MODEL DIRECTORY
Anthropic Model Directory
Anthropic builds the Claude model family, focused on coding, agents and long-context work.
Website · USPublic models
22
With relay prices
22
Relay sites
117
Reasoning
18
Tool call
21
Structured output
0
Multimodal input
21
Text models
22
Image models
0
Video models
0
Audio models
0
Release range
2024-03-13 ~ 2026-10-07
22 models foundPrices in USD per 1M tokens; relay prices and ≈ are converted from CNY at today's rate
| Model | Provider | Type | Relays | Context | Max output | Input | Output | Capabilities | Price (input / output) | Details | ||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
Claude Haiku 5.5claude-haiku-5-5 | Anthropic | Text | 66 sites | 1M | 128K | Text: SupportedImage: SupportedPDF: SupportedFile: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: Not supported | 43.4 | Official$0.1 / $0.5Lowest$0.0018 / $0.009 | 2026-10-07 | |
Claude Haiku 5.5 is for high-volume, latency-sensitive work such as classification, extraction, and routing. The API id is claude-haiku-5-5. It accepts text and image input, with a 1M context window, up to 128K output tokens, and adaptive thinking at a default effort of medium. The overview lists pricing from $0.10/M input and $0.50/M output. The Cursor price table lists $0.10 input, $0.125 cache write, $0.01 cache read, and $0.50 output (verified 2026-10-09). Basics
Limits
InputText: SupportedImage: SupportedAudio: Not supportedVideo: Not supportedPDF: SupportedFile: Supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: SupportedTool call: SupportedStructured output: UnknownTemperature: Not supported Pricing
| ||||||||||||
Sonnet 5.5claude-sonnet-5-5 | Anthropic | Text | 93 sites | 1M | 128K | Text: SupportedImage: SupportedPDF: SupportedFile: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: Not supported | 56.0 | Official$2 / $10Lowest$0.0179 / $0.0897 | 2026-09-28 | |
Claude Sonnet 5.5 is the current Anthropic balance of speed and intelligence for everyday coding, agents, and knowledge work. The API id is claude-sonnet-5-5. It accepts text and image input, with a 1M context window, up to 128K output tokens, and adaptive thinking at a default effort of high. API pricing is $2/M input and $10/M output (verified 2026-10-09). Basics
Limits
InputText: SupportedImage: SupportedAudio: Not supportedVideo: Not supportedPDF: SupportedFile: Supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: SupportedTool call: SupportedStructured output: UnknownTemperature: Not supported Pricing
| ||||||||||||
Opus 5.5claude-opus-5-5 | Anthropic | Text | 98 sites | 1M | 128K | Text: SupportedImage: SupportedPDF: SupportedFile: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: Not supported | 57.6 | Official$4 / $20Lowest$0.0359 / $0.1794 | 2026-09-22 | |
Claude Opus 5.5 is Anthropic's model for long-running agentic coding and knowledge work, and the recommended starting point for most workloads. It accepts text and image input, with a 1M context window, up to 128K output tokens, and adaptive thinking always on. Best for long-horizon coding, knowledge work, and production tasks that need reliable tool use. Basics
Limits
InputText: SupportedImage: SupportedAudio: Not supportedVideo: Not supportedPDF: SupportedFile: Supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: SupportedTool call: SupportedStructured output: UnknownTemperature: Not supported Pricing
| ||||||||||||
Claude Fable 5.1claude-fable-5.1 | Anthropic | Text | 97 sites | - | - | - | Text: Supported | Reason: UnknownTools: UnknownJSON: UnknownTemperature: Unknown | 53.4 | OfficialNo priceLowest$0.0897 / $0.4485 | 2026-08 | |
Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows and tool use; 1M context, priced at $10/M input and $50/M output. Currently ranked #1 on all three Artificial Analysis indices: Intelligence 53.4, Coding 81.6, Agentic 58.0. Basics
Limits
InputText: Not supportedImage: Not supportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Unknown OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: UnknownTool call: UnknownStructured output: UnknownTemperature: Unknown Pricing
| ||||||||||||
Opus 5claude-opus-5 | Anthropic | Text | 102 sites | 1M | 128K | Text: SupportedImage: SupportedPDF: SupportedFile: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: Not supported | 50.8 | Official$5 / $25Lowest$0.0207 / $0.1035 | 2026-07-24 | |
Claude Opus 5 is Anthropic's next-generation Opus flagship for agentic coding, hard reasoning, and long-running workflows, with adaptive thinking enabled by default. Best for highly autonomous production work that needs reliable engineering output and deep analysis. Basics
Limits
InputText: SupportedImage: SupportedAudio: Not supportedVideo: Not supportedPDF: SupportedFile: Supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: SupportedTool call: SupportedStructured output: UnknownTemperature: Not supported Pricing
| ||||||||||||
Claude Sonnet 5claude-sonnet-5 | Anthropic | Text | 99 sites | 1M | 128K | Text: SupportedImage: SupportedPDF: SupportedFile: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: Not supported | 38.2 | Official$2 / $10Lowest$0.0124 / $0.0621 | 2026-06-30 | |
Claude Sonnet 5 balances speed and output quality, with adaptive thinking enabled by default and lower official pricing than Opus and Fable, plus about 200K context. Best for everyday development, code review, documentation, and medium-complexity tasks. Basics
Limits
InputText: SupportedImage: SupportedAudio: Not supportedVideo: Not supportedPDF: SupportedFile: Supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: SupportedTool call: SupportedStructured output: UnknownTemperature: Not supported Pricing
| ||||||||||||
Claude Fable 5claude-fable-5 | Anthropic | Text | 101 sites | 1M | 128K | Text: SupportedImage: SupportedPDF: SupportedFile: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: Not supported | 49.6 | Official$10 / $50Lowest$0.0897 / $0.4485 | 2026-06-09 | |
Claude Fable 5 is Anthropic's flagship for agentic coding, long-running workflows, and tool use, with adaptive thinking enabled by default. Best for highly autonomous tasks, complex orchestration, and reliable engineering output, and the baseline for comparing Fable 5.1. Basics
Limits
InputText: SupportedImage: SupportedAudio: Not supportedVideo: Not supportedPDF: SupportedFile: Supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: SupportedTool call: SupportedStructured output: UnknownTemperature: Not supported Pricing
| ||||||||||||
Claude Mythos 5claude-mythos-5 | Anthropic | Text | 3 sites | 1M | 128K | Text: SupportedImage: SupportedPDF: SupportedFile: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: Not supported | - | OfficialNo priceLowest$0.3065 / $1.53 | 2026-06-09 | |
Restricted Claude model for advanced cybersecurity and biology research workflows Basics
Limits
InputText: SupportedImage: SupportedAudio: Not supportedVideo: Not supportedPDF: SupportedFile: Supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: SupportedTool call: SupportedStructured output: UnknownTemperature: Not supported Pricing
| ||||||||||||
Claude Opus 4.8claude-opus-4-8 | Anthropic | Text | 108 sites | 1M | 128K | Text: SupportedImage: SupportedPDF: SupportedFile: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: Not supported | 41.8 | Official$5 / $25Lowest$0.0207 / $0.1035 | 2026-05-28 | |
Claude Opus 4.8 is the current Anthropic Opus flagship for hard reasoning, long-document analysis, and production-grade coding, with about 200K context. Best when output quality, complex problem solving, and deep analysis matter most. Basics
Limits
InputText: SupportedImage: SupportedAudio: Not supportedVideo: Not supportedPDF: SupportedFile: Supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: SupportedTool call: SupportedStructured output: UnknownTemperature: Not supported Pricing
| ||||||||||||
Claude Opus 4.7claude-opus-4-7 | Anthropic | Text | 98 sites | 1M | 128K | Text: SupportedImage: SupportedPDF: SupportedFile: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: Not supported | 40.7 | Official$5 / $25Lowest$0.0448 / $0.2242 | 2026-04-16 | |
Claude Opus 4.7 is the previous-generation Opus flagship, still suited to hard reasoning, complex coding, and long-document tasks, with about 200K context. Best for workflows already integrated with this version that need a stable continuation. Basics
Limits
InputText: SupportedImage: SupportedAudio: Not supportedVideo: Not supportedPDF: SupportedFile: Supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: SupportedTool call: SupportedStructured output: UnknownTemperature: Not supported Pricing
| ||||||||||||
Claude Sonnet 4.6claude-sonnet-4-6 | Anthropic | Text | 100 sites | 1M | 64K | Text: SupportedImage: SupportedPDF: SupportedFile: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: Supported | 30.1 | Official$3 / $15Lowest$0.0269 / $0.1345 | 2026-02-17 | |
Claude workhorse for coding agents, careful analysis, and production cost control Basics
Limits
InputText: SupportedImage: SupportedAudio: Not supportedVideo: Not supportedPDF: SupportedFile: Supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: SupportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Claude Opus 4.6claude-opus-4-6 | Anthropic | Text | 95 sites | 1M | 128K | Text: SupportedImage: SupportedPDF: SupportedFile: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: Supported | 31.9 | Official$5 / $25Lowest$0.0448 / $0.2242 | 2026-02-05 | |
Claude Opus 4.6 is an earlier Opus flagship for hard reasoning, complex coding, and long-document analysis, with about 200K context. Best for legacy workflows still tied to this version. Basics
Limits
InputText: SupportedImage: SupportedAudio: Not supportedVideo: Not supportedPDF: SupportedFile: Supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: SupportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Claude Opus 4.5claude-opus-4-5 | Anthropic | Text | 49 sites | 200K | 64K | Text: SupportedImage: SupportedPDF: SupportedFile: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: Supported | 29.1 | Official$5 / $25Lowest$0.0265 / $0.1327 | 2025-11-24 | |
Flagship Claude model for deep reasoning, coding, and long-horizon agents Basics
Limits
InputText: SupportedImage: SupportedAudio: Not supportedVideo: Not supportedPDF: SupportedFile: Supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: SupportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Claude Haiku 4.5claude-haiku-4-5 | Anthropic | Text | 80 sites | 200K | 64K | Text: SupportedImage: SupportedPDF: SupportedFile: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: Supported | - | Official$1 / $5Lowest$0.0052 / $0.0262 | 2025-10-15 | |
Fast Claude lane for lightweight agents, office tasks, and responsive chat Basics
Limits
InputText: SupportedImage: SupportedAudio: Not supportedVideo: Not supportedPDF: SupportedFile: Supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: SupportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Claude Sonnet 4.5claude-sonnet-4-5 | Anthropic | Text | 47 sites | 200K | 64K | Text: SupportedImage: SupportedPDF: SupportedFile: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: Supported | 20.7 | Official$3 / $15Lowest$0.0161 / $0.0804 | 2025-09-29 | |
Balanced Claude model for coding, analysis, agent workflows, and cost control Basics
Limits
InputText: SupportedImage: SupportedAudio: Not supportedVideo: Not supportedPDF: SupportedFile: Supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: SupportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Claude Opus 4.1claude-opus-4-1 | Anthropic | Text | 13 sites | 200K | 32K | Text: SupportedImage: SupportedPDF: SupportedFile: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: Supported | 22.8 | OfficialNo priceLowest$1.01 / $5.05 | 2025-08-05 | |
Flagship Claude model for deep reasoning, coding, and long-horizon agents Basics
Limits
InputText: SupportedImage: SupportedAudio: Not supportedVideo: Not supportedPDF: SupportedFile: Supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: SupportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Claude Opus 4claude-opus-4-0 | Anthropic | Text | 12 sites | 200K | 32K | Text: SupportedImage: SupportedPDF: SupportedFile: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: Supported | 20.6 | OfficialNo priceLowest$1.01 / $5.05 | 2025-05-22 | |
Flagship Claude model for deep reasoning, coding, and long-horizon agents Basics
Limits
InputText: SupportedImage: SupportedAudio: Not supportedVideo: Not supportedPDF: SupportedFile: Supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: SupportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Claude Sonnet 4claude-sonnet-4-0 | Anthropic | Text | 14 sites | 200K | 64K | Text: SupportedImage: SupportedPDF: SupportedFile: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: Supported | 18.9 | OfficialNo priceLowest$0.0538 / $0.2691 | 2025-05-22 | |
Balanced Claude model for coding, analysis, agent workflows, and cost control Basics
Limits
InputText: SupportedImage: SupportedAudio: Not supportedVideo: Not supportedPDF: SupportedFile: Supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: SupportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Claude Sonnet 3.7claude-3-7-sonnet-20250219 | Anthropic | Text | 7 sites | 200K | 64K | Text: SupportedImage: SupportedPDF: SupportedFile: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: Supported | 15.3 | OfficialNo priceLowest$0.2018 / $1.01 | 2025-02-19 | |
Balanced Claude model for coding, analysis, agent workflows, and cost control Basics
Limits
InputText: SupportedImage: SupportedAudio: Not supportedVideo: Not supportedPDF: SupportedFile: Supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: SupportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Claude Haiku 3.5claude-3-5-haiku-20241022 | Anthropic | Text | 5 sites | 200K | 8.2K | Text: SupportedImage: SupportedPDF: SupportedFile: Supported | Text: Supported | Reason: Not supportedTools: SupportedJSON: UnknownTemperature: Supported | 8.9 | OfficialNo priceLowest$0.0598 / $0.299 | 2024-10-22 | |
Fast Claude model for responsive assistance, classification, and lightweight agents Basics
Limits
InputText: SupportedImage: SupportedAudio: Not supportedVideo: Not supportedPDF: SupportedFile: Supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: Not supportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Claude Sonnet 3.5 v2claude-3-5-sonnet-20241022 | Anthropic | Text | 4 sites | 200K | 8.2K | Text: SupportedImage: SupportedPDF: SupportedFile: Supported | Text: Supported | Reason: Not supportedTools: SupportedJSON: UnknownTemperature: Supported | 7.9 | OfficialNo priceLowest$0.6727 / $3.36 | 2024-10-22 | |
Balanced Claude model for coding, analysis, agent workflows, and cost control Basics
Limits
InputText: SupportedImage: SupportedAudio: Not supportedVideo: Not supportedPDF: SupportedFile: Supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: Not supportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Claude Haiku 3claude-3-haiku-20240307 | Anthropic | Text | 5 sites | 200K | 4.1K | Text: SupportedImage: SupportedPDF: SupportedFile: Supported | Text: Supported | Reason: Not supportedTools: SupportedJSON: UnknownTemperature: Supported | 5.6 | OfficialNo priceLowest$0.0168 / $0.0841 | 2024-03-13 | |
Legacy model retained for compatibility with older integrations Basics
Limits
InputText: SupportedImage: SupportedAudio: Not supportedVideo: Not supportedPDF: SupportedFile: Supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: Not supportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Capabilities and limits come from public sources. “Unknown” means no reliable data yet, not “not supported”. Relay counts include only sites with a current public price, de-duplicated per site.
Data source: models.dev · OpenRouter
Intelligence scores come from the OpenRouter benchmark rankings (Intelligence Index); higher is smarter.