PROVIDER DIRECTORY · ONE KEY
Find the right provider for language, image, and video workloads—then move between models without rebuilding your integration.
Build reasoning agents, coding tools, and high-volume AI workflows with the Claude models currently available through LinkModel.
Anthropic develops the Claude family of language models. Opus targets the most capable reasoning and agent workloads, Sonnet balances intelligence, speed, and cost, and Haiku is optimized for fast, efficient tasks. LinkModel only presents a model as available when it appears in the live catalog.
Choose Opus for the most demanding reasoning and agent work, Sonnet for balanced production workloads, or Haiku for speed and efficiency. This catalog only shows Anthropic models currently listed on LinkModel.
11 models listed
Compare live Claude models for advanced reasoning, coding, tool use, long-running agents, and efficient high-volume language tasks.
Claude Opus4.8Anthropic's flagship LLM for agentic coding, multidisciplinary reasoning, and knowledge work, with sharper judgment and stronger honesty, a 1M-token context window, and fast mode—built for code migration, deep research, and legal/financial analysis.
Claude Sonnet4.6Anthropic's high-value mid-tier model approaching Opus-level performance on coding, computer use, and agent orchestration, with 1M context and adaptive thinking — built for scaled coding, desktop automation, and enterprise agents.
Claude Opus4.7Anthropic's flagship LLM excelling at long-horizon agents and coding, scoring 87.6% on SWE-bench Verified, with 1M context, adaptive thinking, and high-res vision — for complex coding and enterprise workflows.
Claude Opus4.6Anthropic's frontier flagship model built for deep reasoning, long-horizon agentic coding, and enterprise knowledge work — tops Terminal-Bench 2.0 and HLE with 1M context and adaptive thinking for the hardest tasks.
Claude Haiku5.5Anthropic's fast lightweight language model for classification, extraction, routing, and high-volume subagents, with million-token context, vision, and adaptive thinking.
Claude Sonnet5.5Anthropic's high-performance general model balancing speed and intelligence for everyday development, agent orchestration, and professional work with million-token context and vision.
Claude Opus5.5Anthropic's high-capability reasoning model for long-running coding agents and professional knowledge work, with million-token context, vision, and sustained tool use.
Claude Fable5.1Anthropic's frontier language model for long-running coding agents, multistep research, and complex document analysis in demanding knowledge workflows.
Claude Fable5Anthropic's frontier language model with a one-million-token context, long-running agentic coding, and multistep reasoning for complex research and knowledge work.
Claude Opus5Anthropic's high-capability language model for complex coding, long-running agents, and deep reasoning with a one-million-token context for enterprise workflows.
Claude Sonnet5Anthropic's balanced language model for agentic coding, tool use, and computer operation, with a one-million-token context for everyday development and enterprise automation.
Start with Claude Opus 4.8 for the hardest reasoning, coding, and long-running agent workloads; Claude Sonnet 4.6 for balanced production intelligence; or Claude Haiku 4.5 when speed and cost efficiency matter most. Recommendations only appear when the matching model is live in LinkModel's catalog.
The highest-capability Claude tier for difficult analysis, advanced software engineering, and long-running agent workflows.
A balanced Claude tier for production agents, coding, and general knowledge work where capability, latency, and cost all matter.
Use the live Claude family for complex reasoning, software development, agents, and efficient production automation from one account.
Build coding assistants and autonomous engineering workflows that can reason across large codebases, use tools, and complete multi-step tasks.
Analyze complex material, synthesize findings, and produce structured outputs with the live Claude tier that fits the required depth and latency.
Power assistants, classification, extraction, and tool-driven business processes while balancing response quality, speed, and cost.
Access supported Claude tiers alongside other leading providers while keeping credentials, usage, and billing in one workflow.
Use one LinkModel API key for the supported Opus, Sonnet, and Haiku models enabled in the live catalog.
Compare or combine Claude with other language models without maintaining a separate provider account and billing workflow.
Review usage and pay-as-you-go charges in one LinkModel account while selecting the Claude tier that fits each workload.
Use one LinkModel credential to select a live Claude model, send the matching request, and monitor usage from the same account.
Create a LinkModel API key and use it to authenticate requests for the Anthropic models enabled for your account.
Select an available Opus, Sonnet, or Haiku model and open its model page to confirm the current identifier, request schema, and pricing.
Submit the request, handle the response, and compare usage before moving the workflow into production.
FAQ
Model capabilities and selection guidance are reviewed against the official Anthropic sources listed here.
Editorial content reviewed: September 1, 2026
Anthropic and its model names belong to their respective owners. LinkModel is an independent API aggregation platform and does not imply a formal relationship.
![Claude Opus 4.5 API Pricing: Platform Cost Comparison [2026]](https://static.linkmodel.ai/blog-cover/cover-claude-opus-pricing.png)
Claude Opus API pricing in 2026 — from 4.5 through the current Opus 4.8 at $5/$25 per million tokens. Batch, caching, routing multipliers, and how platforms compare.
A practical Claude Sonnet 4.6 API guide — near-Opus quality at $3/$15 per million tokens. Pricing, strengths, and when Sonnet is the smarter, cheaper choice than Opus.
A practical Claude Haiku 4.5 API guide — Anthropic's fastest, cheapest model at $1/$5 per million tokens. When Haiku is enough, and when to escalate to Sonnet or Opus.
