Chat with any text model.

• Any text model

  Pick a model in the message box, or leave it on Auto. Change the model for the next message, or have an answer written again by another one.

• Files and images

  Attach PDFs, Word documents, images, CSV, JSON, text and code files. A picture needs a model that reads images; Auto picks one.

• Answers as they are written

  The answer streams in. Stop it, continue it or regenerate it, and move between the versions of an answer.

• Branch a conversation

  Start a new conversation from any answer and take it another way. The original stays as it was.

• Hand the result on

  Create image, Build this and Ask consensus take the conversation to Image, Code or Consensus.

• Keep it in a project

  Save a chat to a project, next to its code, media and files. Search and rename your chats.

1. 01

   Ask

   Type a question, attach what the model should read, and pick a model or leave it on Auto.

2. 02

   Read the answer

   The answer appears as the model writes it. When it is done, its cost in credits shows under it.

3. 03

   Take it further

   Ask a follow-up, regenerate with another model, branch the conversation, or hand the result to Code, Image or Consensus.

• Claude Opus 5.5
• GPT-6 Sol
• Claude Sonnet 5
• Gemini 3.8 Flash
• GPT-6 Luna
• DeepSeek V4.1 Flash
• DeepSeek V4 Pro
• Claude Opus 5
• Grok 4.7
• Kimi K3
• Qwen3.8 Max
• GPT-6 Astra
• GLM 5.3
• Mistral Medium 3.5
• Claude Fable 5.1
• Gemini 3.6 Flash
• GPT-5.6 Sol
• Qwen3.8 Flash
• Kimi K2.7 Code
• Qwen3.7 Plus
• GPT-5.5
• Mistral Large 3
• Claude Opus 4.7
• Devstral 2
• Gemini 3.5 Flash Lite
• GLM 5
• Gemini 2.5 Pro
• Llama 4 Maverick
• DeepSeek V3
• Qwen-Plus
• Kimi K2
• Mistral Large
• Sonar

On Auto, ewpire picks a model for each message and moves on to the next one if that model is unavailable; a model you pick yourself is never replaced.

• Claude Opus 5.5: a request with 2,000 input tokens and 1,000 output tokens costs 0.02954 credits – 0.00844 for the input and 0.0211 for the output.

Counted from the prices in the model catalog, where one credit is $1. The exact charge of each request appears in Usage.

• A file can be up to 20 MB, and a model is given up to 200,000 tokens of a file's text.
• A message can carry up to 10 files.
• You can upload 30 files a minute and 300 a day.
• A conversation longer than the model's context is trimmed from its oldest messages, and the answer says so.
• Daily limits reset at midnight UTC.

• It does not check an answer against other models. A single model can be confidently wrong; Consensus puts the same question to several.
• It does not take audio or video files. Attachments are PDFs, Word documents, images, CSV, JSON, text and code files.
• It does not swap a model you picked. If that model is unavailable, the request ends with an error and nothing is charged.

• Docs
• FAQ on the modes
• Pricing
• Model catalog