L LLM Cloud Hub
Context window

Medium-context LLMs — 32k to 200k tokens

The standard production sweet spot: enough room for full conversations, retrieved RAG chunks, and reasonably-sized codebase snippets without paying for premium long-context pricing.

169 models match this tag · sorted by lowest total cost.

# Model Provider Context In $/1M Out $/1M
1 CoBuddy (free) Baidu Qianfan 131k 0.0000 0.0000
2 GLM 4.5 Air (free) Z.ai 131k 0.0000 0.0000
3 Hermes 3 405B Instruct (free) Nous 131k 0.0000 0.0000
4 LFM2.5-1.2B-Instruct (free) LiquidAI 33k 0.0000 0.0000
5 LFM2.5-1.2B-Thinking (free) LiquidAI 33k 0.0000 0.0000
6 Laguna M.1 (free) Poolside 131k 0.0000 0.0000
7 Laguna XS.2 (free) Poolside 131k 0.0000 0.0000
8 Llama 3.2 3B Instruct (free) Meta 131k 0.0000 0.0000
9 Llama 3.3 70B Instruct (free) Meta 66k 0.0000 0.0000
10 MiniMax M2.5 (free) MiniMax 197k 0.0000 0.0000
11 Nemotron Nano 12B 2 VL (free) NVIDIA 128k 0.0000 0.0000
12 Nemotron Nano 9B V2 (free) NVIDIA 128k 0.0000 0.0000
13 Qianfan-OCR-Fast (free) Baidu Qianfan 66k 0.0000 0.0000
14 Uncensored (free) Venice 33k 0.0000 0.0000
15 gpt-oss-120b (free) OpenAI 131k 0.0000 0.0000
16 gpt-oss-20b (free) OpenAI 131k 0.0000 0.0000
17 Mistral Nemo Mistral 131k 0.0200 0.0300
18 Gemma 3 4B Google 131k 0.0400 0.0800
19 Granite 4.0 Micro IBM 131k 0.0170 0.1100
20 Mistral Small 3 Mistral 33k 0.0500 0.0800
21 Qwen2.5 7B Instruct Qwen 33k 0.0400 0.1000
22 LFM2-24B-A2B LiquidAI 33k 0.0300 0.1200
23 Granite 4.1 8B IBM 131k 0.0500 0.1000
24 Qwen-Turbo Qwen 131k 0.0325 0.1300
25 Gemma 3 12B Google 131k 0.0400 0.1300
26 gpt-oss-20b OpenAI 131k 0.0300 0.1400
27 Nova Micro 1.0 Amazon 128k 0.0350 0.1400
28 Gemma 3n 4B Google 33k 0.0600 0.1200
29 Command R7B (12-2024) Cohere 128k 0.0375 0.1500
30 Trinity Mini Arcee AI 131k 0.0450 0.1500
31 GLM 4 32B Z.ai 128k 0.1000 0.1000
32 Ministral 3 3B 2512 Mistral 131k 0.1000 0.1000
33 Nemotron Nano 9B V2 NVIDIA 131k 0.0400 0.1600
34 gpt-oss-120b OpenAI 131k 0.0390 0.1800
35 Llama 3.2 1B Instruct Meta 60k 0.0270 0.2000
36 Gemma 3 27B Google 131k 0.0800 0.1600
37 Mistral Small 3.2 24B Mistral 128k 0.0750 0.2000
38 Rnj 1 Instruct EssentialAI 33k 0.1500 0.1500
39 Reka Flash 3 Rekaai 66k 0.1000 0.2000
40 UI-TARS 7B ByteDance 128k 0.1000 0.2000
41 Qwen3 14B Qwen 41k 0.1000 0.2400
42 Qwen3 Coder 30B A3B Instruct Qwen 160k 0.0700 0.2700
43 ERNIE 4.5 21B A3B Baidu Qianfan 120k 0.0700 0.2800
44 ERNIE 4.5 21B A3B Thinking Baidu Qianfan 131k 0.0700 0.2800
45 Llama Guard 4 12B Meta 164k 0.1800 0.1800
46 Spotlight Arcee AI 131k 0.1800 0.1800
47 Qwen3 32B Qwen 41k 0.0800 0.2800
48 gpt-oss-safeguard-20b OpenAI 131k 0.0750 0.3000
49 Llama 3.2 3B Instruct Meta 80k 0.0510 0.3400
50 Devstral Small 1.1 Mistral 131k 0.1000 0.3000
51 Voxtral Small 24B 2507 Mistral 32k 0.1000 0.3000
52 Llama 3.3 70B Instruct Meta 131k 0.1000 0.3200
53 Phi 4 Mini Instruct Microsoft 128k 0.0800 0.3500
54 Qwen3 8B Qwen 41k 0.0500 0.4000
55 Qwen3 30B A3B Thinking 2507 Qwen 131k 0.0800 0.4000
56 Llama 3.2 11B Vision Instruct Meta 131k 0.2450 0.2450
57 Llama 3.3 Nemotron Super 49B V1.5 NVIDIA 131k 0.1000 0.4000
58 Llama Guard 3 8B Meta 131k 0.4800 0.0300
59 Qwen3 VL 32B Instruct Qwen 131k 0.1040 0.4160
60 Hermes 4 70B Nous 131k 0.1300 0.4000
61 Qwen3 30B A3B Qwen 41k 0.0900 0.4500
62 Tongyi DeepResearch 30B A3B Alibaba 131k 0.0900 0.4500
63 Qwen VL Plus Qwen 131k 0.1365 0.4095
64 Qwen3 VL 8B Instruct Qwen 131k 0.0800 0.5000
65 R1 Distill Qwen 32B DeepSeek 33k 0.2900 0.2900
66 Hermes 3 70B Instruct Nous 131k 0.3000 0.3000
67 Rocinante 12B TheDrummer 33k 0.1700 0.4300
68 Trinity Large Preview Arcee AI 131k 0.1500 0.4500
69 DeepSeek V3.2 DeepSeek 131k 0.2520 0.3780
70 DeepSeek V3.1 Nex N1 Nex AGI 131k 0.1350 0.5000
71 Olmo 3 32B Think AllenAI 66k 0.1500 0.5000
72 Qwen3 VL 30B A3B Instruct Qwen 131k 0.1300 0.5200
73 DeepSeek V3.2 Exp DeepSeek 164k 0.2700 0.4100
74 Hunyuan A13B Instruct Tencent 131k 0.1400 0.5700
75 DeepSeek V3.2 Speciale DeepSeek 164k 0.2870 0.4310
76 Command R (08-2024) Cohere 128k 0.1500 0.6000
77 GPT-4o-mini OpenAI 128k 0.1500 0.6000
78 GPT-4o-mini (2024-07-18) OpenAI 128k 0.1500 0.6000
79 GPT-4o-mini Search Preview OpenAI 128k 0.1500 0.6000
80 Solar Pro 3 Upstage 128k 0.1500 0.6000
81 Qwen2.5 72B Instruct Qwen 33k 0.3600 0.4000
82 Cydonia 24B V4.1 TheDrummer 131k 0.3000 0.5000
83 Grok 3 Mini xAI 131k 0.3000 0.5000
84 Grok 3 Mini Beta xAI 131k 0.3000 0.5000
85 Llama 3.1 70B Instruct Meta 131k 0.4000 0.4000
86 Saba Mistral 33k 0.2000 0.6000
87 UnslopNemo 12B TheDrummer 33k 0.4000 0.4000
88 Qwen3 Next 80B A3B Thinking Qwen 131k 0.0975 0.7800
89 Mistral Small 3.1 24B Mistral 128k 0.3500 0.5600
90 DeepSeek V3 0324 DeepSeek 164k 0.2000 0.7700
91 GLM 4.5 Air Z.ai 131k 0.1300 0.8500
92 DeepSeek V3.1 DeepSeek 164k 0.2100 0.7900
93 Mercury 2 Inception 128k 0.2500 0.7500
94 Qwen2.5 VL 72B Instruct Qwen 32k 0.2500 0.7500
95 GLM 4.6V Z.ai 131k 0.3000 0.9000
96 DeepSeek V3 DeepSeek 164k 0.3200 0.8900
97 DeepSeek V3.1 Terminus DeepSeek 164k 0.2700 0.9500
98 MiniMax M2.1 MiniMax 197k 0.2900 0.9500
99 WizardLM-2 8x22B Microsoft 66k 0.6200 0.6200
100 MiniMax M2 MiniMax 197k 0.2550 1.0000
101 MiniMax M2.5 MiniMax 197k 0.1500 1.1500
102 Coder Large Arcee AI 33k 0.5000 0.8000
103 INTELLECT-3 Prime Intellect 131k 0.2000 1.1000
104 Skyfall 36B V2 TheDrummer 33k 0.5500 0.8000
105 ERNIE 4.5 300B A47B Baidu Qianfan 123k 0.2800 1.1000
106 Llama 3.3 Euryale 70B Sao10K 131k 0.6500 0.7500
107 MiniMax M2.7 MiniMax 197k 0.2600 1.2000
108 Qwen3 VL 8B Thinking Qwen 131k 0.1170 1.3650
109 MiniMax M2-her MiniMax 66k 0.3000 1.2000
110 R1 Distill Llama 70B DeepSeek 131k 0.7000 0.8000
111 Qwen3 235B A22B Thinking 2507 Qwen 131k 0.1495 1.4950
112 Perceptron Mk1 Perceptron 33k 0.1500 1.5000
113 Qwen2.5 Coder 32B Instruct Qwen 33k 0.6600 1.0000
114 ERNIE 4.5 VL 424B A47B Baidu Qianfan 123k 0.4200 1.2500
115 Qwen3 VL 30B A3B Thinking Qwen 131k 0.1300 1.5600
116 Llama 3.1 Euryale 70B v2.2 Sao10K 131k 0.8500 0.8500
117 Virtuoso Large Arcee AI 131k 0.7500 1.2000
118 Hermes 3 405B Instruct Nous 131k 1.0000 1.0000
119 Morph V3 Fast Morph 82k 0.8000 1.2000
120 Sonar Perplexity 127k 1.0000 1.0000
121 Aion-1.0-Mini AionLabs 131k 0.7000 1.4000
122 Qwen3 235B A22B Qwen 131k 0.4550 1.8200
123 Devstral Medium Mistral 131k 0.4000 2.0000
124 GLM 4.5V Z.ai 66k 0.6000 1.8000
125 Mistral Medium 3 Mistral 131k 0.4000 2.0000
126 Mistral Medium 3.1 Mistral 131k 0.4000 2.0000
127 Aion-2.0 AionLabs 131k 0.8000 1.6000
128 Aion-RP 1.0 (8B) AionLabs 33k 0.8000 1.6000
129 Cogito v2.1 671B Deep Cogito 128k 1.2500 1.2500
130 Qwen VL Max Qwen 131k 0.5200 2.0800
131 R1 0528 DeepSeek 164k 0.5000 2.1500
132 Nano Banana (Gemini 2.5 Flash Image) Google 33k 0.3000 2.5000
133 GLM 4.5 Z.ai 131k 0.6000 2.2000
134 Qwen3 VL 235B A22B Thinking Qwen 131k 0.2600 2.6000
135 Kimi K2 0711 MoonshotAI 131k 0.5700 2.3000
136 GPT Audio Mini OpenAI 128k 0.6000 2.4000
137 R1 DeepSeek 64k 0.7000 2.5000
138 Qianfan-OCR-Fast Baidu Qianfan 66k 0.6800 2.8100
139 Nano Banana 2 (Gemini 3.1 Flash Image Preview) Google 66k 0.5000 3.0000
140 Hermes 4 405B Nous 131k 1.0000 3.0000
141 Maestro Reasoning Arcee AI 131k 0.9000 3.3000
142 Switchpoint Router Switchpoint 131k 0.8500 3.4000
143 Qwen-Max Qwen 33k 1.0400 4.1600
144 Mistral Large Mistral 128k 2.0000 6.0000
145 Mistral Large 2407 Mistral 131k 2.0000 6.0000
146 Mistral Large 2411 Mistral 131k 2.0000 6.0000
147 Mixtral 8x22B Instruct Mistral 66k 2.0000 6.0000
148 Pixtral Large 2411 Mistral 131k 2.0000 6.0000
149 Sonar Deep Research Perplexity 128k 2.0000 8.0000
150 Sonar Reasoning Pro Perplexity 128k 2.0000 8.0000
151 GPT-5 Chat OpenAI 128k 1.2500 10.0000
152 GPT-5.1 Chat OpenAI 128k 1.2500 10.0000
153 Aion-1.0 AionLabs 131k 4.0000 8.0000
154 Command R+ (08-2024) Cohere 128k 2.5000 10.0000
155 GPT Audio OpenAI 128k 2.5000 10.0000
156 GPT-4o OpenAI 128k 2.5000 10.0000
157 GPT-4o (2024-08-06) OpenAI 128k 2.5000 10.0000
158 GPT-4o (2024-11-20) OpenAI 128k 2.5000 10.0000
159 GPT-4o Audio OpenAI 128k 2.5000 10.0000
160 GPT-4o Search Preview OpenAI 128k 2.5000 10.0000
161 Nano Banana Pro (Gemini 3 Pro Image Preview) Google 66k 2.0000 12.0000
162 GPT-5.2 Chat OpenAI 128k 1.7500 14.0000
163 GPT-5.3 Chat OpenAI 128k 1.7500 14.0000
164 Grok 3 xAI 131k 3.0000 15.0000
165 Grok 3 Beta xAI 131k 3.0000 15.0000
166 GPT-4o (2024-05-13) OpenAI 128k 5.0000 15.0000
167 GPT-4 Turbo OpenAI 128k 10.0000 30.0000
168 GPT-4 Turbo (older v1106) OpenAI 128k 10.0000 30.0000
169 GPT-4 Turbo Preview OpenAI 128k 10.0000 30.0000

Related

Keyboard shortcuts

?
Show this overlay
/
Focus the first form field
g h
Go to / (home)
g b
Go to /best-llm-for
g c
Go to /cost
g s
Go to /self-hosted
g x
Go to /compliance
Esc
Close any overlay

Inspired by Linear and GitHub conventions. The two-key sequences (g then h) work within ~1 second.