Browse AI models

21 models tracked - grouped by family, best families first

Families Newest Quality Value Size
All Edge Consumer Enthusiast Workstation Premier
Any 8GB 12GB 24GB 32GB 48GB 64GB 96GB
More filters

Claude Fable

🇺🇸 Anthropic 2 models best 95
Claude Fable 5.1 Sep 1, 2026 text + metadata
1000k ctx no local build proprietary $10.00/M in
95
10 pts/$
Claude Fable 5 Jun 10, 2026
1000k ctx no local build proprietary $10.00/M in
95
10 pts/$

Claude Opus

🇺🇸 Anthropic 2 models best 95
Claude Opus 5 Aug 7, 2026 text + metadata
1000k ctx no local build proprietary $5.00/M in
95
19 pts/$
Claude Opus 4.8 May 29, 2026
1000k ctx no local build proprietary $5.00/M in
93
19 pts/$

GPT-5.6

🇺🇸 OpenAI 1 model best 95
GPT-5.6 Sol Aug 5, 2026 no marks
1050k ctx no local build proprietary $5.00/M in
95
19 pts/$

Grok

🇺🇸 xAI 1 model best 92
Grok 4.6 Aug 12, 2026
500k ctx no local build proprietary $2.00/M in
92
46 pts/$

Qwen

🇨🇳 Alibaba 1 model best 91
Qwen3.8-Max MoE Aug 3, 2026 text + metadata
2400.0B 95.0B active 1000k ctx no local build apache 2.0 $2.00/M in
91
46 pts/$

Other labs (Kimi · LFM · Command R+)

🇨🇳 Moonshot AI 3 models best 90
Kimi K3 MoE Jul 16, 2026 text + metadata
2800.0B 104.0B active 1000k ctx 610GB min RAM other 1 var $0.68/M in
90
132 pts/$
Kimi K2.7 Code MoE Jun 16, 2026 text + metadata
1000.0B 32.0B active 256k ctx no local build other $0.66/M in
86
131 pts/$
Kimi K2 MoE Jul 11, 2025 text + metadata
1000.0B 128k ctx no local build other $0.57/M in
85
149 pts/$

DeepSeek

🇨🇳 DeepSeek 1 model best 89
DeepSeek V4 Pro MoE Apr 24, 2026 text + metadata
1600.0B 49.0B active 1000k ctx no local build mit $0.25/M in
89
356 pts/$

LongCat

🇨🇳 Meituan 1 model best 86
LongCat 2.0 MoE Jul 3, 2026
1600.0B 48.0B active 1000k ctx no local build mit $0.30/M in
86
287 pts/$

Ember

🇺🇸 Fireworks Research 1 model best 85
Ember-1 Sep 23, 2026
no local build proprietary
85

Nemotron

🇺🇸 NVIDIA 1 model best 85
Nemotron 3 Ultra MoE Jun 4, 2026
550.0B 55.0B active 262k ctx no local build other $0.50/M in
85
170 pts/$

Swe

🇺🇸 Cognition 1 model best 85
SWE-2 MoE Sep 10, 2026
2800.0B 104.0B active no local build proprietary
85

Llama

🇺🇸 Meta 1 model best 84
Llama 3.1 405B Jul 23, 2024 no marks
405.0B 128k ctx no local build llama 3
84

Mimo

🇨🇳 Xiaomi 1 model best 84
MiMo-V2.6-Pro MoE Sep 21, 2026
1020.0B 42.0B active 1024k ctx 2040GB min RAM mit 1 var
84

Muse

🇺🇸 Meta 1 model best 55
Muse Spark 1.2 Aug 5, 2026 no marks
1000k ctx no local build proprietary $1.25/M in

Pareto

🇺🇸 Unbiased AI 1 model best 40
Pareto Sep 17, 2026
no local build proprietary hosted

K2 Horizon

IFM Technologies 1 model best 0
K2 Horizon 375B Sep 3, 2026
375.0B params no local build

Nex N2 5

Nex AGI 1 model best 0
Nex-N2.5-Max MoE Sep 8, 2026
1600.0B 49.0B active 1050k ctx no local build

FAQ

What is the cheapest LLM API?

Open-weight models like DeepSeek, Qwen, and GLM are the cheapest LLM APIs - often under $1 per million input tokens. Sort the table by best value to rank quality per dollar.

Which LLM has the best coding score?

Coding scores vary by benchmark; filter the table by use case coding to see coding_score per model, or open any model's page for its benchmark breakdown.

How do I compare LLM pricing?

This table shows per-million-token input and output prices across providers. Open a model's pricing page for live rates, cached-input discounts, and price history.