Arrow 2
quiverai/arrow-2A chat model with a 131K-token context window, at $4.20 per million input tokens and $21.00 per million output tokens.
Details
- Maker
- quiverai
- Kind
- Chat
- Context window
- 131,072 tokens
- Max output
- 131,072 tokens
- Input
- $4.20 per million tokens
- Cached input
- $0.42 per million tokens, 90% off
- Cache write
- $5.25 per million tokens
- Output
- $21.00 per million tokens
- Capabilities
- Reasoning, tool use, vision, image generation
- Takes
- Text, image
- Returns
- Text, image
- Zero data retention
- Not on every provider
- No training on requests
- Not on every provider
- Released
- 2026-09-16
Description
SVG generation model with agentic refinement and tool calling.
Call it
curl
curl https://phantom.codes/v1/chat/completions \
-H "Authorization: Bearer $PHANTOM_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "quiverai/arrow-2",
"messages": [
{"role": "user", "content": "Hello"}
]
}'Set PHANTOM_KEY to your key. Any OpenAI client works with the base URL https://phantom.codes/v1.