Reasoning Tools JSON

Lightweight ByteDance Seed 2.0 model for low-latency multimodal reasoning and high-volume tasks

bytedance-seed/seed-2.0-mini 2026-02-14 256K context $0.03/M input $0.297/M output
9 providers
Reasoning Tools JSON

Flagship ByteDance Seed 2.0 model for complex multimodal reasoning and long-horizon agent workflows

bytedance-seed/seed-2.0-pro 2026-02-14 256K context $0.475/M input $2.375/M output
6 providers
JSON

Cost-efficient ByteDance Seed 2.0 model for production chat, analysis, and structured generation

bytedance-seed/seed-2.0-lite 2026-02-14 256K context $0.089/M input $0.534/M output
8 providers
Tools Open weights

Earlier Kimi frontier model for long-context agents, coding, and multimodal work

moonshotai/kimi-k2.5 2026-01 262.144K context $0.3/M input $1.9/M output
46 providers
Reasoning Tools JSON

New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs

google/gemini-3-flash-preview 2025-12-17 1.04858M context $0.5/M input $3/M output
25 providers
Reasoning

Multimodal reasoning model for visual analysis, planning, and tool use

amazon/nova-2-lite 2025-12-02 1M context $0.3/M input $2.5/M output
4 providers
Reasoning Tools JSON

Preview Gemini flagship for complex reasoning, coding, and rich multimodal prompts

google/gemini-3-pro-preview 2025-11-18 1.04858M context $0.57/M input $3.43/M output
10 providers
Reasoning Tools JSON

Fast Gemini workhorse for multimodal apps where latency and price matter

google/gemini-2.5-flash 2025-06-17 1.04858M context $0.3/M input $2.5/M output
30 providers
Reasoning Tools JSON

Google's proven reasoning model for coding, math, and multimodal analysis

google/gemini-2.5-pro 2025-06-17 1.04858M context $1.25/M input $10/M output
29 providers
Reasoning Tools JSON

Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents

google/gemini-2.5-flash-lite 2025-06-17 1.04858M context $0.1/M input $0.4/M output
18 providers
Tools

Earlier Gemini Flash workhorse for responsive multimodal apps and tool use

google/gemini-2.0-flash 2024-12-11 1.04858M context $0.1/M input $0.42/M output
2 providers
Tools

Low-latency Gemini model for high-volume multimodal and agent workloads

google/gemini-2.0-flash-lite 2024-12-11 1.04858M context $0.052/M input $0.21/M output
2 providers
Tools

Efficient model for low-latency assistance, extraction, and routine automation

amazon/nova-lite 2024-12-03 300K context $0.06/M input $0.24/M output
3 providers
Tools

Flagship model for demanding analysis, coding, and production agent workflows

amazon/nova-pro 2024-12-03 300K context $0.8/M input $3.2/M output
3 providers