LLM Reference

Arrow 2

Released
2026-09-07
Last refreshed
2026-09-17
Status
Researched today
ProprietaryCommercial use: conditionalMultimodalRAGAgentsLong contextVisionJSON / Tool useMultimodal

Arrow 2 is worth evaluating for rag, agents, and long context when its provider route and context window match the workload.

Use it for

  • Teams evaluating rag, agents, and long context
  • Workloads that can use a 131k context window
  • Buyers comparing 1 tracked provider route

Do not use it for

  • Workloads where another current model has stronger sourced task evidence
Specifications
Family
Arrow
Released
2026-09-07
Context
131k
Max output
65,536
Specialization
vector-svg
Openness
Proprietary
License
ProprietaryCommercial use: conditional
Weights
Not released
Code
Unknown
Training
Pretrained
Created by

QuiverAI is a Frontier AI for Design lab building foundational models for generating, editing, and animating vector grap

Website
Pricing
Output / 1M
$20.00
Input / 1M
$4.00

Cheapest of 1 route · QuiverAI · cache read $0.400

About

Arrow 2 (API model id arrow-2) is QuiverAI's generally available vector SVG model prioritizing speed and cost per asset. First-party launch blog (Sep 7, 2026): faster generation; cleaner geometry; stronger composition; improvements across illustrations, diagrams, technical line work, raster vectorization, and micro-animations of existing SVG shapes/groups. Tip thread @QuiverAI 2026-09-16: available now in App and API. Docs: inputs text/image/SVG; output SVG; context 131,072; max output 65,536; SVG generation + image vectorization supported; SVG editing/animation and Responses (open_responses) when enabled in catalog. Billing token_usage. Blog guidance: choose Arrow 2 when speed and cost per asset are the priority.

Top use-case fit: coding, agents, and build tasks

RAG

Included by capability and metadata signals in the decision map.

Agents

Included by capability and metadata signals in the decision map.

Long context

Included by capability and metadata signals in the decision map.

Provider price ladder

Compare API pricing across 1 providers for input and output tokens, batch, and cached reads when available.

ProviderInput / 1MOutput / 1MCacheRoute
QuiverAI$4.00$20.00read $0.400
Serverless

Capabilities

VisionMultimodalJSON / Tool usePrompt Caching

Benchmark peer barsfor RAG

No task-mapped benchmark peers are available for this model yet.

Migration checks

No linked migration route is available for this model yet.

API versions

arrow-2