Earlier Kimi frontier model for long-context agents, coding, and multimodal work
Models
Every model in the catalog with source-linked pricing, context limits, provider availability, and published benchmark results.
Hybrid-reasoning DeepSeek model with thinking and non-thinking modes, sparse attention, and tool-use
Largest Gemma 4 instruction model for open, self-hosted chat and reasoning
Open Gemma instruction model for efficient chat and self-hosted deployments
Classic open reasoning model for transparent math, coding, and deliberate problem solving
Thinking Kimi model for slower research passes, planning, and hard technical questions
Largest open Gemma 3 instruction model for multilingual text generation and visual understanding
Open multimodal Gemma instruction model for multilingual text generation and image understanding
Open multimodal Gemma instruction model for efficient text generation and image understanding
| Model | Creator | Score | Inputs | Context | Input | Output | Released | Compare |
|---|---|---|---|---|---|---|---|---|
| Kimi K2.5moonshotai/kimi-k2.5 | 46.8 | 262.144K | $0.3 | $1.9 | 2026-01 | |||
| DeepSeek V3.2deepseek/deepseek-v3.2 | 44.2 | 128K | $0.18 | $0.35 | 2025-12-01 | |||
| Gemma 4 31B ITgoogle/gemma-4-31b-it | 43.4 | 262.144K | $0.09 | $0.34 | 2026-04-02 | |||
| Gemma 4 26B A4B ITgoogle/gemma-4-26b-a4b-it | 39.3 | 262.144K | $0.042 | $0.22 | 2026-04-02 | |||
| DeepSeek-R1deepseek/deepseek-r1 | 24.6 | 128K | $0.7 | $2.5 | 2025-01-20 | |||
| Kimi K2 Thinkingmoonshotai/kimi-k2-thinking | 21.0 | 262.144K | $0.4 | $2.5 | 2025-11-06 | |||
| Gemma 3 27B ITgoogle/gemma-3-27b-it | 10.1 | 131.072K | $0.08 | $0.16 | 2025-03-12 | |||
| Gemma 3 12B ITgoogle/gemma-3-12b-it | 5.8 | 131.072K | $0.05 | $0.1 | 2025-03-12 | |||
| Gemma 3 4B ITgoogle/gemma-3-4b-it | 2.7 | 131.072K | $0.04 | $0.08 | 2025-03-12 |