Eliminating the 4 Hidden Taxes: AI Tokens, Manual Work, SaaS Cliffs & AI Scrapers Sponsor this header →
Open Weights

Cheapest Open-Weight LLM APIs (Llama, DeepSeek, Qwen, Mistral)

Open-weight models combine zero vendor lock-in with ultra-competitive serverless pricing. Start on a managed API gateway and move seamlessly to dedicated GPUs when scale warrants.

#1 Ranked
Google: Gemma 4 26B A4B (free)
Free / 1M blended
262K context • Google
#2 Ranked
Google: Gemma 4 31B (free)
Free / 1M blended
262K context • Google
#3 Ranked
Meta: Llama 3.1 8B Instruct
$0.025 / 1M blended
131K context • Meta Llama
#ModelProviderInput / 1MOutput / 1MBlendedContext
1 Google: Gemma 4 26B A4B (free)
FreeVisionOpen Weight
Google Free Free Free 262K
2 Google: Gemma 4 31B (free)
FreeVisionOpen Weight
Google Free Free Free 262K
3 Meta: Llama 3.1 8B Instruct
Open Weight
Meta Llama $0.02 $0.04 $0.025 131K
4 Mistral: Mistral Nemo
Open Weight
Mistral AI $0.029 $0.03 $0.029 131K
5 Qwen: Qwen3.7 Flash
ReasoningVisionOpen Weight
Qwen $0.03 $0.13 $0.055 1M
6 Google: Gemma 3 4B
VisionOpen Weight
Google $0.05 $0.10 $0.063 131K
7 DeepSeek: DeepSeek V4 Flash Latest
Open Weight
DeepSeek $0.044 $0.132 $0.066 1.05M
8 Google: Gemma 3 12B
VisionOpen Weight
Google $0.05 $0.15 $0.075 131K
9 DeepSeek: DeepSeek V4.1 Flash
VisionOpen Weight
DeepSeek $0.05 $0.199 $0.087 1.05M
10 Microsoft: Phi 4
Open Weight
Microsoft $0.07 $0.14 $0.087 16K
11 Google: Gemma 4 26B A4B
VisionOpen Weight
Google $0.068 $0.225 $0.107 262K
12 DeepSeek: DeepSeek V4 Flash 0731
Open Weight
DeepSeek $0.044 $0.30 $0.108 1.05M
13 DeepSeek: DeepSeek V4 Flash 0423
Open Weight
DeepSeek $0.09 $0.18 $0.113 1.05M
14 Qwen: Qwen3.5-Flash
VisionOpen Weight
Qwen $0.065 $0.26 $0.114 1M
15 Meta: Llama 3.2 3B Instruct
Open Weight
Meta Llama $0.05 $0.33 $0.12 131K
16 Qwen: Qwen3 Coder 30B A3B Instruct
Open Weight
Qwen $0.07 $0.28 $0.122 262K
17 Qwen: Qwen3 32B
Open Weight
Qwen $0.08 $0.28 $0.13 131K
18 Meta: Llama 4 Scout
VisionOpen Weight
Meta Llama $0.10 $0.30 $0.15 1.31M
19 Qwen: Qwen3 30B A3B Instruct 2507
Open Weight
Qwen $0.10 $0.30 $0.15 262K
20 Qwen: Qwen3 14B
Open Weight
Qwen $0.12 $0.24 $0.15 41K
21 DeepSeek: DeepSeek Flash Latest
VisionOpen Weight
DeepSeek $0.036 $0.50 $0.152 1.05M
22 Google: Gemma 3 27B
VisionOpen Weight
Google $0.08 $0.45 $0.172 131K
23 Meta: Llama Guard 4 12B
VisionOpen Weight
Meta Llama $0.18 $0.18 $0.18 164K
24 Qwen: Qwen3.5-9B
VisionOpen Weight
Qwen $0.17 $0.25 $0.19 262K
25 Qwen: Qwen3 30B A3B
Open Weight
Qwen $0.12 $0.50 $0.215 41K
26 Qwen: Qwen3.8 Flash
ReasoningVisionOpen Weight
Qwen $0.15 $0.47 $0.23 1M
27 Qwen: Qwen3.8 Omni Flash
ReasoningVisionOpen Weight
Qwen $0.15 $0.47 $0.23 1M
28 Google: Gemma 4 31B
VisionOpen Weight
Google $0.20 $0.40 $0.25 262K
29 DeepSeek: DeepSeek V4.1 Flash 1017
VisionOpen Weight
DeepSeek $0.15 $0.60 $0.263 1.05M
30 Qwen: Qwen3 VL 30B A3B Instruct
VisionOpen Weight
Qwen $0.15 $0.60 $0.263 262K
31 Cohere: Command R (08-2024)
Open Weight
Cohere $0.15 $0.60 $0.263 128K
32 Qwen: Qwen3 Coder Next
Open Weight
Qwen $0.12 $0.80 $0.29 262K
33 DeepSeek: DeepSeek V3.2
Open Weight
DeepSeek $0.26 $0.38 $0.29 164K
34 Qwen: Qwen3.6 35B A3B
VisionOpen Weight
Qwen $0.10 $0.90 $0.30 262K
35 Qwen: Qwen3 235B A22B Instruct 2507
Open Weight
Qwen $0.14 $0.80 $0.305 262K
36 DeepSeek: DeepSeek V3.2 Exp
Open Weight
DeepSeek $0.27 $0.41 $0.305 164K
37 DeepSeek: DeepSeek V4 Flash Vision Exp
VisionOpen Weight
DeepSeek $0.216 $0.647 $0.323 1.05M
38 Qwen: Qwen3 Next 80B A3B Instruct
Open Weight
Qwen $0.10 $1.10 $0.35 262K
39 Qwen: Qwen3.5-35B-A3B
VisionOpen Weight
Qwen $0.14 $1.00 $0.355 262K
40 Qwen2.5 72B Instruct
Open Weight
Qwen $0.36 $0.40 $0.37 33K
41 Qwen: Qwen3 VL 8B Instruct
VisionOpen Weight
Qwen $0.25 $0.75 $0.375 262K
42 Qwen: Qwen-Plus
Open Weight
Qwen $0.26 $0.78 $0.39 1M
43 Qwen: Qwen3 Coder Flash
Open Weight
Qwen $0.195 $0.975 $0.39 1M
44 Qwen: Qwen3.6 Flash
VisionOpen Weight
Qwen $0.188 $1.13 $0.422 1M
45 DeepSeek: DeepSeek V3.1
ReasoningOpen Weight
DeepSeek $0.25 $0.95 $0.425 164K
46 DeepSeek: DeepSeek V3 0324
Open Weight
DeepSeek $0.25 $1.00 $0.438 164K
47 DeepSeek: DeepSeek V3
Open Weight
DeepSeek $0.257 $1.03 $0.45 164K
48 DeepSeek: DeepSeek V3.1 Terminus
Open Weight
DeepSeek $0.27 $1.00 $0.453 164K
49 Qwen: Qwen3 Coder 480B A35B
Open Weight
Qwen $0.30 $1.00 $0.475 262K
50 Meta: Llama 4 Maverick
VisionOpen Weight
Meta Llama $0.35 $1.00 $0.512 524K
51 Qwen: Qwen3.8 27B
VisionOpen Weight
Qwen $0.06 $1.96 $0.535 1.02M
52 Qwen: Qwen3.5-27B
VisionOpen Weight
Qwen $0.195 $1.56 $0.536 262K
53 Qwen: Qwen3.7 Plus
VisionOpen Weight
Qwen $0.32 $1.28 $0.56 1M
54 Qwen: Qwen3.5 Plus 2026-02-15
VisionOpen Weight
Qwen $0.26 $1.56 $0.585 1M
55 Qwen: Qwen3 VL 235B A22B Instruct
VisionOpen Weight
Qwen $0.21 $1.90 $0.632 262K
56 Google: Gemma 2 27B
Open Weight
Google $0.65 $0.65 $0.65 8K
57 Qwen: Qwen3.5 Plus 2026-04-20
VisionOpen Weight
Qwen $0.30 $1.80 $0.675 1M
58 Meta: Llama 3.3 70B Instruct
Open Weight
Meta Llama $0.71 $0.71 $0.71 131K
59 Qwen: Qwen3.5-122B-A10B
VisionOpen Weight
Qwen $0.26 $2.08 $0.715 262K
60 Meta: Llama 3.1 70B Instruct
Open Weight
Meta Llama $0.72 $0.72 $0.72 131K
61 Qwen: Qwen3.6 Plus
VisionOpen Weight
Qwen $0.325 $1.95 $0.731 1M
62 Qwen2.5 Coder 32B Instruct
Open Weight
Qwen $0.66 $1.00 $0.745 33K
63 Qwen: Qwen2.5 VL 72B Instruct
VisionOpen Weight
Qwen $0.80 $1.00 $0.85 128K
64 DeepSeek: R1 0528
ReasoningOpen Weight
DeepSeek $0.571 $2.29 $1.00 164K
65 AionLabs: Aion-RP 1.0 (8B)
Open Weight
Aion Labs $0.80 $1.60 $1.00 33K
66 Qwen: Qwen3.6 27B
VisionOpen Weight
Qwen $0.32 $3.20 $1.04 262K
67 DeepSeek: DeepSeek V4 Pro 0423
Open Weight
DeepSeek $0.90 $1.50 $1.05 1.05M
68 Qwen: Qwen3.5 397B A17B
VisionOpen Weight
Qwen $0.45 $3.00 $1.09 262K
69 Qwen: Qwen3 235B A22B Thinking 2507
ReasoningOpen Weight
Qwen $0.45 $3.50 $1.21 128K
70 Nous: Hermes 4 405B
ReasoningOpen Weight
Nous Research $1.00 $3.00 $1.50 131K
71 DeepSeek: DeepSeek V4 Pro 0813
Open Weight
DeepSeek $1.32 $3.96 $1.98 1.05M
72 DeepSeek: DeepSeek Pro Latest
Open Weight
DeepSeek $0.10 $8.00 $2.07 1.05M
73 Qwen: Qwen4 Max
VisionOpen Weight
Qwen $1.43 $4.28 $2.14 1M
74 Qwen: Qwen3.7 Max
Open Weight
Qwen $1.48 $4.42 $2.21 1M
75 Qwen: Qwen3.8 2.4T A95B
Open Weight
Qwen $2.00 $6.00 $3.00 1.05M
76 Qwen: Qwen3.8 Max (0902)
VisionOpen Weight
Qwen $2.00 $6.00 $3.00 1M
77 Mistral: Mixtral 8x22B Instruct
Open Weight
Mistral AI $2.00 $6.00 $3.00 66K
78 Cohere: Command R+ (08-2024)
Open Weight
Cohere $2.50 $10.00 $4.38 128K
79 Qwen: Qwen3.8 Max Prime
VisionOpen Weight
Qwen $4.00 $12.00 $6.00 1M

Try These Models Without Multiple Billing Accounts

Multi-Provider Gateway

OpenRouter

Unified API gateway for 300+ LLMs with automatic fallbacks and unified billing.

Call via OpenRouter →
Open-Weight Inference

Together AI

High-throughput serverless inference & fine-tuning for Llama, DeepSeek, and Qwen.

Run on Together AI →
Fastest Tokens/Sec

GroqCloud

LPU-accelerated inference delivering hundreds of tokens per second for real-time voice & agents.

Test on Groq →

Some outbound infrastructure and API gateway links on KostoZero are partner referrals that help keep this observatory free and independent at no extra cost to you.

Get Instant Price-Drop (>10%), New AI Bot & SaaS Cliff Alerts

Every 6 hours our autonomous sync checks 40+ LLMs, AI crawlers, and SaaS pricing cliffs—alerting you when prices drop >10% or new scrapers appear.