Models
81 models from 12 providers, all included in every plan — every one of them a click away inside EVA.
Anthropic
Claude Fable 5.1
Anthropic's most capable generally available Claude model for demanding reasoning, long-running agentic coding, research, and complex knowledge work.
Claude Fable 5
Anthropic generally available Claude Fable 5 model for demanding reasoning, long-horizon agentic work, coding, and multimodal analysis.
Claude Opus 5
Anthropic's flagship model for complex agentic coding, enterprise analysis, and long-horizon multi-step work.
Claude Sonnet 5
Anthropic frontier Sonnet model for coding, agents, tool use, and professional knowledge work with adaptive thinking and a 1M-token context window.
Claude Opus 4.8
Anthropic's latest Claude Opus model for frontier coding, agentic workflows, complex reasoning, and long-context professional work.
Claude Opus 4.7
Anthropic's latest and most capable model with industry-leading intelligence for complex reasoning and autonomous task execution.
Claude Opus 4.6
Anthropic's flagship Claude 4.6 Opus model delivering top-tier intelligence for the most demanding tasks.
Claude Sonnet 4.6
Anthropic's advanced Claude 4.6 Sonnet model optimized for coding, complex reasoning, and agentic task execution.
Claude Opus 4.5
Anthropic's most advanced flagship model in the Claude 4.5 family.
Claude Sonnet 4.5
Anthropic's most advanced Claude 4.5 model designed for coding, agentic AI workflows, and complex reasoning.
Claude Haiku 4.5
Anthropic's smallest and fastest model in the Claude 4.5 lineup, optimized for low cost, low latency, and real-time responsiveness, while delivering near-frontier performance on coding, agentic workflows, and extended reasoning tasks.
DeepSeek
DeepSeek V4 Pro 0813
DeepSeek's long-context V4 Pro snapshot for advanced reasoning, coding, and complex automation.
DeepSeek V4 Flash 0731
DeepSeek's efficient V4 Flash snapshot for fast reasoning, coding, and long-context tasks.
DeepSeek V4 Flash
DeepSeek's fast and ultra cost-efficient flagship with 1M context and optional thinking mode — the most affordable frontier-class model available.
DeepSeek V4 Pro
DeepSeek's most capable V4 model with frontier-level reasoning, 1M context, and deep optimization for agentic coding workflows.
GLM (z.ai)
GLM-5.3 Flash
Z.ai's efficient native multimodal million-context model for coding and long-horizon agent tasks.
GLM-5.3
Z.ai's million-context reasoning model for complex software engineering and long-horizon agent tasks.
GLM-5.2
Z.ai flagship model for 1M-context long-horizon engineering, coding agents, refactoring, and complex multi-step automation.
GLM-5.1
GLM-5.1 delivers a major leap in long-horizon coding capability — capable of working independently for 8+ hours on a single task, autonomously planning, executing, and self-improving to deliver complete engineering-grade results.
GLM-5
Z.ai's flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows. Delivers production-grade performance on large-scale programming tasks with advanced agentic planning and iterative self-correction.
Gemini 3.8 Flash
Google's most intelligent Flash model for long-horizon software engineering, autonomous agents, and complex enterprise workflows.
Gemini 3.7 Flash
Google's latest stable Flash model for complex coding, agentic workflows, multimodal reasoning, and reliable multi-step execution.
Gemini 3.6 Flash
Google's GA Flash model for fast multimodal reasoning, long-context analysis, web-grounded answers, and high-throughput knowledge work.
Gemini 3.5 Flash
Google's fast, highly capable Gemini 3.5 model for agentic workflows, coding, multimodal analysis, and long-context tasks.
Gemini 3.5 Flash-Lite
Google's GA lightweight Flash-Lite model for low-cost multimodal tasks, fast document analysis, and efficient high-volume chat.
Gemini 3.1 Pro
Refined Gemini 3 Pro with better thinking, improved token efficiency, and enhanced factual consistency. Optimized for software engineering behavior, agentic workflows, and precise multi-step execution across real-world domains.
Gemini 2.5 Flash-Lite
Ultra-fast lightweight preview focused on speed for simple tasks.
Gemini 2.5 Flash
Google's fast and cost-efficient reasoning model with a 1-million-token context window, native multimodal support, and adaptive thinking for a wide range of tasks.
Gemini 2.5 Pro
Powerful multimodal reasoning model with excellent STEM capabilities.
Meta
MiniMax
MiniMax M3
MiniMax frontier coding and agentic model with native multimodality, sparse attention, and a 1M-token context window.
MiniMax M2.7
MiniMax latest flagship agentic model designed for autonomous real-world productivity, featuring multi-agent collaboration, live debugging, financial modelling, and full document generation across Word, Excel, and PowerPoint.
MiniMax M2.5
MiniMax M2.5 available free via OpenRouter — SOTA real-world productivity model scoring 80.2% on SWE-Bench Verified. Fluent in office automation, agentic workflows, and cross-software coordination.
Mistral
Mistral Medium 3.5
Mistral frontier-class dense multimodal model optimized for agentic coding, reliable tool use, configurable reasoning, and professional workflows.
Mistral Small 4
Mistral Small 4 unifies reasoning, multimodal understanding, and agentic coding capabilities into a single 24B model — the most capable Mistral Small yet.
Ministral 3
Small, dense multimodal model designed for efficient text and vision understanding with deployment-friendly performance.
Mistral Large 3
State-of-the-art open-weight multimodal Mixture-of-Experts (MoE) LLM with enormous context support, strong reasoning, and enterprise-grade performance.
Magistral Small 1.2
Open-weight small reasoning LLM from Mistral AI.
Magistral Medium 1.2
Mistral AI's frontier-class multimodal reasoning model.
Mistral Medium 3.1
Frontier-class multimodal model from Mistral AI.
Moonshot
Kimi K3
Moonshot AI flagship open-weight reasoning model for long-horizon coding, large codebases, knowledge work, and agentic workflows.
Kimi K2.6
Moonshot AI next-generation multimodal model for long-horizon coding, UI/UX generation, and multi-agent orchestration.
Kimi K2 Thinking
Moonshot AI advanced reasoning model with long-horizon thinking.
OpenAI
GPT-5.6 Sol
OpenAI's frontier GPT-5.6 model for complex professional work, with a 1.05M token context window, native web search, and image generation.
GPT-5.6 Luna
OpenAI's cost-efficient GPT-5.6 model for high-volume workloads, with a 1.05M token context window, native web search, and image generation.
GPT-5.6 Terra
OpenAI's mid-tier GPT-5.6 model balancing intelligence and cost, with a 1.05M token context window, native web search, and image generation.
GPT-5.5
OpenAI's newest frontier model representing a new class of intelligence. More intelligent and more token-efficient than GPT-5.4, with native computer use, coding capabilities, and a 1M context window.
GPT-5.5 Pro
Maximum-performance version of GPT-5.5 using more compute to think harder and provide consistently better answers. The most capable and accurate model in the GPT-5.5 family.
GPT-5.4
OpenAI's frontier model for complex professional work. The first mainline reasoning model incorporating GPT-5.3-Codex capabilities, with native computer use, 1M context, and state-of-the-art token efficiency.
GPT-5.4 Pro
Maximum-performance version of GPT-5.4 using more compute to think harder. Designed for the hardest professional tasks requiring the highest accuracy.
GPT-5.4 nano
OpenAI's smallest and most cost-efficient GPT-5.4-class model, optimized for high-volume simple tasks with native reasoning support and a 400k context window.
GPT-5.4 mini
OpenAI's strongest mini model for coding, computer use, and subagents. Brings the strengths of GPT-5.4 to a faster, more efficient model designed for high-volume workloads.
GPT-5.2
OpenAI's newest flagship GPT-5 series model.
GPT-5.2 pro
OpenAI's most advanced professional variant of the GPT-5.2 family.
GPT-5
OpenAI's next-generation flagship model, offering unparalleled intelligence, reasoning, and multimodal capabilities.
GPT-5 pro
OpenAI's advanced high-reasoning version of the GPT-5 series, designed to produce smarter, more precise, and in-depth answers.
GPT-5 nano
OpenAI's smallest and fastest GPT-5 variant, optimized for ultra-low latency, high throughput, and cost-efficient text and basic multimodal tasks.
GPT-5 mini
A compact version of GPT-5, optimized for speed and efficiency while retaining strong reasoning and basic multimodal support.
GPT-4.1
OpenAI's latest flagship instruction-following model with a 1-million-token context window, strong coding, vision, and agentic task capabilities.
GPT-4.1 mini
Compact version of GPT‑4.1 for faster yet capable responses.
o3
Enhanced reasoning and depth—ideal for heavy-duty logic and research.
o3-pro
OpenAI's professional-grade reasoning model that uses significantly more compute per query to deliver higher accuracy on the most demanding tasks.
Perplexity
Sonar Reasoning Pro
Premium reasoning-tier with chain-of-thought logic, large context (127k tokens), and extensive citation.
Sonar Deep Research
Expert-level research model that autonomously performs dozens of web searches, synthesizes sources, and generates comprehensive reports (typically 2–4 minutes per task).
Sonar
Lightweight, fast, and real-time search-enabled model for quick, citation-backed web answers.
Sonar Pro
Enhanced version with larger context and richer citation output for in-depth multi-step answers.
Qwen
Qwen3.8 Flash
Qwen's efficient million-context multimodal reasoning model for coding, agents, visual understanding, and long-video analysis.
Qwen3.8 27B
Qwen's efficient 27B multimodal reasoning model for coding, analysis, and production workloads.
Qwen3.8 Max
Qwen's flagship million-context model for reasoning, coding, multimodal analysis, and agentic work.
Qwen3.7 Plus
Alibaba balanced multimodal Qwen 3.7 model for agentic coding, visual understanding, tool use, and long-context productivity workflows.
Qwen3.7 Max
Alibaba flagship Qwen 3.7 text model for long-horizon autonomous agents, advanced coding, reasoning, and productivity tasks.
Qwen3.6 Plus
Qwen3.6 Plus builds on a hybrid architecture combining efficient linear attention with sparse MoE routing — major gains in agentic coding, front-end development, and reasoning over the 3.5 series.
Qwen3.5 Flash
Alibaba's ultra cost-efficient Qwen3.5 Flash model — fast inference with strong reasoning and 1M context at minimal cost.
Qwen3.5 Plus
High-capability Qwen3.5 native vision-language model with hybrid linear attention and sparse MoE architecture, delivering state-of-the-art performance across reasoning, coding, and multimodal tasks.
xAI
Grok 4.6
xAI's frontier model for coding, agentic tasks, knowledge work, and fast high-quality reasoning.
Grok 4.5
xAI/SpaceXAI flagship model for coding, agentic tasks, knowledge work, engineering, and efficient high-speed reasoning.
Grok 4.3
xAI's newest flagship model with strong agentic tool calling, instruction following, low hallucination rate, and configurable reasoning.
Grok 4.20
xAI's newest flagship model with industry-leading speed, agentic tool calling, and optional reasoning. Combines low hallucination rate with strict prompt adherence.
Grok 4.20 (Non-Reasoning)
xAI's flagship Grok 4.20 in fast non-reasoning mode — same frontier capabilities with lower latency when chain-of-thought is not needed.