Browse AI models

104 models tracked

Sort

Families Newest Quality Value Size

Tier

All Edge Consumer Enthusiast Workstation Premier

VRAM

Any 8GB 12GB 24GB 32GB 48GB 64GB 96GB

More filters

Best value - quality per dollar

DeepSeek V4.1 Flash MoE coding reasoning DeepSeek 🇨🇳 China Sep 10

552.0B 16.0B active 1000k ctx 265GB min RAM mit 2 var $0.01/M in

93 92 90

6977 pts/$

DeepSeek V4 Flash 0731 MoE coding reasoning DeepSeek 🇨🇳 China Jul 31 text + metadata

284.0B 13.0B active 1000k ctx 168GB min RAM mit 2 var $0.01/M in

93 91 92 90

6250 pts/$

Mistral Nemo 12B coding chat Mistral AI 🇫🇷 France Jul 18

12.2B 128k ctx 7GB min RAM apache 2.0 2 var $0.02/M in

58 60 62

3735 pts/$

Llama 3.1 8B Instruct coding chat Meta 🇺🇸 USA Jul 23 no marks

8.0B 128k ctx 5GB min RAM llama 3 3 var $0.02/M in

52 55 62

3100 pts/$

GLM-5.3-Flash MoE coding reasoning Zhipu AI 🇨🇳 China Aug 26

320.0B 18.0B active 1000k ctx 100GB min RAM mit 4 var $0.04/M in

93 92 92 91

2528 pts/$

Gemma 4 26B A4B MoE coding reasoning Google 🇺🇸 USA Apr 30 no marks

25.2B 3.8B active 256k ctx 15GB min RAM other 4 var $0.04/M in

85 88 84

2000 pts/$

Qwen3.6 35B A3B MoE coding reasoning Alibaba 🇨🇳 China Apr 22 text + metadata

35.0B 3.0B active 262k ctx 20GB min RAM apache 2.0 2 var $0.05/M in

90 91 95 87

1740 pts/$

GLM 5.2 MoE coding reasoning Zhipu AI 🇨🇳 China Jun 13

744.0B 40.0B active 1000k ctx 240GB min RAM mit 5 var $0.06/M in

91 92 85 88

1544 pts/$

Gemma 3 12B coding reasoning Google 🇺🇸 USA Feb 27 no marks

12.2B 128k ctx 8GB min RAM other 2 var $0.05/M in

62 65 68

1360 pts/$

Llama 3.2 1B Instruct chat general Meta 🇺🇸 USA Sep 25 no marks

1.2B 128k ctx 1GB min RAM llama 3 2 var $0.03/M in

20 25 35

1296 pts/$

Gemma 3 4B chat general Google 🇺🇸 USA Feb 27 no marks

4.3B 128k ctx 3GB min RAM other 2 var $0.05/M in

42 45 55

1100 pts/$

Gemma 3 27B coding reasoning Google 🇺🇸 USA Feb 27 no marks

27.2B 128k ctx 17GB min RAM other 2 var $0.07/M in

68 71 72

1029 pts/$

Llama 3.2 3B Instruct chat general Meta 🇺🇸 USA Sep 25 no marks

3.2B 128k ctx 2GB min RAM llama 3 2 var $0.05/M in

35 38 50

1000 pts/$

Phi-4 14B coding reasoning Microsoft 🇺🇸 USA Dec 12 no marks

14.7B 16k ctx 9GB min RAM mit 3 var $0.07/M in

75 78 70

1000 pts/$

Qwen3 32B coding reasoning Alibaba 🇨🇳 China Apr 28 text + metadata

32.8B 128k ctx 20GB min RAM apache 2.0 4 var $0.08/M in

80 82 78

975 pts/$

Gemma 4 31B coding reasoning Google 🇺🇸 USA Apr 2 no marks

30.7B 256k ctx 19GB min RAM apache 2.0 5 var $0.10/M in

86 89 85

850 pts/$

Llama 3.3 70B Instruct coding reasoning Meta 🇺🇸 USA Dec 6 no marks

70.6B 128k ctx 22GB min RAM llama 3 4 var $0.10/M in

72 77 80

800 pts/$

Qwen3 14B coding reasoning Alibaba 🇨🇳 China Apr 28 text + metadata

14.7B 128k ctx 9GB min RAM apache 2.0 2 var $0.10/M in

72 75 70

700 pts/$

Qwen3 30B A3B MoE coding reasoning Alibaba 🇨🇳 China Apr 28 text + metadata

30.5B 3.0B active 128k ctx 16GB min RAM apache 2.0 2 var $0.12/M in

75 78 72

600 pts/$

Pokee-Isaac 28B coding reasoning Pokee AI 🇺🇸 USA Aug 4

28.0B 10000k ctx 18GB min RAM other 3 var $0.15/M in

90 88 95 88

587 pts/$

Qwen3 8B coding reasoning Alibaba 🇨🇳 China Apr 28 text + metadata

8.2B 128k ctx 5GB min RAM apache 2.0 2 var $0.12/M in

67 70 65

556 pts/$

Qwen3.8-Omni-Flash MoE general reasoning Alibaba 🇨🇳 China Sep 14

125.0B 1000k ctx no local build proprietary $0.15/M in

65 76 80

533 pts/$

GPT-5.6 Luna coding reasoning OpenAI 🇺🇸 USA Aug 5 no marks

1050k ctx no local build proprietary $0.20/M in

82 80 85 82

410 pts/$

DeepSeek V3 0324 MoE coding reasoning DeepSeek 🇨🇳 China Mar 24 text + metadata

671.0B 37.0B active 128k ctx 188GB min RAM mit 2 var $0.25/M in

92 88 87

348 pts/$

Qwen3.6 27B coding reasoning Alibaba 🇨🇳 China Nov 1 text + metadata

27.0B 128k ctx 17GB min RAM apache 2.0 2 var $0.25/M in

85 87 82

328 pts/$

DeepSeek V3.2 Exp MoE coding reasoning DeepSeek 🇨🇳 China Sep 29 text + metadata

685.0B 37.0B active 128k ctx no local build mit $0.27/M in

80 86 83

307 pts/$

DeepSeek V3.1 Terminus MoE coding reasoning DeepSeek 🇨🇳 China Sep 29 text + metadata

685.0B 37.0B active 128k ctx no local build mit $0.27/M in

80 85 82

304 pts/$

LongCat 2.0 MoE coding reasoning Meituan 🇨🇳 China Jul 3

1600.0B 48.0B active 1000k ctx no local build mit $0.30/M in

93 90 86

287 pts/$

DeepSeek V4 Pro MoE coding reasoning DeepSeek 🇨🇳 China Apr 24 text + metadata

1600.0B 49.0B active 1000k ctx no local build mit $0.45/M in

94 93 88 89

198 pts/$

Qwen3 235B A22B MoE coding reasoning Alibaba 🇨🇳 China Apr 28 text + metadata

235.0B 22.0B active 128k ctx 68GB min RAM apache 2.0 2 var $0.46/M in

88 90 85

187 pts/$

Nemotron 3 Ultra MoE coding reasoning NVIDIA 🇺🇸 USA Jun 4

550.0B 55.0B active 262k ctx no local build other $0.50/M in

84 86 85

170 pts/$

Kimi K2 MoE coding reasoning Moonshot AI 🇨🇳 China Jul 11 text + metadata

1000.0B 128k ctx no local build other $0.57/M in

90 88 85

149 pts/$

Kimi K2.7 Code MoE coding reasoning Moonshot AI 🇨🇳 China Jun 16 text + metadata

1000.0B 32.0B active 256k ctx no local build other $0.67/M in

91 89 89 86

128 pts/$

Gemini 3.7 Flash coding reasoning Google 🇺🇸 USA Aug 13

1000k ctx no local build proprietary $0.75/M in

88 88 88 87

116 pts/$

Kimi K3 MoE coding reasoning Moonshot AI 🇨🇳 China Jul 16 text + metadata

2800.0B 104.0B active 1000k ctx 610GB min RAM other 1 var $0.84/M in

94 93 93 90

107 pts/$

Gemini 4 Argon coding agentic Google 🇺🇸 USA Sep 30

1000k ctx no local build proprietary $2.00/M in

96 96 96 94

47 pts/$

GPT-6.1 Sol coding agentic OpenAI 🇺🇸 USA Sep 29

1050k ctx no local build proprietary $2.00/M in

95 93 95 92

46 pts/$

Grok 4.6 coding reasoning xAI 🇺🇸 USA Aug 12

500k ctx no local build proprietary $2.00/M in

93 93 93 92

46 pts/$

Qwen3.8-Max MoE coding reasoning Alibaba 🇨🇳 China Aug 3 text + metadata

2400.0B 95.0B active 1000k ctx no local build apache 2.0 $2.00/M in

88 91 91

46 pts/$

Claude Sonnet 5.5 coding agentic Anthropic 🇺🇸 USA Sep 28

1000k ctx no local build proprietary $2.00/M in

94 92 93 91

46 pts/$

GPT-5.6 Terra coding reasoning OpenAI 🇺🇸 USA Aug 5 no marks

1050k ctx no local build proprietary $2.00/M in

90 90 90 90

45 pts/$

Claude Sonnet 5 coding reasoning Anthropic 🇺🇸 USA Jul 1

1000k ctx no local build proprietary $2.00/M in

90 88 90 88

44 pts/$

GLM 5.3 MoE coding reasoning Zhipu AI 🇨🇳 China Aug 14

743.0B 40.0B active 1000k ctx no local build mit $2.80/M in

94 93 90 92

33 pts/$

Command R+ 104B reasoning writing Cohere 🇨🇦 Canada Apr 4

104.0B 128k ctx no local build cc by 4.0 $2.50/M in

60 70 75

30 pts/$

Claude Opus 5 coding reasoning Anthropic 🇺🇸 USA Aug 7 text + metadata

1000k ctx no local build proprietary $5.00/M in

95 95 95 95

19 pts/$

GPT-5.6 Sol coding reasoning OpenAI 🇺🇸 USA Aug 5 no marks

1050k ctx no local build proprietary $5.00/M in

95 95 95 95

19 pts/$

Claude Opus 4.8 coding reasoning Anthropic 🇺🇸 USA May 29

1000k ctx no local build proprietary $5.00/M in

94 93 92 93

19 pts/$

Claude Fable 5 coding reasoning Anthropic 🇺🇸 USA Jun 10

1000k ctx no local build proprietary $10.00/M in

95 95 95 95

10 pts/$

Claude Fable 5.1 coding reasoning Anthropic 🇺🇸 USA Sep 1 text + metadata

1000k ctx no local build proprietary $10.00/M in

96 96 95 95

10 pts/$

Claude Opus 5.5 coding agentic Anthropic 🇺🇸 USA Sep 22

1000k ctx no local build proprietary $10.00/M in

96 95 96 94

9 pts/$

Flux 3 Action robotics world-model Black Forest Labs 🇩🇪 Germany Sep 24

7.0B 17GB min RAM flux kommunity 1 var -

pplx-embed-v2-late-9b embeddings retrieval Perplexity 🇺🇸 USA Oct 7

8.4B 262k ctx 17GB min RAM mit 1 var -

GLiNER2.5-Decide classification routing Fastino 🇺🇸 USA Sep 24

340M 1GB min RAM apache 2.0 2 var -

Qwen-Image-2.1 image-generation image-editing Alibaba 🇨🇳 China Sep 20

7.0B 16GB min RAM qwen research 1 var -

MiMo-V2.6-Flash MoE agentic coding Xiaomi 🇨🇳 China Sep 21

309.0B 15.0B active 1024k ctx 80GB min RAM mit 2 var -

78 77 80 76

CUA-S1-FORMS general trycua Sep 18

no local build mit (source only no weights published) -

Pareto research coding Unbiased AI 🇺🇸 USA Sep 17

no local build proprietary hosted -

Union Alpha MoE coding reasoning Sep 16

no local build proprietary -

92 88 85

Jev general chat TypeSafe Sep 15 no marks

60k ctx no local build proprietary $0.04/M in

d1-omni-600M audio vision Liquid AI 🇺🇸 USA Oct 7

590M 128k ctx 2GB min RAM liquid ai license 1 var -

d1-3B multimodal edge Liquid AI 🇺🇸 USA Oct 7

3.1B 32k ctx 4GB min RAM liquid ai license 1 var -

Clef-Omni MoE decision-model omni Cloudflare 🇺🇸 USA Oct 9

35.3B 3.0B active 65k ctx 24GB min RAM apache 2.0 1 var -

Mellum2.1 12B Thinking MoE coding completion JetBrains Oct 8

12.2B 2.5B active 131k ctx 10GB min RAM apache 2.0 2 var -

Torchcast Decision 12B decision-model classification Torchcast 🇺🇸 USA Oct 2

12.0B 262k ctx 8GB min RAM cc by nc 4.0 1 var -

EmbeddingGemma 2 embeddings rag Google 🇺🇸 USA Oct 6

740M 262k ctx 2GB min RAM apache 2.0 2 var -

JEV-27B-VL decision-model vision AutoTrust 🇺🇸 USA Sep 30

27.8B 262k ctx 16GB min RAM apache 2.0 2 var -

GEV-26B-Decide decision-model classification AutoTrust 🇺🇸 USA Oct 2

25.8B 262k ctx 16GB min RAM apache 2.0 2 var -

pplx-decider-v1.1-27b decision-model classification Perplexity 🇺🇸 USA Oct 5

26.1B 262k ctx 16GB min RAM apache 2.0 2 var -

Clef-flash decision-model classification Cloudflare 🇺🇸 USA Oct 1

9.4B 262k ctx 8GB min RAM apache 2.0 1 var -

Clef decision-model classification Cloudflare 🇺🇸 USA Oct 1

27.4B 262k ctx 16GB min RAM apache 2.0 2 var -

Kolibri 1 MoE coding agentic Aleph Alpha Oct 3

1048k ctx 156GB min RAM apache 2.0 1 var -

62 68 66 54

MiniMax M3 coding agentic MiniMax Jun 2

1048k ctx 128GB min RAM minimax community 4 var -

MiniMax M2.7 coding agentic MiniMax Apr 9

200k ctx 61GB min RAM minimax community 3 var -

Ember-1 agentic coding Fireworks Research 🇺🇸 USA Sep 23

no local build proprietary -

92 88 88 85

Nemotron 3 Diarization audio diarization NVIDIA 🇺🇸 USA Sep 23

100M 0GB min RAM openmdw 1.1 2 var -

Mixtral 8x7B Instruct MoE coding chat Mistral AI 🇫🇷 France Dec 11

46.7B 12.9B active 32k ctx 19GB min RAM apache 2.0 2 var -

62 65 68

Laya general chat ConvAI Innovations Sep 18 no marks

420M 1k ctx 1GB min RAM apache 2.0 3 var -

Phi-4 Mini coding reasoning Microsoft 🇺🇸 USA Feb 1 no marks

3.8B 128k ctx 3GB min RAM mit 2 var -

55 58 52

OpenJev general chat Undisclosed Sep 16 no marks

600M 8k ctx 1GB min RAM mit 3 var -

Jeff classification routing mstrasser (firelex) Sep 28

2.0B 262k ctx 1GB min RAM apache 2.0 2 var -

Gemma 3 270M chat general Google 🇺🇸 USA Aug 14 no marks

270M 32k ctx 1GB min RAM other 2 var -

12 15 25

Gemma 3 1B chat general Google 🇺🇸 USA Feb 27 no marks

1.0B 32k ctx 1GB min RAM other 2 var -

22 26 38

Ternary Bonsai 2 27B general chat Prism ML Sep 17 no marks

27.4B 262k ctx no local build apache 2.0 -

Llama 3.1 405B coding reasoning Meta 🇺🇸 USA Jul 23 no marks

405.0B 128k ctx no local build llama 3 -

82 85 84

Ornith-1.5-35B-A3B MoE coding reasoning Ornith AI 🇺🇸 USA Aug 18

36.0B 3.0B active 262k ctx 22GB min RAM mit 5 var -

91 89 85 86

Ornith-1.5-9B coding reasoning Ornith AI 🇺🇸 USA Aug 18

9.0B 262k ctx 6GB min RAM mit 5 var -

78 76 78 74

Nemotron 3.5 Lightning MoE coding agentic NVIDIA 🇺🇸 USA Aug 11

31.6B 3.6B active 1000k ctx 34GB min RAM other 3 var -

78 76 80 74

Ornith-1.5-397B MoE coding reasoning Ornith AI 🇺🇸 USA Aug 18

403.0B 262k ctx 248GB min RAM mit 4 var -

93 91 88 89

Qwen3 4B coding reasoning Alibaba 🇨🇳 China Apr 28 text + metadata

4.0B 32k ctx 3GB min RAM apache 2.0 1 var -

58 60 56

LFM2.5 8B A1B MoE chat general Liquid AI 🇺🇸 USA Sep 1

8.0B 1.0B active 32k ctx 3GB min RAM apache 2.0 1 var -

45 50 58

Gemma 3n E4B chat general Google 🇺🇸 USA Jun 26 no marks

4.0B 32k ctx 8GB min RAM other 2 var -

46 48 58

Gemma 3n E2B chat general Google 🇺🇸 USA Jun 26 no marks

2.0B 32k ctx 6GB min RAM other 2 var -

35 38 48

Gemma 4 12B coding reasoning Google 🇺🇸 USA Jun 1 no marks

12.0B 128k ctx 7GB min RAM other 2 var -

70 74 72

SWE-2 MoE coding agentic Cognition 🇺🇸 USA Sep 10

2800.0B 104.0B active no local build proprietary -

95 88 95 85

Nex-N2.5-Max MoE general reasoning Nex AGI Sep 8

1600.0B 49.0B active 1050k ctx no local build -

Qwen3.8-Flash-Next MoE coding reasoning Alibaba 🇨🇳 China Aug 26

180.0B 6.0B active 262k ctx 24GB min RAM qwen community 1.0 3 var -

92 92 93 89

Qwen3.8-27B coding reasoning Alibaba 🇨🇳 China Aug 5

27.0B 262k ctx 8GB min RAM apache 2.0 4 var -

88 89 94 85

Nemotron 3 Nano 4B general NVIDIA 🇺🇸 USA Jun 5

4.0B 1000k ctx 3GB min RAM other 1 var -

Muse Glimmer 30B coding agentic Meta 🇺🇸 USA Aug 10

30.0B 128k ctx 24GB min RAM apache 2.0 3 var -

Muse Spark 1.2 coding agentic Meta 🇺🇸 USA Aug 5 no marks

1000k ctx no local build proprietary $1.25/M in

Needle 3 general Cactus Compute Sep 17

120M 8k ctx no local build -

K2 Horizon 375B general IFM Technologies Sep 3

375.0B no local build -

Xing4.0-29B-A4B MoE agentic coding China Telecom AI 🇨🇳 China Sep 22

29.0B 4.0B active 256k ctx 15GB min RAM apache 2.0 2 var -

75 73 78 72

MiMo-V2.6-Pro MoE agentic coding Xiaomi 🇨🇳 China Sep 21

1020.0B 42.0B active 1024k ctx 2040GB min RAM mit 1 var -

86 85 88 84

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.