OPAPI
OpenAI
gpt-5.6-sol
ReasoningCodingMultimodal
Context1049K
Input$4
Output$20
MODEL ENCYCLOPEDIA
Find the right AI model for your workload
Start with capabilities, pricing, context and model families—not a leaderboard alone.
Popular:
MODEL DIRECTORY
Explore models by your constraints
Pricing stays connected to the existing llmprice.app data pipeline.
68 models match
OPAPI
OpenAI
gpt-5.6-terra
ChatbotCodingMultimodal
Context1049K
Input$2
Output$12
OPAPI
OpenAI
gpt-5.6-luna
ChatbotFastAffordable
Context1049K
Input$0.2
Output$1.2
OPAPI
OpenAI
gpt-5.5
ChatbotReasoningMultimodal
Context1049K
Input$5
Output$30
OPAPI
OpenAI
gpt-5.4
ChatbotCodingMultimodal
Context1049K
Input$2.5
Output$15
OPAPI
OpenAI
gpt-5.4-mini
ChatbotCodingAffordable
Context1049K
Input$0.75
Output$4.5
OPAPI
OpenAI
gpt-5.4-nano
ChatbotAffordableFast
Context1049K
Input$0.2
Output$1.25
OPAPI
OpenAI
gpt-4o
ChatbotMultimodal
Context128K
Input$2.5
Output$10
OPAPI
OpenAI
gpt-4o-mini
ChatbotAffordableFast
Context128K
Input$0.15
Output$0.6
OPAPI
OpenAI
o3
ReasoningCoding
Context200K
Input$2
Output$8
OPAPI
OpenAI
o4-mini
ReasoningCodingAffordable
Context200K
Input$1.1
Output$4.4
ANAPI
Anthropic
claude-opus-5
CodingReasoningLong Context
Context1049K
Input$5
Output$25
ANAPI
Anthropic
claude-fable-5
CodingReasoning
Context1049K
Input$10
Output$50
ANAPI
Anthropic
claude-mythos-5
ChatbotReasoning
Context1049K
Input$10
Output$50
ANAPI
Anthropic
claude-opus-4-8
CodingReasoningLong Context
Context1049K
Input$5
Output$25
ANAPI
Anthropic
claude-opus-4-6
CodingReasoningLong Context
Context1049K
Input$5
Output$25
ANAPI
Anthropic
claude-sonnet-5
CodingReasoningLong Context
Context1049K
Input$2
Output$10
ANAPI
Anthropic
claude-sonnet-4-6
CodingChatbot
Context1049K
Input$3
Output$15
ANAPI
Anthropic
claude-haiku-4-5
ChatbotAffordableFast
Context200K
Input$1
Output$5
GOAPI
gemini-3.7-flash
Context1049K
Input$0.75
Output$3.75
GOAPI
gemini-3.6-flash
Context1049K
Input$0.75
Output$3.75
GOAPI
gemini-3.1-flash-lite
ChatbotAffordableFast
Context1049K
Input$0.25
Output$1.5
GOAPI
gemini-3.5-flash
ChatbotFastMultimodal
Context1049K
Input$1.5
Output$9
GOAPI
gemini-3.1-pro
CodingReasoningLong Context
Context1049K
Input$2
Output$12
GOAPI
gemini-2.5-pro
CodingReasoningLong Context
Context1049K
Input$1.25
Output$10
GOAPI
gemini-2.5-flash
ChatbotAffordableFast
Context1049K
Input$0.3
Output$2.5
MIAPI
Mistral
mistral-large-3
ChatbotCoding
Context128K
Input$2
Output$6
MIAPI
Mistral
mistral-medium-3.5
ChatbotCoding
Context128K
Input$1.5
Output$7.5
MIAPI
Mistral
codestral-latest
Coding
Context256K
Input$0.3
Output$0.9
DEAPI
DeepSeek
deepseek-v4-flash
ChatbotAffordableFast
Context1000K
Input$0.14
Output$0.28
DEAPI
DeepSeek
deepseek-chat-v4
ChatbotAffordableFast
Context131K
Input$0.2574
Output$1.0287
DEAPI
DeepSeek
deepseek-reasoner-v4
ReasoningCoding
Context131K
Input$0.435
Output$0.87
XAAPI
xAI
grok-4.20
Context2000K
Input$1.25
Output$2.5
XAAPI
xAI
grok-4.5
ReasoningCodingChatbot
Context500K
Input$2
Output$6
XAAPI
xAI
grok-4.3
ChatbotMultimodal
Context131K
Input$1.25
Output$2.5
TOAPI
Together AI
meta-llama/Llama-3.3-70B-Instruct-Turbo
ChatbotAffordable
Context131K
Input$0.88
Output$0.88
TOAPI
Together AI
Qwen/Qwen2.5-72B-Instruct-Turbo
ChatbotCodingAffordable
Context131K
Input$1.2
Output$1.2
COAPI
Cohere
command-a
ChatbotLong Context
Context256K
Input$2.5
Output$10
COAPI
Cohere
command-r
ChatbotAffordable
Context128K
Input$2.5
Output$10
GRAPI
Groq
llama-3.3-70b-versatile
ChatbotAffordableFast
Context128K
Input$0.59
Output$0.79
MIAPI
Microsoft
Phi-4
CodingChatbotAffordable
Context16K
Input$0.07
Output$0.14
MIAPI
Microsoft
Phi-4-mini
ChatbotAffordableFast
Context128K
Input$0.02
Output$0.04
MIAPI
Microsoft
MAI-DS-R1
ReasoningCoding
Context128K
Input$0.14
Output$0.28
MIAPI
Microsoft
Llama-3.3-70B-Instruct
ChatbotCoding
Context128K
Input$0.1
Output$0.32
ZHAPI
Zhipu
GLM-5.2
CodingReasoningLong Context
Context1000K
Input$0.966
Output$3.036
ZHAPI
Zhipu
GLM-4.7
ChatbotCodingAffordable
Context205K
Input$0.4
Output$1.75
ALAPI
Alibaba
qwen3.8-max
ReasoningCodingLong Context
Context1000K
Input$2
Output$6
ALAPI
Alibaba
qwen3.5
CodingReasoningLong Context
Context1000K
Input$0.1
Output$0.15
ALAPI
Alibaba
qwen3.5-plus
ChatbotCodingLong Context
Context1000K
Input$0.32
Output$1.28
ALAPI
Alibaba
qwen3.5-flash
ChatbotAffordableFast
Context1000K
Input$0.03
Output$0.13
ALAPI
Alibaba
qwen-plus
ChatbotCodingAffordable
Context131K
Input$0.26
Output$0.78
ALAPI
Alibaba
qwen-turbo
ChatbotAffordableFast
Context1000K
Input$0.05
Output$0.2
MOAPI
Moonshot AI
kimi-k3
ReasoningCodingLong Context
Context1000K
Input$3
Output$15
MOAPI
Moonshot AI
kimi-k2.6
CodingReasoningLong Context
Context262K
Input$0.95
Output$4
BYAPI
ByteDance
doubao-seed-2.1-pro
ReasoningCodingMultimodal
Context256K
Input$0.83
Output$4.14
BYAPI
ByteDance
doubao-seed-2.1-turbo
ChatbotCodingAffordable
Context256K
Input$0.41
Output$2.07
MIAPI
MiniMax
MiniMax-M3
CodingReasoningLong Context
Context1000K
Input$0.3
Output$1.2
BAAPI
Baidu
ERNIE 5.1
ChatbotReasoning
Context128K
Input$0.59
Output$2.65
BAAPI
Baidu
ERNIE X1
ReasoningAffordable
Context128K
Input$0.28
Output$1.1
BAAPI
Baidu
ERNIE 4.5
ChatbotMultimodal
Context128K
Input$0.55
Output$2.2
TEAPI
Tencent
Hunyuan HY3
ReasoningChatbotAffordable
Context256K
Input$0.063
Output$0.21
TEAPI
Tencent
Hunyuan TurboS
ChatbotAffordableFast
Context256K
Input$0.11
Output$0.28
BAAPI
Baichuan
Baichuan4
ChatbotReasoning
Context32K
Input$13.89
Output$13.89
BAAPI
Baichuan
Baichuan4-Air
ChatbotAffordableFast
Context32K
Input$0.136
Output$0.136
STAPI
StepFun
Step 3.7 Flash
ChatbotCodingMultimodal
Context262K
Input$0.2
Output$1.15
STAPI
StepFun
Step 3.5 Flash
ChatbotAffordableFast
Context262K
Input$0.1
Output$0.3
01API
01.AI
Yi-Lightning
ChatbotAffordableFast
Context16K
Input$0.14
Output$0.14
INAPI
InclusionAI
Ling-3.0-flash
ChatbotAffordableFast
Context262K
Input$0.07
Output$0.22
DECISION GUIDES
Choose by scenario, not leaderboard position
Start with coding, RAG or high-throughput needs, then validate price and specs.
LLM BASICS
New to model selection? Start here
01How should I compare API models?＋
Define the quality bar first, then compare price, latency, context and modalities.
02Is a larger context window always better?＋
No. More context can increase cost and latency; retrieval and caching also matter.
03How do I estimate monthly LLM cost?＋
Multiply tokens per request by monthly volume, then apply input and output rates.
Model leaderboards — straight to the answer
Four rankings computed from the current dataset. Follow any model for full specs and monthly cost.
5 cheapest models
By blended rate at a 3:1 input-to-output mix
- 1.Phi-4-miniMicrosoft$0.025 / 1M
- 2.qwen3.5-flashAlibaba$0.055 / 1M
- 3.Phi-4Microsoft$0.088 / 1M
- 4.qwen-turboAlibaba$0.088 / 1M
- 5.Hunyuan HY3Tencent$0.10 / 1M
5 best-value models
Quality score ÷ output price
- 1.Phi-4-miniMicrosoft1700.0
- 2.qwen3.5-flashAlibaba630.8
- 3.qwen3.5Alibaba606.7
- 4.Yi-Lightning01.AI557.1
- 5.Phi-4Microsoft542.9
5 highest-quality models
Composite benchmark score
- 1.gpt-5.6-solOpenAIQuality 98
- 2.gpt-5.5OpenAIQuality 97
- 3.claude-opus-5AnthropicQuality 97
- 4.claude-fable-5AnthropicQuality 96
- 5.claude-mythos-5AnthropicQuality 96
5 largest context windows
For long documents and whole codebases
- 1.grok-4.20xAI2000K
- 2.gpt-5.6-solOpenAI1049K
- 3.gpt-5.6-terraOpenAI1049K
- 4.gpt-5.6-lunaOpenAI1049K
- 5.gpt-5.5OpenAI1049K