Qwen 3.5 9B (MLX 4-bit)
Alibaba · 2 offerings · released 2026-02-23
Context33K
Reference input / output$0 / $0Atomic Chat · USD / 1M
Tools · Vision · Open weights
Model intelligence
cheapest model explorer
Transparent metadata constraints and cost assumptions. No proprietary benchmark scores are copied or invented.
Inspect sourced capabilities and paired provider prices; the value index is a documented heuristic. Read the methodology.
All capability, availability and price filters
Prices use a single reference offering selected with a 4:1 input/output ratio. Adoption and benchmark comparisons require source-specific evidence; see Trends. Unknown capabilities are not confirmed support.
467 models · sourced catalogCheck source dates on model pages
Qwen3.5 0.8B
Alibaba · 2 offerings · released 2026-03-02
Context33K
Reference input / output$0 / $0QVAC · USD / 1M
Tools · Open weights
Qwen3.6 27B FP8
Alibaba · 1 offering · released 2026-04-22
Context262K
Reference input / output$0 / $0InferX · USD / 1M
Reasoning · Tools · Vision · Open weights
Qwen3.6-35B-A3B-fp8-no-thinking
Alibaba · 1 offering · released 2026-04-17
Context262K
Reference input / output$0 / $0InferX · USD / 1M
Tools · Vision · Open weights
Qwen3 Coder Next FP8
Alibaba · 2 offerings · released 2026-02-03
Context256K
Reference input / output$0 / $0InferX · USD / 1M
Tools · Open weights
Qwen3-Coder-Next-FP8-no-thinking
Alibaba · 1 offering · released 2026-02-03
Context260K
Reference input / output$0 / $0InferX · USD / 1M
Tools · Open weights
Qwen3Guard-Gen-0.6B
Alibaba · 2 offerings · released 2026-01-22
Context33K
Reference input / output$0 / $0OVHcloud AI Endpoints · USD / 1M
Open weights
Qwen3Guard-Gen-8B
Alibaba · 2 offerings · released 2026-01-22
Context33K
Reference input / output$0 / $0OVHcloud AI Endpoints · USD / 1M
Open weights
North Mini Code
Cohere · 4 offerings · released 2026-06-09
Context256K
Reference input / output$0 / $0OpenRouter · USD / 1M
Reasoning · Tools · Open weights
North Small Translate
Cohere · 1 offering · released 2026-09-09
Context33K
Reference input / output$0 / $0Cohere · USD / 1M
Open weights
R1 Distill Qwen 1.5B
DeepSeek · 1 offering · released 2025-01-01
Context33K
Reference input / output$0 / $0Alibaba (China) · USD / 1M
Reasoning
Gemma 4 31B IT FP8
Google · 1 offering · released 2026-04-02
Context262K
Reference input / output$0 / $0InferX · USD / 1M
Reasoning · Tools · Vision · Open weights
Gemma 4 E4B Instruct (MLX 4-bit)
Google · 1 offering · released 2026-04-02
Context33K
Reference input / output$0 / $0Atomic Chat · USD / 1M
Open weights
Lyria 3 Clip Preview
Google · 3 offerings · released 2026-03-25
Context1.05M
Reference input / output$0 / $0OpenRouter · USD / 1M
Vision
Lyria 3 Pro Preview
Google · 3 offerings · released 2026-03-25
Context1.05M
Reference input / output$0 / $0Kilo Gateway · USD / 1M
Vision
paligemma
Google · 1 offering · released 2024-05-14
Context128K
Reference input / output$0 / $0Nvidia · USD / 1M
Vision · Open weights
bevformer
NVIDIA · 1 offering · released 2025-03-18
Context128K
Reference input / output$0 / $0Nvidia · USD / 1M
Open weights
Laguna XS 2.1
NVIDIA · 7 offerings · released 2026-07-02
Context262K
Reference input / output$0 / $0Poolside · USD / 1M
Reasoning · Tools · Open weights
llama-3.1-nemotron-safety-guard-8b-v3
NVIDIA · 1 offering · released 2025-10-28
Context128K
Reference input / output$0 / $0Nvidia · USD / 1M
Open weights
nemotron-voicechat
NVIDIA · 1 offering · released 2026-03-16
Context128K
Reference input / output$0 / $0Nvidia · USD / 1M
Tools · Open weights
sparsedrive
NVIDIA · 1 offering · released 2025-03-18
Context128K
Reference input / output$0 / $0Nvidia · USD / 1M
Open weights
streampetr
NVIDIA · 1 offering · released 2025-11-13
Context128K
Reference input / output$0 / $0Nvidia · USD / 1M
Open weights
NanoGPT Help
OpenAI · 1 offering · released 2026-06-06
Context6K
Reference input / output$0 / $0NanoGPT · USD / 1M
No confirmed capabilities
GLM-4.5-Flash
Zhipu AI · 5 offerings · released 2025-07-28
Context131K
Reference input / output$0 / $0EmpirioLabs AI · USD / 1M
Reasoning · Tools
GPT OSS 20B
OpenAI · 58 offerings · released 2025-08-05
Context131K
Reference input / output$0.007 / $0.027NanoGPT · USD / 1M
Reasoning · Tools · Open weights
Gemma 2
Google · 1 offering · released 2024-06-25
Context8K
Reference input / output$0.01 / $0.03Helicone · USD / 1M
No confirmed capabilities
Llama Prompt Guard 2 22M
Meta · 3 offerings · released 2025-04-29
Context512
Reference input / output$0.01 / $0.01Helicone · USD / 1M
Open weights
Llama Prompt Guard 2 86M
Meta · 3 offerings · released 2025-04-29
Context512
Reference input / output$0.01 / $0.01Helicone · USD / 1M
Open weights
GLM-5.3-Flash
Zhipu AI · 123 offerings · released 2026-08-26
Context1M
Reference input / output$0.0163 / $0.1821OpenRouter · USD / 1M
Reasoning · Tools · Vision · Open weights
GPT OSS 120B
OpenAI · 102 offerings · released 2025-08-05
Context128K
Reference input / output$0.018 / $0.067Kilo Gateway · USD / 1M
Reasoning · Tools · Open weights
Qwen3.5 2B
Alibaba · 2 offerings · released 2026-03-02
Context33K
Reference input / output$0.02 / $0.10Requesty · USD / 1M
Tools · Open weights
titan-embed-text
Amazon · 1 offering · released 2024-04-30
Context8K
Reference input / output$0.02 / $0SAP AI Core · USD / 1M
No confirmed capabilities
Llama 3.1 8B (decentralized)
Meta · 1 offering · released 2024-01-01
Context128K
Reference input / output$0.02 / $0.03NanoGPT · USD / 1M
Open weights
Mistral NeMo
Mistral AI · 17 offerings · released 2024-07-18
Context128K
Reference input / output$0.02 / $0.04Meganova · USD / 1M
Tools · Open weights
GLM-4.6V-Flash
Zhipu AI · 7 offerings · released 2025-12-08
Context128K
Reference input / output$0.0218 / $0.2184ZenMux · USD / 1M
Reasoning · Tools · Vision · Open weights
Qwen Flash
Alibaba · 8 offerings · released 2025-07-28
Context1M
Reference input / output$0.022 / $0.216Merge Gateway · USD / 1M
Reasoning · Tools
Qwen3 VL Flash
Alibaba · 3 offerings · released 2025-10-09
Context262K
Reference input / output$0.022 / $0.215Merge Gateway · USD / 1M
Tools · Vision
Gemma 4 26B A4B IT
Google · 32 offerings · released 2026-04-02
Context262K
Reference input / output$0.024 / $0.10Kilo Gateway · USD / 1M
Reasoning · Tools · Vision · Open weights
Nemotron 3.5 Lightning
NVIDIA · 21 offerings · released 2026-08-11
Context1M
Reference input / output$0.025 / $0.12Kilo Gateway · USD / 1M
Reasoning · Tools · Open weights
Qwen3.5 Flash
Alibaba · 16 offerings · released 2026-02-23
Context1M
Reference input / output$0.0282 / $0.282AIHubMix · USD / 1M
Reasoning · Tools · Vision
Qwen3.7 Flash
Alibaba · 17 offerings · released 2026-07-15
Context1M
Reference input / output$0.0282 / $0.1128AIHubMix · USD / 1M
Reasoning · Tools · Vision
Qwen2.5 Coder 7B fast
Alibaba · 1 offering · released 2024-09-15
Context32K
Reference input / output$0.03 / $0.09Helicone · USD / 1M
No confirmed capabilities
Seed 2.0 Mini
ByteDance · 15 offerings · released 2026-02-14
Context256K
Reference input / output$0.03 / $0.28ZenMux · USD / 1M
Reasoning · Tools · Vision
OCR 2
DeepSeek · 3 offerings · released 2026-01-27
Context8K
Reference input / output$0.03 / $0.03Novita AI · USD / 1M
Vision · Open weights
Nova Micro 1.0
Amazon · 4 offerings · released 2024-12-05
Context128K
Reference input / output$0.035 / $0.14Kilo Gateway · USD / 1M
Tools
Nova Micro
Amazon · 8 offerings · released 2024-12-03
Context128K
Reference input / output$0.035 / $0.14SAP AI Core · USD / 1M
Tools
AutoGLM Phone 9B Multilingual
Zhipu AI · 2 offerings · released 2025-12-10
Context66K
Reference input / output$0.035 / $0.138Novita AI · USD / 1M
Vision · Open weights
Command R7B (12-2024)
Cohere · 6 offerings · released 2024-12-13
Context128K
Reference input / output$0.0375 / $0.15Kilo Gateway · USD / 1M
Tools · Open weights
Command R7B Arabic
Cohere · 1 offering · released 2025-02-27
Context128K
Reference input / output$0.0375 / $0.15Cohere · USD / 1M
Tools · Open weights
Qwen3.5 4B
Alibaba · 7 offerings · released 2026-03-02
Context262K
Reference input / output$0.04 / $0.07EmpirioLabs AI · USD / 1M
Reasoning · Tools · Vision · Open weights
Qwen3.8 27B Abliterated
Alibaba · 1 offering · released 2026-10-29
Context262K
Reference input / output$0.04 / $1.35NEAR AI Cloud · USD / 1M
Reasoning · Tools · Vision
Gemma 4 E2B IT
Google · 2 offerings · released 2026-04-02
Context131K
Reference input / output$0.04 / $0.08Amazon Bedrock · USD / 1M
Reasoning · Tools · Vision · Open weights
Llama 3 8B Lunaris
Meta · 3 offerings · released 2024-08-13
Context8K
Reference input / output$0.04 / $0.05OpenRouter · USD / 1M
Open weights
GPT-5 Mini
OpenAI · 40 offerings · released 2025-08-07
Context400K
Reference input / output$0.04 / $0.29QiHang · USD / 1M
Reasoning · Tools · Vision
GLM-4.6V FlashX
Zhipu AI · 2 offerings · released 2025-12-08
Context128K
Reference input / output$0.04 / $0.40LLM Gateway · USD / 1M
Reasoning · Tools · Vision
Qwen-VL OCR
Alibaba · 2 offerings · released 2024-10-28
Context34K
Reference input / output$0.043 / $0.072Alibaba (China) · USD / 1M
Vision
Qwen3.6 35B-A3B
Alibaba · 44 offerings · released 2026-04-17
Context262K
Reference input / output$0.045 / $0.30engy · USD / 1M
Reasoning · Tools · Vision · Open weights
Qwen3.8 27B
Alibaba · 65 offerings · released 2026-08-14
Context262K
Reference input / output$0.045 / $0.32engy · USD / 1M
Reasoning · Tools · Vision · Open weights
GPT-5 Nano
OpenAI · 34 offerings · released 2025-08-07
Context400K
Reference input / output$0.0455 / $0.3636Poe · USD / 1M
Reasoning · Tools · Vision
Llama 3.2 11B Vision Instruct
Meta · 4 offerings · released 2024-09-25
Context128K
Reference input / output$0.0485 / $0.676Cloudflare Workers AI · USD / 1M
Vision · Open weights
Qwen3.5 9B
Alibaba · 23 offerings · released 2026-02-23
Context262K
Reference input / output$0.05 / $0.15NanoGPT · USD / 1M
Reasoning · Tools · Vision · Open weights
DiffusionGemma 26B A4B IT
Google · 3 offerings · released 2026-06-09
Context250K
Reference input / output$0.05 / $0.15NanoGPT · USD / 1M
Reasoning · Tools · Vision · Open weights
Gemma 4 12B IT
Google · 3 offerings · released 2026-06-09
Context262K
Reference input / output$0.05 / $0.25NanoGPT · USD / 1M
Tools · Vision · Open weights
Mistral Small 3
Mistral AI · 6 offerings · released 2025-01-30
Context33K
Reference input / output$0.05 / $0.08Kilo Gateway · USD / 1M
Open weights
Nemotron 3.5 Content Safety
NVIDIA · 9 offerings · released 2026-06-02
Context128K
Reference input / output$0.05 / $0.15Vultr · USD / 1M
Reasoning · Vision · Open weights
nemotron-3-nano-30b-a3b
NVIDIA · 18 offerings · released 2025-12-15
Context256K
Reference input / output$0.05 / $0.20Kilo Gateway · USD / 1M
Reasoning · Tools · Open weights
Nemotron 3 Super 120B A12B
NVIDIA · 29 offerings · released 2026-03-11
Context262K
Reference input / output$0.05 / $0.25NanoGPT · USD / 1M
Reasoning · Tools · Open weights
Qwen3 30B A3b fp8
Alibaba · 1 offering · released 2025-04-28
Context33K
Reference input / output$0.0509 / $0.335Cloudflare Workers AI · USD / 1M
Reasoning · Tools · Open weights
Llama Guard 3 8B
Meta · 3 offerings · released 2024-07-23
Context131K
Reference input / output$0.055 / $0.055Eden AI · USD / 1M
Open weights
Phi 4
Microsoft · 4 offerings · released 2025-01-10
Context16K
Reference input / output$0.056 / $0.112Kilo Gateway · USD / 1M
No confirmed capabilities
Qwen3.5 35B-A3B
Alibaba · 26 offerings · released 2026-02-23
Context262K
Reference input / output$0.0564 / $0.4512AIHubMix · USD / 1M
Reasoning · Tools · Vision · Open weights
Nova Lite 1.0
Amazon · 5 offerings · released 2024-12-05
Context300K
Reference input / output$0.0595 / $0.238NanoGPT · USD / 1M
Tools · Vision
Qwen2.5 Coder 32B Instruct
Alibaba · 9 offerings · released 2024-11-12
Context33K
Reference input / output$0.06 / $0.20Hugging Face · USD / 1M
Open weights
Qwen3 8B
Alibaba · 11 offerings · released 2025-04-29
Context41K
Reference input / output$0.06 / $0.06SiliconFlow · USD / 1M
Reasoning · Tools · Open weights
Nova Lite
Amazon · 8 offerings · released 2024-12-03
Context300K
Reference input / output$0.06 / $0.24Vercel AI Gateway · USD / 1M
Tools · Vision
R1 0528 Qwen3 8B
DeepSeek · 1 offering · released 2025-05-29
Context128K
Reference input / output$0.06 / $0.09Novita AI · USD / 1M
Reasoning · Open weights
Nemotron 3.5 Super VL 120B A12B
NVIDIA · 16 offerings · released 2026-10-15
Context1.05M
Reference input / output$0.06 / $0.35Kilo Gateway · USD / 1M
Reasoning · Tools · Vision · Open weights
GLM-4.7-Flash
Zhipu AI · 31 offerings · released 2026-01-19
Context200K
Reference input / output$0.06 / $0.40Eden AI · USD / 1M
Reasoning · Tools · Open weights
GLM-4.7-FlashX
Zhipu AI · 10 offerings · released 2026-01-19
Context200K
Reference input / output$0.06 / $0.40Vercel AI Gateway · USD / 1M
Reasoning · Tools · Open weights
glm-5.1
Zhipu AI · 71 offerings · released 2026-03-27
Context203K
Reference input / output$0.06 / $0.22AIHubMix · USD / 1M
Reasoning · Tools · Open weights
GLM-5.3
Zhipu AI · 126 offerings · released 2026-08-14
Context1M
Reference input / output$0.0699 / $1.40OpenRouter · USD / 1M
Reasoning · Tools · Open weights
Seed 1.6 Flash (250715) (ByteDance)
ByteDance · 1 offering · released 2025-07-26
Context256K
Reference input / output$0.07 / $0.30LLM Gateway · USD / 1M
Reasoning · Tools · Vision
Gemini 3 Flash Preview
Google · 37 offerings · released 2025-12-17
Context1.05M
Reference input / output$0.07 / $0.43QiHang · USD / 1M
Reasoning · Tools · Vision
Llama 3.2 11B Instruct
Meta · 2 offerings · released 2024-09-25
Context128K
Reference input / output$0.07 / $0.33DevPass (LLM Gateway) · USD / 1M
Open weights
Phi 4 Multimodal
Microsoft · 4 offerings · released 2025-02-26
Context128K
Reference input / output$0.07 / $0.11NanoGPT · USD / 1M
Open weights
gpt-oss-safeguard-20b
OpenAI · 12 offerings · released 2025-10-29
Context131K
Reference input / output$0.07 / $0.20Merge Gateway · USD / 1M
Reasoning · Tools · Open weights
GLM 4.7 Flash Heretic
Zhipu AI · 1 offering · released 2026-02-04
Context200K
Reference input / output$0.07 / $0.40Venice AI · USD / 1M
Reasoning · Tools · Open weights
GLM-5.2
Zhipu AI · 144 offerings · released 2026-06-13
Context1M
Reference input / output$0.07 / $1.40NanoGPT · USD / 1M
Reasoning · Tools · Open weights
Qwen Long
Alibaba · 2 offerings · released 2025-01-25
Context10M
Reference input / output$0.072 / $0.287Alibaba (China) · USD / 1M
No confirmed capabilities
Qwen3 VL 8B Instruct
Alibaba · 5 offerings · released 2025-10-14
Context262K
Reference input / output$0.0747 / $0.2989SiliconFlow (China) · USD / 1M
Tools · Vision · Open weights
gemini-2.0-flash-lite
Google · 3 offerings · released 2024-12-11
Context2M
Reference input / output$0.075 / $0.30302.AI · USD / 1M
Vision
GPT-4o mini
OpenAI · 30 offerings · released 2024-07-18
Context128K
Reference input / output$0.075 / $0.30Cloudflare AI Gateway · USD / 1M
Tools · Vision
Qwen3 14B
Alibaba · 10 offerings · released 2025-04-28
Context33K
Reference input / output$0.076 / $0.228LLM Gateway · USD / 1M
Tools
Qwen3-30B-A3B
Alibaba · 14 offerings · released 2025-04-28
Context128K
Reference input / output$0.08 / $0.29Helicone · USD / 1M
Tools · Open weights
Qwen3 32B
Alibaba · 26 offerings · released 2025-04-28
Context131K
Reference input / output$0.08 / $0.24NanoGPT · USD / 1M
Reasoning · Tools · Open weights
M2.7
MiniMax · 55 offerings · released 2026-03-18
Context205K
Reference input / output$0.08 / $0.32LLM Gateway · USD / 1M
Reasoning · Tools · Open weights
Qwen3.5 27B
Alibaba · 24 offerings · released 2026-02-23
Context262K
Reference input / output$0.0846 / $0.6768AIHubMix · USD / 1M
Reasoning · Tools · Vision · Open weights
Seed 2.0 Lite
ByteDance · 14 offerings · released 2026-02-14
Context256K
Reference input / output$0.087 / $0.5217Qiniu · USD / 1M
Vision
Qwen Doc Turbo
Alibaba · 1 offering · released unknown
Context131K
Reference input / output$0.087 / $0.144Alibaba (China) · USD / 1M
Tools
Qwen3-235B-A22B
Alibaba · 12 offerings · released 2025-04-28
Context128K
Reference input / output$0.0875 / $0.35NanoGPT · USD / 1M
Tools · Open weights