google/gemini-4-neon/chatGoogle's Gemini 4 Neon API pairs deep multi-step reasoning with a 1,048,576-token window for heavy software architecture, research synthesis, and structured tool orchestration.
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
- $2.10 / 1 million tokens
- Cached input
- $0.105 / 1 million tokens
- Output
- $10.50 / 1 million tokens
- Context
- 1,048,576
- Max output
- 65,536
$2.10/10.50per 1 million tokens · input / output
multimodal-ui-audit Audits a dark-mode boutique hotel hero screenshot for visual contrast, card spacing, and midnight editorial mood using medium reasoning effort.
- 2048
- medium
- Input types
- Text
- Output types
- Text
- Input
- $2.10 / 1 million tokens
- Cached input
- $0.105 / 1 million tokens
- Output
- $10.50 / 1 million tokens
- Context
- 1,048,576
- Max output
- 65,536
$2.10/10.50per 1 million tokens · input / output
structured-contract-json Extracts wardrobe styling, lighting cues, deliverables, and talent clearance clauses from a late-night campaign memo into a strict JSON Schema payload.
- 2048
- medium
- Input types
- Text
- Output types
- Text
- Input
- $2.10 / 1 million tokens
- Cached input
- $0.105 / 1 million tokens
- Output
- $10.50 / 1 million tokens
- Context
- 1,048,576
- Max output
- 65,536
$2.10/10.50per 1 million tokens · input / output
tool-calling-triage Triggers a live continuity-ledger function call for a midnight penthouse scene at low reasoning effort before proposing script edits.
- 1024
- auto
- low
This example starts at Input $2.10 / Output $10.50 per 1 million tokens. The Playground updates the estimate when you change the settings.
