Guide

GPT-6.1 Sol Pro is the same underlying model as [GPT-6.1 Sol](https://openrouter.ai/openai/gpt-6.1-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...

GPT-6.1 Sol Pro is the same underlying model as [GPT-6.1 Sol](https://openrouter.ai/openai/gpt-6.1-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...

GPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series. It is suited for agentic coding, computer use, document-heavy professional...

GPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series. It is suited for agentic coding, computer use, document-heavy professional...

Together AI is an AI cloud for running open-source models. Its serverless inference API gives pay-per-token access to models like Llama, DeepSeek, Qwen, GLM, Kimi, MiniMax, and gpt-oss through an OpenAI-compatible endpoint. Beyond serverless inference, Together AI offers dedicated endpoints, fine-tuning, batch inference, and GPU clusters for teams that need more control over performance and cost.

Cohere is an enterprise AI company that builds the Command family of language models, designed for business use cases like retrieval-augmented generation (RAG), tool use, and multilingual chat. The lineup also includes Command A Vision for images, Command A Reasoning for multi-step problems, and the open-weight Aya models covering 23 languages. Cohere offers a free, rate-limited trial key for testing and pay-per-token production keys, with an OpenAI-compatible endpoint that works with any OpenAI-compatible client.

Near-Astra performance for complex coding, computer use, and professional work at a lower cost.

GPT model for general reasoning, writing, coding, and tool-assisted tasks

General-purpose chat model for instruction following, writing, and analysis

Efficient model for low-latency assistance, extraction, and routine automation

Efficient model for low-latency assistance, extraction, and routine automation

Near-Astra performance for complex coding, computer use, and professional work at a lower cost.

Near-Astra performance for complex coding, computer use, and professional work at a lower cost.

Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade. It is especially strong at building features, fixing bugs, and producing...

Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade. It is especially strong at building features, fixing bugs, and producing...

Fast Claude model for everyday coding, agents, and knowledge work

MiMo flash model for fast multimodal assistance and agent workflows

Fast Claude model for everyday coding, agents, and knowledge work

Fast Claude model for everyday coding, agents, and knowledge work

Z.AI is the international platform of Zhipu AI, the team behind the GLM model family. Its API gives pay-per-token access to GLM models for chat, reasoning, coding, and vision through an OpenAI-compatible endpoint, including free Flash models for lighter tasks.

OpenCode Go is a model service from the OpenCode team that gives you one API key for 30+ curated coding models, including DeepSeek V4, Qwen3.8, GLM-5.3, Kimi K3, MiMo, MiniMax, and Grok, billed per token. Most models use an OpenAI-compatible Chat Completions endpoint, while the GPT, Grok, and Muse Spark models use the OpenAI Responses API.

Cloudflare AI Gateway sits between your apps and AI providers such as OpenAI, Anthropic, Google, xAI, and DeepSeek, adding caching, rate limiting, logging, and analytics across all of them. Its unified OpenAI-compatible endpoint lets one Cloudflare API token reach models from every provider. Store your provider keys in the gateway or use Cloudflare's Unified Billing to pay per token, then connect TypingMind with an authentication token created inside your gateway.

AWS Bedrock is a fully managed AWS service that gives you access to 100+ foundation models from leading AI providers, including Anthropic Claude, Meta Llama, Mistral, and more, through a single OpenAI-compatible API. Bedrock uses pay-as-you-go pricing with no monthly fees or minimum commitments, and requests run inside your own AWS account. Long-term API keys work with any OpenAI-compatible client, and you can monitor usage in the AWS console.

Xiaomi MiMo is Xiaomi's API platform for its MiMo language models. The lineup includes Pro models for complex reasoning and coding, Flash models for fast, low-cost tasks, UltraSpeed variants for faster output, and multimodal models that accept images, audio, and video as input. The MiMo API uses pay-as-you-go pricing and offers an OpenAI-compatible endpoint, so it works with any OpenAI-compatible client.

Flagship Claude model for deep reasoning, coding, and long-horizon agents

Balanced Claude model for coding, analysis, agent workflows, and cost control

Multimodal reasoning model for visual analysis, planning, and tool use

Jev Router picks the best model and reasoning effort for each request, balancing quality, speed, and cost. It runs on [Jev](https://openrouter.ai/~typesafe/jev-latest), TypeSafe's first System One model, and adapts as your...

Perceptron Mk1.5 is Perceptron's embodied reasoning model for physical agents. It accepts text, image, video, and audio input, and answers with text plus optional structured annotations: points, boxes, polygons, tracks,...

Cerebras runs AI models on its wafer-scale chips, delivering some of the fastest inference available, often thousands of tokens per second. Its cloud offers open models such as gpt-oss 120B and Qwen through a serverless API. Cerebras uses pay-per-token pricing and an OpenAI-compatible Chat Completions endpoint, so it works with any OpenAI-compatible client.

Multimodal reasoning model for visual analysis, planning, and tool use

Meituan's multimodal reasoning model for coding and agent tasks, with image understanding and a 1M-token context window

Ember-1 is a specialized reasoning model from Fireworks Research, built on [Kimi K3](https://openrouter.ai/moonshotai/kimi-k3). It is designed to make every token go further: it produces shorter reasoning traces, using roughly 40%...

Alibaba Cloud Model Studio is Alibaba Cloud's platform for the Qwen model family, from the flagship Qwen Max models to fast, low-cost Qwen Flash models, plus vision, omni, and reasoning variants. It also hosts third-party models such as DeepSeek and GLM. Model Studio supports the OpenAI Responses API with pay-as-you-go pricing, and offers endpoints in several regions, including China (Hong Kong), Singapore, US (Virginia), and Germany (Frankfurt).

MiniMax is an AI company that builds the MiniMax M-series language models, designed for coding, agentic workflows, and long-context reasoning at a low price per token. The lineup includes MiniMax-M3 and the M2 family, with highspeed variants for faster output. The MiniMax API uses pay-as-you-go pricing and offers an OpenAI-compatible endpoint, so it works with any OpenAI-compatible client.

Novita AI is a cloud platform for running open-source AI models, with 100+ models such as DeepSeek, Kimi, Qwen, GLM, MiniMax, Llama, and gpt-oss available through a serverless API. It uses pay-per-token pricing and an OpenAI-compatible endpoint, so it works with any OpenAI-compatible client. Novita also offers GPU instances and agent sandboxes for teams that need more control.

GLM-5.3-Prime is the high-speed variant of Z.ai's GLM-5.3, inheriting its full capabilities while delivering 1.5–2× the output throughput through inference acceleration. It supports text input and output with a 1M-token...

Qwen3.8 Max Prime is a higher-throughput variant of Qwen3.8 Max from Alibaba's Qwen team, served as a separate SKU at a higher price point. It accepts text, image, and video...

Space Bunny Alpha is an anonymous large model with blazing-fast inference, strong coding capabilities and native multimodal input support. It delivers adjustable reasoning effort, and a 1M-token context window. Space...

Aion 3.5 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It is the smaller, lower-cost sibling of Aion 3.5 and uses...

Aion 3.5 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It uses a collaborative generation process in which multiple specialized models each...

Solar Mini 4 is Upstage's compact, cost-efficient language model, a 35B-parameter mixture-of-experts with 3B active parameters and a 524K context window. It is built for agentic use cases where response...

Ollama Cloud runs large open models on Ollama's datacenter hardware, so you can use models too big for your own computer, like DeepSeek V4, Kimi K3, GLM-5.3, Qwen3.5 397B, and gpt-oss 120B, with the same Ollama account. Usage is billed per million tokens from your account's usage credits, and the API is OpenAI-compatible, so it works with any OpenAI-compatible client.

Reasoning model for deliberate analysis, multi-step problem solving, and tool use

Efficient model for low-latency assistance, extraction, and routine automation

Image model for prompt-driven generation, editing, and visual design workflows

High-throughput edition of Qwen3.8 Max for coding, professional work, multimodal understanding, and long-running agent workflows

Speech generation model for controllable voice, narration, and audio delivery

Speech generation model for controllable voice, narration, and audio delivery

Multimodal reasoning model for visual analysis, planning, and tool use

Anonymous preview reasoning model for coding, agentic tasks, tool use, and multimodal input