Claude Sonnet 5 chat from Anthropic through an OpenAI-compatible endpoint. It takes up to 1,000,000 tokens of text and image context and returns up to 64,000, with low, medium or high reasoning effort, up to 128 tool definitions and SSE streaming.
Workbench
These examples were written for this endpoint. Replace the prompt and sample media URLs with your own accessible inputs, then check the current quote and model availability before submitting.
- Input types
- Text
- Output types
- Text
- Input
- $1.90 / 1 million tokens
- Cached input
- $0.19 / 1 million tokens
- Output
- $9.50 / 1 million tokens
- Context
- 1M
- Max output
- 64K
$1.90/9.50per 1 million tokens · input / output
long-session-turn The everyday turn: the whole history sent back untouched, with reasoning effort held at low. This example exists to show where the model sits - most turns do not need peak capability.
- 1200
- low
- Input types
- Text
- Output types
- Text
- Input
- $1.90 / 1 million tokens
- Cached input
- $0.19 / 1 million tokens
- Output
- $9.50 / 1 million tokens
- Context
- 1M
- Max output
- 64K
$1.90/9.50per 1 million tokens · input / output
multi-character-scene Three characters in one room. The voices are pinned in the system message, the user turn carries only the situation, and effort goes to high.
- 2000
- high
- Input types
- Text
- Output types
- Text
- Input
- $1.90 / 1 million tokens
- Cached input
- $0.19 / 1 million tokens
- Output
- $9.50 / 1 million tokens
- Context
- 1M
- Max output
- 64K
$1.90/9.50per 1 million tokens · input / output
tool-driven-session One narrated turn with tools. Tool results stay in the conversation and count against the window, so a long chain eventually needs pruning.
- 1500
- medium
This example starts at Input $1.90 / Output $9.50 per 1 million tokens. The Playground updates the estimate when you change the settings.