AI Models

Choose from our range of AI models optimized for different tasks. All models are available across all subscription tiers.

Understanding Compute Tokens (CT)

Compute Tokens (CT) are our unified billing unit for both AI model usage and environment/container runtime. LLM API costs are passed through at a 1:1 rate with zero markup—we don't add margins on top of provider pricing. The CT Cost column shows relative cost compared to Claude Sonnet 4.5 (our 1x baseline).

1xBaseline (Sonnet 4.5)
0.05x20x cheaper
2.0x2x more expensive

Model Comparison

ModelIntelligenceSpeedContextInput / 1MCached / 1MOutput / 1M
CT Cost
Claude Opus 4.7

Anthropic’s latest flagship for the most complex reasoning and agentic coding work.

Highest
Medium1M$5.00$0.50$25.00
5.0x
Claude Opus 4.6

Previous-generation flagship Claude model for complex reasoning and coding.

Highest
Medium1M$5.00$0.50$25.00
5.0x
Claude Sonnet 4.5

Best balance of intelligence and speed. Excellent for coding and daily tasks.

High
Fast200k$3.00$0.30$15.00
3.0x
Claude Haiku 4.5Recommended

Fast and cost-effective for quick tasks and high-volume operations.

Good
Very Fast200k$1.00$0.10$5.00
1x (baseline)
GPT-5.5 Pro

OpenAI highest-accuracy model for the hardest professional and agentic work.

Highest
Medium1M$30.00$180.00
35.1x
GPT-5.5

OpenAI frontier model for coding, professional work, and long-context agents.

Highest
Fast1M$5.00$0.50$30.00
5.6x
GPT-5.4

OpenAI flagship model for advanced coding, planning, and computer use.

Highest
Fast1M$2.50$0.25$15.00
2.8x
GPT-5.4 mini

OpenAI mini model tuned for fast coding, subagents, and computer-use tasks.

High
Fast400k$0.75$0.07$4.50
0.84x
GPT-5.4 nano

Lightweight OpenAI model for simple instructions, routing, and high-volume tasks.

Good
Very Fast400k$0.20$0.02$1.25
0.23x
Gemini 3.1 Pro

Higher-reasoning Gemini model for complex planning and analysis.

Highest
Fast1M$3.00$0.30$15.00
3.0x
Gemini 3 Flash

Fast default model for everyday agent execution.

High
Very Fast1M$1.00$0.10$5.00
1x (baseline)
Gemini 3.1 Flash

Fast Gemini tier that currently routes through the same runtime as Gemini 3 Flash.

High
Very Fast1M$1.00$0.10$5.00
1x (baseline)
DeepSeek V4 Pro

DeepSeek flagship model running through Clawcode for agentic coding and long-context reasoning.

Highest
Fast1M$0.43$0.04$0.87
0.28x
DeepSeek V4 Flash

Fast DeepSeek V4 model running through Clawcode for efficient agent execution.

High
Very Fast1M$0.14$0.03$0.28
0.09x
Kimi K2.6

Moonshot flagship served via Cloudflare Workers AI for long-horizon coding and agentic execution.

Highest
Fast262k$0.95$0.16$4.00
0.87x

Research Models

Specialized models for comprehensive web research, multi-source analysis, and detailed report generation.

ModelIntelligenceSpeedContextInput / 1MOutput / 1MBest For
Gemini 3 ProRecommended

Most capable research model with Deep Think reasoning and 1M token context.

Highest
Medium1M$2.00$12.00
Deep researchComplex reasoningComprehensive reports
Gemini 3 Flash

Fast research model, 3x faster than Pro with excellent cost efficiency.

Highest
Fast1M$0.50$3.00
Quick researchSummariesHigh-volume tasks

Image Generation Models

Create stunning visuals with our AI image generation models, from rapid prototypes to photorealistic artwork.

ModelQualitySpeedMax ResolutionPrice / ImageBest For
Gemini 3 Pro ImageRecommended

Premium image generation with up to 4K resolution and exceptional detail.

HighestMediumUp to 4096x4096
$0.134 2K
$0.24 4K
Professional graphicsMarketing assetsHigh-res artwork
Gemini 3 Flash Image

Fast image generation for rapid prototyping and high-volume workflows.

HighVery FastUp to 1024x1024
$0.039
Quick mockupsSocial mediaBatch generation

Flagship Models

Our most capable models with the highest intelligence and reasoning capabilities.

Claude Opus 4.7

Anthropic’s latest flagship for the most complex reasoning and agentic coding work.

5.0xrelative cost
Highest
Medium1M context
Pricing per 1M tokens
Input
$5.00
Cached
$0.50
Output
$25.00
Complex reasoningAgentic codingResearchLong-context analysis

GPT-5.5 Pro

OpenAI highest-accuracy model for the hardest professional and agentic work.

35.1xrelative cost
Highest
Medium1M context
Pricing per 1M tokens
Input
$30.00
Cached
Output
$180.00
Hard professional workHigh-accuracy reasoningTool useDeep analysis

GPT-5.5

OpenAI frontier model for coding, professional work, and long-context agents.

5.6xrelative cost
Highest
Fast1M context
Pricing per 1M tokens
Input
$5.00
Cached
$0.50
Output
$30.00
Complex codingAgentic workflowsProfessional workComputer use

GPT-5.4

OpenAI flagship model for advanced coding, planning, and computer use.

2.8xrelative cost
Highest
Fast1M context
Pricing per 1M tokens
Input
$2.50
Cached
$0.25
Output
$15.00
Complex codingAgentic workflowsComputer useDeep planning

Gemini 3.1 Pro

Higher-reasoning Gemini model for complex planning and analysis.

3.0xrelative cost
Highest
Fast1M context
Pricing per 1M tokens
Input
$3.00
Cached
$0.30
Output
$15.00
Complex reasoningLong-context analysisDeep planning

Kimi K2.6

Moonshot flagship served via Cloudflare Workers AI for long-horizon coding and agentic execution.

0.87xrelative cost
Highest
Fast262k context
Pricing per 1M tokens
Input
$0.95
Cached
$0.16
Output
$4.00
Long-horizon codingAgentic executionTool callingComplex UI generation

DeepSeek V4 Pro

DeepSeek flagship model running through Clawcode for agentic coding and long-context reasoning.

0.28xrelative cost
Highest
Fast1M context
Pricing per 1M tokens
Input
$0.43
Cached
$0.04
Output
$0.87
Agentic codingLong-context reasoningTool callingComplex planning

Claude Opus 4.6

Previous-generation flagship Claude model for complex reasoning and coding.

5.0xrelative cost
Highest
Medium1M context
Pricing per 1M tokens
Input
$5.00
Cached
$0.50
Output
$25.00
Complex reasoningResearchMulti-step analysisCoding

Claude Sonnet 4.5

Best balance of intelligence and speed. Excellent for coding and daily tasks.

3.0xrelative cost
High
Fast200k context
Pricing per 1M tokens
Input
$3.00
Cached
$0.30
Output
$15.00
CodingAnalysisGeneral tasksContent creation

Efficient Models

Fast and cost-effective for high-volume operations and simpler tasks.

GPT-5.4 mini

OpenAI mini model tuned for fast coding, subagents, and computer-use tasks.

0.84xrelative cost
High
Fast400k context
Pricing per 1M tokens
Input
$0.75
Cached
$0.07
Output
$4.50
CodingSubagentsComputer useFast iteration

GPT-5.4 nano

Lightweight OpenAI model for simple instructions, routing, and high-volume tasks.

0.23xrelative cost
Good
Very Fast400k context
Pricing per 1M tokens
Input
$0.20
Cached
$0.02
Output
$1.25
ClassificationRoutingSimple tasksHigh volume

Gemini 3 Flash

Fast default model for everyday agent execution.

1x (baseline)relative cost
High
Very Fast1M context
Pricing per 1M tokens
Input
$1.00
Cached
$0.10
Output
$5.00
General tasksFast iterationDaily workflows

Gemini 3.1 Flash

Fast Gemini tier that currently routes through the same runtime as Gemini 3 Flash.

1x (baseline)relative cost
High
Very Fast1M context
Pricing per 1M tokens
Input
$1.00
Cached
$0.10
Output
$5.00
General tasksFast iterationDaily workflows

DeepSeek V4 Flash

Fast DeepSeek V4 model running through Clawcode for efficient agent execution.

0.09xrelative cost
High
Very Fast1M context
Pricing per 1M tokens
Input
$0.14
Cached
$0.03
Output
$0.28
Fast agent executionHigh-volume workflowsTool callingDaily automation

Claude Haiku 4.5

Recommended

Fast and cost-effective for quick tasks and high-volume operations.

1x (baseline)relative cost
Good
Very Fast200k context
Pricing per 1M tokens
Input
$1.00
Cached
$0.10
Output
$5.00
Quick tasksClassificationSimple queriesHigh volume

About Pricing

All prices are in USD per 1 million tokens. Input tokens are charged when sending prompts to the model. Cached tokens are charged when using prompt caching (if supported). Output tokens are charged for model responses. Your actual cost depends on the model used and the complexity of your tasks.View subscription plans