context.vn
Menu
Models
Small Models
Speed
S3
VN Infra
Design Arena
Servers
All plans
Auction
Cloud stock
Performance
Stock watch
Sources
models.dev
arena.ai
artificialanalysis.ai
benchlm.ai
roboflow
Models
Small Models
Servers
All plans
every provider, every price
Server auction
Hetzner, one machine per row
Cloud stock
what Hetzner can create where
Performance
repeated benchmarks, and the spread
Stock watch
email me on a restock
Speed
S3
VN Infra
Design Arena
sources
models.dev
arena.ai
artificialanalysis.ai
benchlm.ai
roboflow
Unified Model View
4 unique models across 232 providers
All providers
NanoGPT (207)
Kilo Gateway (173)
OpenRouter (171)
Vercel AI Gateway (161)
AI/ML API (96)
Eden AI (95)
DevPass (LLM Gateway) (80)
LLM Gateway (80)
Merge Gateway (79)
Poe (72)
OpenCode (63)
Venice AI (59)
Cortecs (56)
Requesty (56)
AIHubMix (55)
302.AI (53)
ZenMux (52)
OrcaRouter (51)
DigitalOcean (51)
Azure (50)
Azure Cognitive Services (50)
Abacus (49)
Impossibl (44)
Novita AI (44)
Qiniu (43)
Ofox (42)
Tempr Gateway (41)
Amazon Bedrock (39)
Helicone (39)
Prime Inference (39)
CommandCode (36)
CrossModel (36)
Opper (35)
Kenari (34)
Nvidia (33)
Cloudflare AI Gateway (32)
NEAR AI Cloud (32)
SAP AI Core (32)
Neon (31)
FastRouter (29)
GreenPT (29)
Jiekou.AI (28)
Hugging Face (28)
Deep Infra (27)
OpenCode Go (26)
OpenAI (26)
Perplexity Agent (25)
Standard Compute (24)
AnyAPI (24)
Vivgrid (24)
SiliconFlow (23)
Pioneer (22)
Vertex (21)
EmpirioLabs AI (21)
Databricks (20)
Together AI (20)
GitHub Copilot (19)
Snowflake Cortex (19)
LowRouter (19)
Mistral (19)
FrogBot (18)
The Grid AI (17)
UnoRouter (17)
Alibaba Token Plan (17)
Alibaba Token Plan (China) (17)
Fireworks AI (17)
Alibaba (China) (16)
Cloudflare Workers AI (16)
Nebius Token Factory (16)
LLMTR (16)
Charm Hyper (15)
CoreWeave (15)
Ollama Cloud (15)
SiliconFlow (China) (15)
Boundless (14)
Model Oracle AI (14)
Meganova (14)
TensorX (14)
TokenGo (13)
Z.AI (13)
routing.run (12)
Scaleway (12)
Zhipu AI (12)
Auriko (11)
GMI Cloud (11)
Xpersona (11)
ai& (11)
ClinePass (11)
evroc (11)
IO.NET (11)
SCNet Token Plan (11)
Synthetic (11)
Vultr (11)
Baseten (11)
Regolo AI (11)
Cohere (11)
Aixy (10)
Chutes (10)
Melious (10)
Neuralwatt (10)
Privatemode AI (10)
QiHang (9)
Crusoe (9)
Jalapeno Cloud (9)
Thinking Machines (9)
Arcee (9)
DaoXE (8)
FreeModel (8)
HPC-AI (8)
Modelis (8)
Clarifai (8)
Infomaniak (8)
IteraCompute (8)
Moark (8)
Volcengine Ark Coding Plan (8)
AMD (8)
Bothub (8)
Vancine (7)
above.dev (7)
engy (7)
InferX (7)
Modal (7)
RunInfra (7)
Tinfoil (7)
Groq (7)
OVHcloud AI Endpoints (7)
submodel (7)
Z.AI Coding Plan (7)
TrustedRouter (7)
Ambient (6)
DInference (6)
Inco (6)
SambaNova (6)
Alibaba (6)
AKI.IO (6)
NaN (6)
Umans AI (6)
Umans AI Coding Plan (6)
Google (6)
Berget.AI (6)
Inference (6)
Bee by HEOSSI (6)
Alibaba Coding Plan (5)
Alibaba Coding Plan (China) (5)
Inceptron (5)
Tencent Coding Plan (China) (5)
Wafer (5)
CloudFerro Sherlock (5)
Munito AI (5)
Pendra (5)
SenseNova (China) (5)
Volcengine Ark (5)
STACKIT (5)
Friendli (5)
AI-ROUTER (5)
Anthropic (4)
AgentRouter (4)
Vertex (Anthropic) (4)
EBCloud (4)
Lilac (4)
SCX.ai (4)
Munito AI (EU) (4)
Zhipu AI Coding Plan (4)
watsonx.ai (4)
LucidQuery (4)
Perplexity (4)
StepFun Step Plan (China) (4)
Agnes AI (4)
NeoSmith (4)
Kimi For Coding (kimi.ai) (3)
Kimi For Coding (kimi.com) (3)
Moonshot AI (3)
Moonshot AI (China) (3)
OpenReason (3)
D.Run (China) (3)
DeepSeek (3)
Atomic Chat (3)
ModelScope (3)
QVAC (3)
OCI Generative AI (3)
StepFun (China) (3)
StepFun (Global) (3)
StepFun Step Plan (Global) (3)
Tencent TokenHub (3)
Upstage (3)
Sakana AI (3)
Vispark (3)
klokintegration.se (3)
Subconscious (2)
Cerebras (2)
LMStudio (2)
Infer by Flow7 (2)
xAI (2)
Morph (2)
Nova (2)
Tencent Token Plan (2)
Bailing (2)
abliteration.ai (2)
Claudinio (2)
Liquid Inference (1)
Lynkr (1)
MiniMax (minimax.cn) (1)
MiniMax (minimax.io) (1)
MiniMax Token Plan (minimax.cn) (1)
MiniMax Token Plan (minimax.io) (1)
CoralBricks (1)
Blue Claw (1)
Hetzner (1)
Kosmik Compute (1)
LLM Tech (1)
Mixlayer (1)
SaladCloud AI Gateway (1)
Zenifra (1)
KUAE Cloud Coding Plan (1)
ainetcafe (1)
Wallaby (1)
Pareto Inference (1)
TokenRouter (1)
Meta (1)
Reflection (1)
Sarvam AI (1)
GitLab Duo (1)
Inception (1)
Xiaomi (1)
Xiaomi Token Plan (China) (1)
Xiaomi Token Plan (Europe) (1)
Xiaomi Token Plan (Singapore) (1)
Poolside (1)
LongCat (1)
Echo (1)
Zeldoc (1)
AI21 Labs (1)
Search
Reasoning
Tool Use
Open Weights
Has Pricing
Any modality
Vision
Audio
Video
Any source
models.dev
AA
Arena
2+ sources
Ctx min
32K+
128K+
200K+
1M+
Ctx max
≤32K
≤128K
≤200K
≤1M
Input $
Free
≤$1/M
≤$5/M
≤$15/M
Output $
Free
≤$1/M
≤$5/M
≤$15/M
≤$60/M
25/pg
50/pg
100/pg
200/pg
Clear
Model
Providers
Context
Input $/M
Output $/M
Capabilities
AA Intel
AA Speed
Arena
Sources
grok-4-fast-reasoning
grok
xAI +46
20.0M
Free–$4.00
Free–$15.00
R
T
V
A
46
53/s
1,404
D
A
R
3
grok-4.1
302.AI
200K
$2.00
$10.00
T
V
-
-
1,459
D
A
R
2
x-AI/Grok-4-Fast
Qiniu
2.0M
-
-
R
T
V
A
-
-
-
D
A
R
x-AI/Grok-4.1-Fast
Qiniu
2.0M
-
-
R
T
-
-
-
D
A
R