Anthropic models
All 30 Anthropic models on OpenDunes, priced in Algerian Dinars.
30 models
#1 for reasoning · Claude Opus 5.5 reads text, images and files, keeps about 1,000 pages in mind at once, and replies up to about 128 pages, with an effort setting as the main dial between depth and speed. Give it edits that span a large codebase, bug hunts, financial or scientific analysis, and charts, diagrams or screenshots full of detail. It needs fewer steps and less output than Opus 5 for the same job and reports back in plainer language. For harder reasoning, Anthropic points to Fable 5.1; for lighter work, Sonnet 5.5.
Haiku 5.5 is the quick, small Claude for high-volume work: summarising, sorting, pulling out details, routing, driving a web browser and acting as a helper agent. It reads text, images and files, keeps about 1,000 pages in mind, replies up to about 128 pages, and has an effort setting while deciding for itself how long to think. It succeeds Haiku 4.5, with better coding and computer use.
#2 for interface design · Claude Sonnet 5.5 reads text, images and files, keeps about 1,000 pages in mind at once, and replies up to about 128 pages, with thinking always on and an effort setting as the main dial. It is Anthropic's pick for well-defined daily jobs: shipping a feature, fixing a bug, or turning notes into finished reports, slide decks and spreadsheets. Lower effort keeps it responsive in agents that work step by step. For high-volume sorting and extraction, Haiku 5.5 is faster; for long, hard projects, Opus 5.5.
#8 for games · Claude Sonnet 5 reads text, images and files, keeps about 1,000 pages in mind at once, and replies up to about 128 pages. It decides for itself how long to think, and you set the effort from low to extra high. Use it for coding, agents that work through a task on their own, and professional work such as documents and analysis; it stops some dangerous requests as they happen.
#1 for coding · Claude Fable 5.1 reads text, images and files, keeps about 1,000 pages in mind at once, and replies in text up to about 128 pages. Give it demanding coding work, big changes across a whole codebase, interface and visual code, or finance and analysis work that runs many steps. Its plans and summaries come out shorter than Fable 5's. Anthropic advises comparing it with Opus 5.5 on hard reasoning; Opus 5.5 is the default start, and Sonnet 5.5 suits everyday jobs.
#1 for mobile apps · Claude Opus 5 reads text, images and files, keeps about 1,000 pages in mind at once, and replies up to about 128 pages. Use it to take a software task from start to finish, review code and hunt bugs, read charts and documents, produce office files, and direct several helper agents at once, following instructions steadily through long runs that use tools.
Claude Sonnet 4.6 reads text, images and files, keeps about 1,000 pages in mind at once, and replies up to about 128 pages. Use it for step-by-step development, finding your way around a complex codebase, project management that remembers earlier steps, polished documents, and driving a web browser to test a web app or automate a workflow.
#1 for slide decks · Claude Opus 4.8 reads text, images and files, keeps about 1,000 pages in mind at once, and replies up to about 128 pages. It suits agents that work mostly on their own, and jobs that lean on memory, where the model must stay coherent across a long session: complex coding, debugging across stages, running a project, documents, presentations and data analysis.
Claude Sonnet 4.5 reads text, images and files, keeps about 1,000 pages in mind at once, and replies up to about 64 pages. It is made for coding and for agents that work for a long time, tracking progress across sessions and using several tools at once, and it is used for software engineering, security work, financial analysis and research. It is the older Sonnet.
Claude Haiku 4.5 reads text, images and files, up to about 200 pages, and replies up to about 64 pages, with thinking time you can set. It scored over 73 percent on a widely used coding test, which makes it a quick coding worker for helper agents and tasks run side by side, as well as for real-time chat. It is the older Haiku.
Claude Opus 4.6 reads text, images and files, keeps about 1,000 pages in mind at once, and replies up to about 128 pages. Give it work that unfolds over many steps: large codebases, complex rewrites, multi-step debugging, migration planning and long documents that must stay coherent from start to finish. For quick everyday jobs, Sonnet 5.5 answers faster.
Haiku 5.5 is the quick, small Claude for high-volume work: summarising, sorting, pulling out details, routing, driving a web browser and acting as a helper agent. It reads text, images and files, keeps about 1,000 pages in mind, replies up to about 128 pages, and has an effort setting while deciding for itself how long to think. It succeeds Haiku 4.5, with better coding and computer use.
#1 for slide decks · Autonomous coding and knowledge work on long, ambiguous, multi-step problems that would take a person hours or weeks, checking its own work through verification loops instead of needing someone to check in every few steps
Claude Opus 4.7 reads text, images and files, keeps about 1,000 pages in mind at once, and replies up to about 128 pages. It is aimed at agents that run unattended for hours: working through a big codebase, debugging across several stages, running a whole project, and also drafting documents, building presentations and analysing data without losing the thread. It builds on Opus 4.6.
Claude Opus 4.5 reads text, images and files, up to about 200 pages, and replies up to about 64 pages, with settings for effort and wordiness that trade depth against length. Use it for complex software engineering, research that runs on its own, planning in many steps and automating spreadsheets or a web browser, where it resists hidden instructions planted in what it reads better than earlier Opus models.
#2 for interface design · Claude Sonnet 5.5 reads text, images and files, keeps about 1,000 pages in mind at once, and replies up to about 128 pages, with thinking always on and an effort setting as the main dial. It is Anthropic's pick for well-defined daily jobs: shipping a feature, fixing a bug, or turning notes into finished reports, slide decks and spreadsheets. Lower effort keeps it responsive in agents that work step by step. For high-volume sorting and extraction, Haiku 5.5 is faster; for long, hard projects, Opus 5.5.
#1 for reasoning · Claude Opus 5.5 reads text, images and files, keeps about 1,000 pages in mind at once, and replies up to about 128 pages, with an effort setting as the main dial between depth and speed. Give it edits that span a large codebase, bug hunts, financial or scientific analysis, and charts, diagrams or screenshots full of detail. It needs fewer steps and less output than Opus 5 for the same job and reports back in plainer language. For harder reasoning, Anthropic points to Fable 5.1; for lighter work, Sonnet 5.5.
Claude Opus 4.1 reads text, images and files, up to about 200 pages, and replies up to about 32 pages. It scored 74.5% in a widely used coding test and is good at changes across many files and precise debugging, and it also handles research and data analysis using the tools you connect, with a thinking allowance of up to about 64 pages. It is an older Opus.
#1 for coding · Claude Fable 5.1 reads text, images and files, keeps about 1,000 pages in mind at once, and replies in text up to about 128 pages. Give it demanding coding work, big changes across a whole codebase, interface and visual code, or finance and analysis work that runs many steps. Its plans and summaries come out shorter than Fable 5's. Anthropic advises comparing it with Opus 5.5 on hard reasoning; Opus 5.5 is the default start, and Sonnet 5.5 suits everyday jobs.
#1 for mobile apps · Claude Opus 5 reads text, images and files, keeps about 1,000 pages in mind at once, and replies up to about 128 pages. Use it to take a software task from start to finish, review code and hunt bugs, read charts and documents, produce office files, and direct several helper agents at once, following instructions steadily through long runs that use tools.
Claude Sonnet 4.5 reads text, images and files, keeps about 1,000 pages in mind at once, and replies up to about 64 pages. It is made for coding and for agents that work for a long time, tracking progress across sessions and using several tools at once, and it is used for software engineering, security work, financial analysis and research. It is the older Sonnet.
Claude Haiku 4.5 reads text, images and files, up to about 200 pages, and replies up to about 64 pages, with thinking time you can set. It scored over 73 percent on a widely used coding test, which makes it a quick coding worker for helper agents and tasks run side by side, as well as for real-time chat. It is the older Haiku.
#8 for games · Claude Sonnet 5 reads text, images and files, keeps about 1,000 pages in mind at once, and replies up to about 128 pages. It decides for itself how long to think, and you set the effort from low to extra high. Use it for coding, agents that work through a task on their own, and professional work such as documents and analysis; it stops some dangerous requests as they happen.
Claude Opus 4.6 reads text, images and files, keeps about 1,000 pages in mind at once, and replies up to about 128 pages. Give it work that unfolds over many steps: large codebases, complex rewrites, multi-step debugging, migration planning and long documents that must stay coherent from start to finish. For quick everyday jobs, Sonnet 5.5 answers faster.
Claude Opus 4.5 reads text, images and files, up to about 200 pages, and replies up to about 64 pages, with settings for effort and wordiness that trade depth against length. Use it for complex software engineering, research that runs on its own, planning in many steps and automating spreadsheets or a web browser, where it resists hidden instructions planted in what it reads better than earlier Opus models.
Claude Opus 4.7 reads text, images and files, keeps about 1,000 pages in mind at once, and replies up to about 128 pages. It is aimed at agents that run unattended for hours: working through a big codebase, debugging across several stages, running a whole project, and also drafting documents, building presentations and analysing data without losing the thread. It builds on Opus 4.6.
#1 for slide decks · Claude Opus 4.8 reads text, images and files, keeps about 1,000 pages in mind at once, and replies up to about 128 pages. It suits agents that work mostly on their own, and jobs that lean on memory, where the model must stay coherent across a long session: complex coding, debugging across stages, running a project, documents, presentations and data analysis.
Claude Sonnet 4.6 reads text, images and files, keeps about 1,000 pages in mind at once, and replies up to about 128 pages. Use it for step-by-step development, finding your way around a complex codebase, project management that remembers earlier steps, polished documents, and driving a web browser to test a web app or automate a workflow.
#1 for slide decks · Autonomous coding and knowledge work on long, ambiguous, multi-step problems that would take a person hours or weeks, checking its own work through verification loops instead of needing someone to check in every few steps
Claude Opus 4.1 reads text, images and files, up to about 200 pages, and replies up to about 32 pages. It scored 74.5% in a widely used coding test and is good at changes across many files and precise debugging, and it also handles research and data analysis using the tools you connect, with a thinking allowance of up to about 64 pages. It is an older Opus.