fable-5•Anthropic
1M ctx

Claude model for creative writing, analysis, and controlled agent workflows

128K out maxVisionPDFSWE-Bench Pro: 80.3 resolve rate
In: $10.00 • Out: $50.00
Anthropic
Claude Opus 4.5 (latest)
anthropic/claude-opus-4-5•Anthropic
200K ctx

Flagship Claude model for deep reasoning, coding, and long-horizon agents

64K out maxVisionPDF
In: $5.00 • Out: $25.00
Anthropic
Claude Opus 4.1
anthropic/claude-opus-4-1-20250805•Anthropic
200K ctx

Flagship Claude model for deep reasoning, coding, and long-horizon agents

32K out maxVisionPDF
In: $15.00 • Out: $75.00
Anthropic
Claude Sonnet 4
anthropic/claude-sonnet-4-20250514•Anthropic
200K ctx

Balanced Claude model for coding, analysis, agent workflows, and cost control

64K out maxVisionPDFAider Polyglot: 61.3 percent correct
In: $3.00 • Out: $15.00
Anthropic
Claude Opus 4.1 (latest)
anthropic/claude-opus-4-1•Anthropic
200K ctx

Flagship Claude model for deep reasoning, coding, and long-horizon agents

32K out maxVisionPDF
In: $15.00 • Out: $75.00
Anthropic
Claude Sonnet 4.5 (latest)
anthropic/claude-sonnet-4-5•Anthropic
200K ctx

Balanced Claude model for coding, analysis, agent workflows, and cost control

64K out maxVisionPDFSWE-Bench Pro: 43.6 resolve rate
In: $3.00 • Out: $15.00
Anthropic
Claude Haiku 3.5
anthropic/claude-3-5-haiku-20241022•Anthropic
200K ctx

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

8.2K out maxVisionPDFAider Polyglot: 28 percent correct
In: $0.80 • Out: $4.00
Anthropic
Claude Sonnet 4 (latest)
anthropic/claude-sonnet-4-0•Anthropic
200K ctx

Balanced Claude model for coding, analysis, agent workflows, and cost control

64K out maxVisionPDFAider Polyglot: 61.3 percent correct
In: Free • Out: Free
Anthropic
Claude Opus 4.5
anthropic/claude-opus-4-5-20251101•Anthropic
200K ctx

Flagship Claude model for deep reasoning, coding, and long-horizon agents

64K out maxVisionPDFSWE-Bench Pro: 45.89 resolve rate
In: $5.00 • Out: $25.00
Anthropic
Claude Opus 4
anthropic/claude-opus-4-20250514•Anthropic
200K ctx

Flagship Claude model for deep reasoning, coding, and long-horizon agents

32K out maxVisionPDFAider Polyglot: 72 percent correct
In: $15.00 • Out: $75.00
Anthropic
Claude Haiku 3
anthropic/claude-3-haiku-20240307•Anthropic
200K ctx

Legacy model retained for compatibility with older integrations

4.1K out maxVisionPDF
In: $0.25 • Out: $1.25
Anthropic
Claude Haiku 4.5 (latest)
anthropic/claude-haiku-4-5•Anthropic
200K ctx

Fast Claude lane for lightweight agents, office tasks, and responsive chat

64K out maxVisionPDFSWE-Bench Pro: 39.45 resolve rate
In: $1.00 • Out: $5.00
Anthropic
Claude Sonnet 3.5 v2
anthropic/claude-3-5-sonnet-20241022•Anthropic
200K ctx

Balanced Claude model for coding, analysis, agent workflows, and cost control

8.2K out maxVisionPDFAider Polyglot: 51.6 percent correct
In: Free • Out: Free
Anthropic
Claude Opus 4 (latest)
anthropic/claude-opus-4-0•Anthropic
200K ctx

Flagship Claude model for deep reasoning, coding, and long-horizon agents

32K out maxVisionPDFAider Polyglot: 72 percent correct
In: Free • Out: Free
Anthropic
Claude Sonnet 3.7
anthropic/claude-3-7-sonnet-20250219•Anthropic
200K ctx

Balanced Claude model for coding, analysis, agent workflows, and cost control

64K out maxVisionPDFAider Polyglot: 64.9 percent correct
In: $3.00 • Out: $15.00
Anthropic
Claude Haiku 4.5
anthropic/claude-haiku-4-5-20251001•Anthropic
200K ctx

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

64K out maxVisionPDF
In: $1.00 • Out: $5.00
Anthropic
Claude Sonnet 4.5
anthropic/claude-sonnet-4-5-20250929•Anthropic
200K ctx

Balanced Claude model for coding, analysis, agent workflows, and cost control

64K out maxVisionPDF
In: $3.00 • Out: $15.00
Anthropic