Tasks and inputs
Arrow 2 Telos is listed for Image-text-to-image, Text-to-image. It accepts text, image and produces text, image. Use the publisher’s input format and preprocessing for your chosen deployment.
SyncDev model directory · Profile updated Oct 13, 2026
Arrow 2 Telos is QuiverAI’s SVG model for complex vector creation and refinement with longer context.
Recorded modality support shows what this model can accept and produce. An undocumented modality is shown as unknown rather than assumed to be unsupported.
Accepts
Produces
Arrow 2 Telos is the more capable member of QuiverAI’s Arrow 2 family, positioned for demanding vector work and longer refinement context. It produces SVG artwork rather than a raster image alone. That makes its output useful when an illustration must stay editable, scale without losing detail, or fit into a vector production workflow.
The model is generally available for both Production and Test keys, subject to the authority assigned to the key. The model and chosen operation must both be permitted. Read the model API’s supported operations and billing fields before assuming that generation, editing, animation and vectorization share an interface or a price.
A practical comparison with Arrow 2 should use complex reference artwork and several successive revisions. Inspect the SVG in the renderer you will actually ship. Check path organization, gradients, clipping, typography and whether an edit preserves the parts of the composition that should remain fixed. Record the cost and time to the approved asset, including rejected drafts.
The larger recorded context limit describes request capacity; it does not prove that Telos produces a better result on every design. For simple icons or rapid iteration, the faster Arrow 2 route may be sufficient.
QuiverAI schedules retirement of the remaining Arrow 1.x IDs for 16 October 2026. A migration should pin the intended Arrow 2 model, exercise the operations your workflow uses, and confirm permissions on the deployment key. The linked publisher documentation is the reference for access and lifecycle changes.
Compare the model on the work you need to complete.
Arrow 2 Telos is listed for Image-text-to-image, Text-to-image. It accepts text, image and produces text, image. Use the publisher’s input format and preprocessing for your chosen deployment.
Documented limits: 1.05M context and 65.54K maximum output. Choose the output size and quality your design needs. Include drafts and revisions when budgeting an accepted image.
Use the model identifier and account requirements for the selected API route. Confirm its request limits and output format with one complete task before connecting a larger workflow.
These records share a directory category. Check the source card, output type and deployment requirements before treating a model as a replacement.
Gemini Nano Banana 2.1 is Google's image-generation and conversational-editing model released. It accepts text, images, video and PDFs and returns images and text.
QuiverAI
QuiverAI’s Arrow 2 generates, vectorizes, edits and animates SVG artwork through a model-specific API.
Qwen
Qwen Image 2.1 is a downloadable model that combines text-to-image generation, image editing and native transparent RGBA output.
OpenAI
GPT Image 2.5 Flare creates and edits images from text and image inputs through OpenAI’s image-generation APIs.
OpenAI
GPT Image 2.5 Sunburst creates and edits images from text and image inputs through OpenAI’s image-generation APIs.
xAI
Grok Imagine Image 2.0 is a hosted image-generation and editing model accessed through the Imagine API.