Alibaba
Qwen3.6-PlusCompatibility · Multimodal
In $0.20Out $1.25Public ref.In $0.50Out $3
CompatibilityMultimodal
The model menu.
58 models across Claude, Gemini, GPT, Grok, and leading Chinese labs: one OpenAI-compatible key, a curated menu, and transparent pay-as-you-go pricing in public USD.
Selected models
15 models
Alibaba
Qwen3.7-MaxComplex automation
In $1.24Out $3.72Public ref.In $2.50Out $7.50
FlagshipVisionPlanning
Anthropic
Claude Haiku 4.5Fast, high-volume Claude
In $0.50Out $2.50Public ref.In $1Out $5
FastLow costAssistants
Zhipu
GLM-5Agents · Value
In $0.54Out $1.74Public ref.In $1Out $3.20
AgentsValue
Zhipu
GLM-5.1Reasoning · Agents
In $0.79Out $2.56Public ref.In $1.40Out $4.40
ReasoningAgents
Anthropic
Claude Opus 4.8Hard coding & long-horizon agents
In $3Out $15Public ref.In $5Out $25
FlagshipCodingAgents
OpenAI
GPT-5.5Frontier agentic coding
In $3Out $18Public ref.In $5Out $30
FlagshipCodingAgents
Anthropic
Claude Sonnet 5Real-time agents & tool use
In $1.20Out $6Public ref.In $2Out $10
AgentsTool use1M context
Multimodal reasoning & coding
In $1.20Out $7.20Public ref.In $2Out $12
MultimodalReasoningLong context
Moonshot
Kimi K2.6Long-form reasoning & coding
In $0.48Out $2.30Public ref.In $0.89Out $3.71
ReasoningCodeAgents
Alibaba
Qwen3.5-35B-A3BFast · Budget · MoE
In $0.16Out $1.30Public ref.In $0.25Out $2
FastBudgetMoE
Alibaba
Qwen3.5-PlusProduction value
In $0.28Out $1.55Public ref.In $0.40Out $2.40
ValueAssistantsMultilingual
Moonshot
Kimi K2.5General · Multimodal
In $0.45Out $2Public ref.In $0.57Out $3.01
GeneralMultimodal
Zhipu
GLM-5.2Long-context coding
In $0.90Out $3.10Public ref.In $1.40Out $4.40
1M contextCodingTool use
xAI
Grok 4.5Reasoning & coding
In $1.40Out $4.20Public ref.In $2Out $6
ReasoningCodingAgents
Anthropic
Claude Fable 5Frontier reasoning
In $7Out $35Public ref.In $10Out $50
FlagshipFrontierAgents
Anthropic
Claude Opus 4.5Flagship · Coding · Agents
In $3.88Out $19.38Public ref.In $5Out $25
FlagshipCodingAgents
Anthropic
Claude Opus 4.5 ThinkingFlagship · Reasoning · Thinking
In $3.88Out $19.38Public ref.In $5Out $25
FlagshipReasoningThinking
Anthropic
Claude Opus 4.6Flagship · Coding · Agents
In $3.88Out $19.38Public ref.In $5Out $25
FlagshipCodingAgents
Anthropic
Claude Opus 4.6 ThinkingFlagship · Reasoning · Thinking
In $3.88Out $19.38Public ref.In $5Out $25
FlagshipReasoningThinking
Anthropic
Claude Opus 4.7Hard coding & agents
In $3.50Out $17.5Public ref.In $5Out $25
FlagshipCodingAgents
Anthropic
Claude Sonnet 4.5Balanced · Coding · Agents
In $2.33Out $11.63Public ref.In $3Out $15
BalancedCodingAgents
Anthropic
Claude Sonnet 4.5 (0929)Balanced · Coding · Agents
In $2.33Out $11.63Public ref.In $3Out $15
BalancedCodingAgents
Anthropic
Claude Sonnet 4.5 ThinkingBalanced · Reasoning · Thinking
In $2.33Out $11.63Public ref.In $3Out $15
BalancedReasoningThinking
Anthropic
Claude Sonnet 4.6Balanced coding & agents
In $2.10Out $10.5Public ref.In $3Out $15
BalancedCodingAgents
Anthropic
Claude Sonnet 4.6 ThinkingBalanced · Reasoning · Thinking
In $2.33Out $11.63Public ref.In $3Out $15
BalancedReasoningThinking
High-volume multimodal
In $0.23Out $1.94Public ref.In $0.30Out $2.50
FastMultimodalLow cost
Fast · Low cost · Multimodal
In $0.08Out $0.31Public ref.In $0.10Out $0.40
FastLow costMultimodal
Reasoning · Multimodal · Thinking
In $0.23Out $1.94Public ref.In $0.30Out $2.50
ReasoningMultimodalThinking
Multimodal reasoning
In $0.97Out $7.75Public ref.In $1.25Out $10
MultimodalReasoningLong context
Fast · Multimodal · Preview
In $0.39Out $2.33Public ref.In $0.50Out $3
FastMultimodalPreview
Fast · Low cost · Multimodal
In $0.19Out $1.16Public ref.In $0.25Out $1.50
FastLow costMultimodal
Fast · Low cost · Preview
In $0.19Out $1.16
FastLow costPreview
Reasoning · Multimodal · Thinking
In $1.40Out $8.40Public ref.In $2Out $12
ReasoningMultimodalThinking
Fast multimodal reasoning
In $1.16Out $6.98Public ref.In $1.50Out $9
FastMultimodalReasoning
OpenAI
GPT-4o miniReasoning · Math
In $0.12Out $0.49Public ref.In $0.15Out $0.60
ReasoningMath
OpenAI
GPT-5General assistants & coding
In $0.90Out $7.20Public ref.In $1.25Out $10
GeneralCodingAssistants
OpenAI
GPT-5 MiniFast, high-volume GPT
In $0.20Out $1.60Public ref.In $0.25Out $2
FastLow costRouting
OpenAI
GPT-5.4General coding & agents
In $1.75Out $10.5Public ref.In $2.50Out $15
CodingAgents
OpenAI
GPT-5.4 MiniFast · Low cost
In $0.53Out $3.15Public ref.In $0.75Out $4.50
FastLow cost
OpenAI
GPT-5.6 LunaFrontier · Efficient · Long context
In $0.70Out $4.20Public ref.In $1Out $6
FrontierEfficientLong context
OpenAI
GPT-5.6 SolFrontier · Agents · Long context
In $3.50Out $21Public ref.In $5Out $30
FrontierAgentsLong context
OpenAI
GPT-5.6 TerraBalanced frontier + long context
In $1.75Out $10.5Public ref.In $2.50Out $15
FrontierAgentsLong context
xAI
Grok 4.3Fast reasoning
In $0.88Out $1.75Public ref.In $1.25Out $2.50
ReasoningFast
Alibaba
Qwen3.5-FlashUltra-budget · Fast
In $0.12Out $0.95
Ultra-budgetFast
Alibaba
Qwen3.6 Open 27BOpen · Advanced
In $0.95Out $4.95
OpenAdvanced
Alibaba
Qwen3.6-FlashFast · Budget · Long context
In $0.17Out $1
FastBudgetLong context
Alibaba
Qwen3.7-PlusMultimodal agents
In $0.25Out $1.20Public ref.In $0.40Out $1.60
VisionCodingAgents
Zhipu
GLM-5-TurboAgent · Tool use
In $1.50Out $5.20
AgentTool use
Zhipu
GLM-5V-TurboVision · Coding
In $1.60Out $5.40
VisionCoding
Moonshot
Kimi K2.7 CodeAgentic coding
In $0.72Out $3Public ref.In $0.95Out $4
CodeAgentsRepositories
Moonshot
Kimi K2.7 Code HighSpeedCoding · Fast · Agentic
In $0.62Out $3.72Public ref.In $0.95Out $4
CodingFastAgentic
MiniMax
MiniMax M2.5Value · Agents
In $0.50Out $2
ValueAgents
MiniMax
MiniMax M2.7Coding · Productivity
In $0.52Out $2.10
CodingProductivity
MiniMax
MiniMax M3Long-context product work
In $0.55Out $2.20
Multimodal512KAgents
DeepSeek
DeepSeek V4 FlashBudget · General · Long context
In $0.20Out $0.40
BudgetGeneralLong context
DeepSeek
DeepSeek V4 ProReasoning and debugging
In $0.31Out $0.62Public ref.In $0.44Out $0.87
Reasoning1M contextDebugging
Meituan LongCat
LongCat-2.0Agentic coding
In $1.35Out $5.40
Agentic coding1M contextTool use