Models
4 models
Newest
ByteDance Seed: Seed-2.0-Mini
bytedance-seed/bytedance-seed-seed-2-0-miniLatency-sensitive, high-concurrency, and cost-sensitive model emphasizing fast response and flexible inference.
Feb 27, 2026
256k context
$0.10/M input tokens
$0.40/M output tokens
Text
Image
690M tokens
Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview)
google/google-nano-banana-2-gemini-3-1-flash-image-previewFast multimodal model for image generation and editing, with strong contextual understanding.
Feb 24, 2026
64k context
$0.25/M input tokens
$1.50/M output tokens
Image
447M tokens
Qwen: Qwen3.5-35B-A3B
qwen/qwen-qwen3-5-35b-a3bHigh quality general-purpose model with strong reasoning and tool-use, optimized for throughput.
Feb 20, 2026
128k context
$0.12/M input tokens
$0.60/M output tokens
Text
Trivia
7.2B tokens
Qwen: Qwen3.5-27B
qwen/qwen-qwen3-5-27bBalanced model for chat and long context workloads with predictable pricing and stable output.
Feb 10, 2026
128k context
$0.08/M input tokens
$0.40/M output tokens
Text
3.6B tokens