Access 200+ frontier and specialist models โ GPT-5, Claude Opus, Gemini 2.5, Grok 4, Mistral Large, DeepSeek V3, Groq LLaMA, Perplexity Sonar, and more โ without juggling logins or invoices.
Your workspace ships with every major provider ready to go. Auto Mode picks the right model for each task, and you can switch providers manually with a click.
Creators of GPT-5.5, GPT-5.5 Pro, GPT-5.4, and the lighter GPT-5.4 Mini/Nano family
Claude family of models with extended thinking and safety controls
Grok 4.3 and Grok 4.20 multimodal reasoning models from xAI
Gemini 3.1 and 2.5 multimodal models with million-token context
Anthropic Claude models including Claude Opus 4.8 and 4.7, the latest frontier models for long-running, complex tasks.
Flagship models
OpenAI delivers state-of-the-art multimodal and reasoning models including GPT-5.5, GPT-5.5 Pro, GPT-5.4, GPT-5.4 Pro, GPT-5.4 Mini, GPT-5.4 Nano, o3-pro, o4-mini, and the broader GPT-5 family.
Flagship models
Google Gemini pairs long-context reasoning, multimodal understanding, image-native generation, and open Gemma families spanning Gemini 3.1, Gemini 2.5, and Gemma 4 tiers.
Flagship models
xAI Grok delivers high-context reasoning, fast analysis, multimodal understanding, and tool-heavy agent workflows across Grok 4.3 and the active Grok 4.20 variants.
Flagship models
Groq delivers high-throughput, low-latency inference for open-weight models like LLaMA 3.3 and Mixtral โ perfect for prototyping and production agents.
Flagship models
DeepSeek V4 and DeepSeek Reasoner provide deliberate reasoning, coding, and competitive pricing for engineering and research teams with long-context support.
Flagship models
Mistral provides high-quality open and hosted models โ including Mistral Large 3, Devstral 2, and Mixtral โ balancing speed, accuracy, and multilingual support.
Flagship models
Perplexity Sonar blends DeepSeek reasoning with live web retrieval, returning sourced answers for analysts and customer teams.
Flagship models
OpenRouter aggregates frontier and experimental models across Anthropic, OpenAI, DeepSeek, Z.ai, ByteDance Seed, and many more through a single API.
Flagship models
Together AI offers performant hosted open models โ including LLaMA 3.1 405B and Mixtral โ with flexible pricing and finetuning options.
Flagship models
Fireworks AI accelerates open-source models like DeepSeek and LLaMA with tuned inference, convenient endpoints, and aggressive pricing.
Flagship models
Cohere Command models focus on multilingual accuracy, enterprise guardrails, long-context tool use, and the newer reasoning, vision, and translation specialisations.
Flagship models
MiniMax specializes in compact, high-efficiency models optimized for agent workflows, coding, and tool use with exceptional cost-performance ratio.
Flagship models
Local OpenAI-compatible llama.cpp runtime for private, zero-metered chat when the local server is running.
Flagship models
Need a provider that isnโt listed? Email [email protected] and weโll onboard it for your workspace.