GitLab Transcend - Intelligent orchestration
Mini toolsClaude models
Browse all models from this model family.
ID
Model
Company
Type
Primary task
Open source
-
By AnthropicClaude Opus 4.8 is Anthropic's new flagship model, released May 28, 2026. It improves on Opus 4.7 with stronger coding, more honest self-assessment, and a faster, cheaper fast mode, at the same standard pricing. New features include user-controlled effort levels and Dynamic Workflows for parallel subagents.NewMultimodalReleased 7d ago
-
By AnthropicClaude Opus 4.7 is Anthropic’s latest generally available frontier model, tuned for advanced software engineering, long-running autonomous tasks, stronger instruction following, and better high-resolution vision. It is positioned as a clear upgrade over Opus 4.6, especially for difficult coding work, while keeping the same pricing.NewMultimodalReleased 1mo ago
-
By AnthropicAnthropic’s Sonnet 4.6 model for scaled production and complex tasks across coding, agents, and professional workflows.TextReleased 3mo ago
-
By AnthropicClaude Opus 4.6 is Anthropic’s newest frontier model, built for complex reasoning, large-scale coding and multi-agent orchestration, with major gains in cybersecurity bug-finding and long-horizon enterprise workflows over Opus 4.5.MultimodalReleased 3mo ago
-
By AnthropicClaude Opus 4.5 is Anthropic’s top model for hard reasoning, coding, and long-horizon agents. It improves math, vision, tool use, and safety compared with earlier Claude models.MultimodalReleased 6mo ago
-
By AnthropicClaude Haiku 4.5 is Anthropic’s fast, cost-efficient model. It handles everyday reasoning, coding, and multimodal inputs with long context, tool and function calling, and reliable JSON output, making it a strong default for high-throughput apps.TextReleased 7mo ago
-
By AnthropicClaude Sonnet 4.5 is Anthropic’s balanced, production-ready model—faster than Opus while delivering strong reasoning, coding, and multimodal (text + image) skills. It supports long context, tool/function calling, and schema-true JSON, making it a dependable default for RAG copilots and agents.TextReleased 8mo ago
-
By AnthropicClaude Opus 4.1 (Thinking) is Anthropic’s most capable reasoning model in the Claude 4.1 lineup. It emphasizes deep chain-of-thought analysis, long-context handling, and accurate step-by-step reasoning, making it ideal for complex coding, math, and enterprise-grade RAG/agent workflows.TextReleased 10mo ago
-
By AnthropicClaude Sonnet 4 (Extended Thinking) is the long-deliberation mode of Sonnet 4. It spends extra tokens “thinking” before answering, boosting accuracy on hard reasoning, math, and coding while keeping the same strengths—long context, tool/function calling, JSON outputs, and multimodal text-plus-image understanding.TextReleased 1y ago
-
By AnthropicClaude Opus 4 is Anthropic’s flagship Claude 4 model for deep reasoning and advanced coding. It handles text & image inputs, supports a 200K-token context with up to 32K output tokens, and is available via the Anthropic API, AWS Bedrock, and Google Cloud Vertex AI.TextReleased 1y ago
-
By AnthropicClaude Sonnet 4 improves on Claude Sonnet 3.7 across a variety of areas, especially coding. It offers frontier performance that’s practical for most AI use cases, including user-facing AI assistants and high-volume tasks.TextReleased 1y ago
-
By AnthropicClaude 3.7 Sonnet is Anthropic’s hybrid reasoning model. It can deliver near-instant replies for simple prompts, or switch to “extended thinking” mode for deeper, step-by-step reasoning. Strong improvements in coding, front-end work, math, and instruction following.TextReleased 1y ago
-
By AnthropicClaude 3.5 Haiku is Anthropic’s fast, low-cost Claude 3.5 model for everyday builds—strong instruction following, coding, and multimodal (text + image) reasoning with tool/function calling and long-context support. Ideal for high-throughput apps, agents, and RAG workflows.TextReleased 1y ago
-
By AnthropicClaude 3.5 Sonnet is Anthropic’s balanced model—fast enough for everyday apps yet capable of solid reasoning, coding, and multimodal (text + image) work. It supports long context, tool/function calling, and reliable JSON outputs, making it a strong choice for production copilots and RAG.TextReleased 1y ago
-
By AnthropicClaude 3 Haiku is Anthropic’s fast, low-cost Claude 3 model for everyday apps—strong instruction following, coding, and vision (text + image) with tool/function calling and a long context (around 200K). Ideal for high-throughput agents and RAG.TextReleased 2y ago
-
TextReleased 2y ago
-
TextReleased 2y ago
-
TextReleased 3y ago
-
By AnthropicClaude is Anthropic’s early assistant focused on being helpful, harmless, and honest. It follows instructions safely, writes clearly, and handles multi-turn dialogue for chat, drafting, and Q&A.TextReleased 3y ago
