Find the Cheapest & Best-Fit LLM API

Real-time tracking of 61 providers, 443 models' pricing, capabilities & context window. Covering international and Chinese models, auto-updated daily at 04:00.

Tracked Models 443

Free Models 46

Chinese Provider Models 134

This site tracks public LLM API pricing and benchmarks with daily updates. Background, sources, and caveats live on the About page →

Best Value Models

Filters to models with AA Intelligence Index 40 or higher, then ranks by intelligence per dollar (AA score ÷ input price)

#	Model	Provider	Input	Benchmark
1	Tencent: Hy3	🇨🇳 Tencent	$0.132	AA Index 41
2	MiniMax: MiniMax M3 Multimodal	🇨🇳 MiniMax	$0.300	AA Index 44
3	DeepSeek: DeepSeek V4 Pro	🇨🇳 DeepSeek	$0.435	AA Index 44
4	Xiaomi: MiMo-V2.5-Pro	🇨🇳 Xiaomi	$0.435	AA Index 42
5	Z.ai: GLM 5.2	🇨🇳 Z.ai (Zhipu)	$0.700	AA Index 51

View full ranking →

Strongest Models

Ranked by Artificial Analysis Intelligence Index, a cross-domain intelligence metric

#	Model	Provider	Input	AA Index
1	Claude Opus 5	🇺🇸 Anthropic	$5.00	61
2	Anthropic: Claude Fable 5	🇺🇸 Anthropic	$10.00	60
3	OpenAI: GPT-5.6 Sol	🇺🇸 OpenAI	$5.00	59
4	MoonshotAI: Kimi K3	🇨🇳 Moonshot AI	$3.00	57
5	Anthropic: Claude Opus 4.8	🇺🇸 Anthropic	$5.00	56

View full ranking →

Cheapest Input Price

Cost in USD per million input tokens (excluding free models)

#	Model	Provider	Input	Output
1	inclusionAI: Ling-2.6-flash	🇨🇳 InclusionAI	$0.010	$0.030
2	IBM: Granite 4.0 Micro	🇺🇸 IBM Granite	$0.017	$0.112
3	Mistral: Mistral Nemo	🇫🇷 Mistral AI	$0.019	$0.030
4	Nex AGI: Nex-N2-Mini	🇺🇸 Nexa AI	$0.025	$0.100
5	OpenAI: GPT-5 Nano (batch)	🇺🇸 OpenAI	$0.025	$0.200

View full ranking →

Fastest Output

Ranked by Artificial Analysis measured output speed (tokens/sec)

#	Model	Provider	t/s
1	Inception: Mercury 2	🇺🇸 Inception	902
2	Google: Gemini 3.5 Flash Lite	🇺🇸 Google	435
3	StepFun: Step 3.7 Flash	🇨🇳 StepFun	387
4	NVIDIA: Nemotron 3 Nano Omni (free)	🇺🇸 NVIDIA	305
5	Google: Gemini 3.1 Flash Lite Preview	🇺🇸 Google	303

View full ranking →

Free Models (46)

Models with $0 input price. Some may still charge for output — click to view full pricing details.

Model	Provider	Output $/M	Context
Arcee AI: Trinity Large Thinking (free)	🇺🇸 Arcee AI	Free	262K
Baidu Qianfan: CoBuddy (free)	🇨🇳 Baidu	Free	131K
Baidu: Qianfan-OCR-Fast (free)	🇨🇳 Baidu	Free	66K
Cohere: North Mini Code (free)	🇨🇦 Cohere	Free	256K
DeepSeek: DeepSeek V4 Flash (free)	🇨🇳 DeepSeek	Free	1.05M