WaveSpeedAI

AI Models

Models change every week. This category covers new launches and major updates across image, video, audio, 3D, and LLM models on WaveSpeedAI: what each model does, where it fits, and how builders can call it through one unified API.

K2 Horizon Edge Models: Choose a Device Tier

K2 Horizon Edge Models: Choose a Device Tier

K2 Horizon edge models can be mapped to device tiers without treating parameter count as a complete capability ranking.

6 min read
K2 Horizon 36B Review for Local Agent Workloads

K2 Horizon 36B Review for Local Agent Workloads

K2 Horizon 36B review for one local agent workload, focusing on memory demand, tool use, latency, and recovery reliability.

6 min read
K2 Horizon Review: What the Open Model Family Includes

K2 Horizon Review: What the Open Model Family Includes

K2 Horizon review of the current model family, released checkpoints, and access routes that AI builders can verify today.

5 min read
GPT Image 2.5 API Guide: Flare & Sunburst on WaveSpeedAI
gpt-image-2.5gpt-image-2

GPT Image 2.5 API Guide: Flare & Sunburst on WaveSpeedAI

Use GPT Image 2.5 Flare and Sunburst on WaveSpeedAI with API examples, five quality settings, up to 4K output, and edits using up to 16 reference images.

7 min read
Bria Fibo 1.5 on WaveSpeedAI: Generate 1.5 and Edit 1.5 Versus the Fibo Family
briafibo

Bria Fibo 1.5 on WaveSpeedAI: Generate 1.5 and Edit 1.5 Versus the Fibo Family

Bria Fibo Generate 1.5 and Edit 1.5 are live on WaveSpeedAI at $0.04 per image. What 1.5 changes, every parameter, and when to use them over the earlier Fibo endpoints.

7 min read
Gemini Omni 1.1 Flash API on WaveSpeedAI: 360p to 4K, Video Edit and Reference-to-Video
gemini-omnigemini-omni-1-1-flash

Gemini Omni 1.1 Flash API on WaveSpeedAI: 360p to 4K, Video Edit and Reference-to-Video

Four Gemini Omni 1.1 Flash endpoints are live on WaveSpeedAI. Parameters, resolution tiers, per-second pricing from $0.03 to $0.30, and what changed from Omni Flash.

7 min read
Grok Imagine Image 2.0 API on WaveSpeedAI: Parameters, Pricing and How It Compares to Earlier Grok Image Endpoints
grok-imaginegrok-imagine-image-2-0

Grok Imagine Image 2.0 API on WaveSpeedAI: Parameters, Pricing and How It Compares to Earlier Grok Image Endpoints

xAI Grok Imagine Image 2.0 text-to-image and edit endpoints on WaveSpeedAI: $0.05 and $0.06 per image, 13 aspect ratios, 1K or 2K output, and how they differ from the older Grok image endpoints.

6 min read
Kling O3 4K Adds Video Edit and Video Reference
kling-o3kling

Kling O3 4K Adds Video Edit and Video Reference

Kling O3 4K on WaveSpeedAI now includes video-edit and video-reference endpoints. Every Kling O3 tier, parameter, and price, plus when to pick std, pro, or 4K.

6 min read
Meta Muse Image API on WaveSpeedAI: Text-to-Image and Edit at $0.011
metamuse-image

Meta Muse Image API on WaveSpeedAI: Text-to-Image and Edit at $0.011

Meta Muse Image text-to-image and edit endpoints on WaveSpeedAI: parameters, flat $0.011 pricing, what edit accepts, and how it compares with other low-cost image models.

7 min read
Nano Banana Pro Review for Production Image Work

Nano Banana Pro Review for Production Image Work

Nano Banana Pro review focuses on production image generation, editing, text, consistency, API access, and workflow limits.

6 min read
Claude Fable 5.1 Review for Long-Running Work

Claude Fable 5.1 Review for Long-Running Work

Claude Fable 5.1 review for builders deciding whether its long-running work capabilities justify a premium route in their model stack.

7 min read
HUMAIN M3 Review for Arabic Multimodal Apps

HUMAIN M3 Review for Arabic Multimodal Apps

HUMAIN M3 review for teams assessing a limited-preview Arabic multimodal model, focused on fit, access constraints, and production risk.

6 min read