All models
Anthropic
Claude Sonnet 4.5
Anthropic's September 2025 Sonnet, known for strong coding and long autonomous agent sessions. Still a fine coder and writer, with 1M context here. Cautious on controversial topics, weak at roleplay. Claude Sonnet 5.5 is newer and cheaper per message.
MainstreamThe big labs' models with their own safety filters. Best for work, code and research.
Smart & Cheap
Intelligence
~9.17 credits
Estimated price per message
1M tokens
Context window
Text, Images
Reads
Claude Sonnet 4.5 is a legacy model. Its successor, Claude Sonnet 5.5, is faster or cheaper - and chats that used Claude Sonnet 4.5 move to it automatically.
See Claude Sonnet 5.5The facts
Made by
Anthropic
Content tier
MainstreamThe big labs' models with their own safety filters. Best for work, code and research.
Intelligence
Smart & Cheap
Estimated price per message
~9.17 credits≈ 10 messages for $1
Context window
1M tokens≈ 1,538 pages of text in one go
Reads
Text, Images
Writes
Text
Tool use
Yes - search, memory, code and more
Served via
OpenRouter, Unbottled AI
Status
Legacy
A typical message: 16K tokens in, 1.5K out. Short replies cost less. Models served via OpenRouter bill the real provider cost plus our markup, so actual charges vary. 1 credit = $0.01.
Compare Claude Sonnet 4.5
Same facts, side by side.
Try Claude Sonnet 4.5 now.
No subscription. Free credits to start. The chat opens with Claude Sonnet 4.5 selected and a prompt ready - just send.