AI Model Catalog: 8 Models Compared — Pricing, Context & Benchmarks

Moonshot AI: Kimi K2.5 T

Tools Open weights 21.7

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

DeepSeek: DeepSeek V3.2 T

Reasoning Tools JSON Open weights 18.3

Hybrid-reasoning DeepSeek model with thinking and non-thinking modes, sparse attention, and tool-use

deepseek/deepseek-v3.2 2025-12-01 128K context $0.18/M input $0.35/M output

24 providers

Google: Gemma 4 26B A4B IT T

Reasoning Tools JSON Open weights 11.0

Open Gemma instruction model for efficient chat and self-hosted deployments

google/gemma-4-26b-a4b-it 2026-04-02 262.144K context $0.042/M input $0.22/M output

22 providers

Google: Gemma 4 31B IT T

Reasoning Tools JSON Open weights 6.7

Largest Gemma 4 instruction model for open, self-hosted chat and reasoning

google/gemma-4-31b-it 2026-04-02 262.144K context $0.09/M input $0.34/M output

33 providers

Moonshot AI: Kimi K2 Thinking T

Tools Open weights 1.8

Thinking Kimi model for slower research passes, planning, and hard technical questions

moonshotai/kimi-k2-thinking 2025-11-06 262.144K context $0.4/M input $2.5/M output

22 providers

DeepSeek: DeepSeek-R1 T

Reasoning Tools Open weights 1.1

Classic open reasoning model for transparent math, coding, and deliberate problem solving

deepseek/deepseek-r1 2025-01-20 128K context $0.7/M input $2.5/M output

14 providers

Google: Gemma 3 12B IT T

Open weights 0.1

Open multimodal Gemma instruction model for multilingual text generation and image understanding

google/gemma-3-12b-it 2025-03-12 131.072K context $0.05/M input $0.1/M output

8 providers

Google: Gemma 3 27B IT T

Open weights 0.1

Largest open Gemma 3 instruction model for multilingual text generation and visual understanding

google/gemma-3-27b-it 2025-03-12 131.072K context $0.08/M input $0.16/M output

10 providers

Filterable model directory
Model	Creator	Score	Inputs	Context	Input	Output	Released
Kimi K2.5moonshotai/kimi-k2.5	Moonshot AI	21.7	T	262.144K	$0.3	$1.9	2026-01
DeepSeek V3.2deepseek/deepseek-v3.2	DeepSeek	18.3	T	128K	$0.18	$0.35	2025-12-01
Gemma 4 26B A4B ITgoogle/gemma-4-26b-a4b-it	Google	11.0	T	262.144K	$0.042	$0.22	2026-04-02
Gemma 4 31B ITgoogle/gemma-4-31b-it	Google	6.7	T	262.144K	$0.09	$0.34	2026-04-02
Kimi K2 Thinkingmoonshotai/kimi-k2-thinking	Moonshot AI	1.8	T	262.144K	$0.4	$2.5	2025-11-06
DeepSeek-R1deepseek/deepseek-r1	DeepSeek	1.1	T	128K	$0.7	$2.5	2025-01-20
Gemma 3 12B ITgoogle/gemma-3-12b-it	Google	0.1	T	131.072K	$0.05	$0.1	2025-03-12
Gemma 3 27B ITgoogle/gemma-3-27b-it	Google	0.1	T	131.072K	$0.08	$0.16	2025-03-12