LLM Configuration

Skyvern uses LLMs to analyze screenshots and decide what actions to take. You’ll need to configure at least one LLM provider before running tasks.

How Skyvern uses LLMs

Skyvern makes multiple LLM calls per task step:

Screenshot analysis: Identify interactive elements on the page
Action planning: Decide what to click, type, or extract
Result extraction: Parse data from the page into structured output

A task that runs for 10 steps makes roughly 30+ LLM calls. Choose your provider and model tier with this in mind. For most deployments, configure a single provider using LLM_KEY. Skyvern also supports a SECONDARY_LLM_KEY for lighter tasks to reduce costs.

Quick Start Recommendations

Best models for production (2026):

Provider	Primary Model	Secondary Model	Notes
Anthropic	`ANTHROPIC_CLAUDE4.7_OPUS`	`ANTHROPIC_CLAUDE4.6_SONNET`	Most capable
OpenAI	`OPENAI_GPT5_5`	`OPENAI_GPT5_4`	Latest
Google	`GEMINI_3_PRO`	`GEMINI_3.0_FLASH`	Latest
AWS Bedrock	`BEDROCK_ANTHROPIC_CLAUDE4.7_OPUS_INFERENCE_PROFILE`	`BEDROCK_ANTHROPIC_CLAUDE4.6_SONNET_INFERENCE_PROFILE`	Latest Claude

OpenAI

The most common choice. Requires an API key from platform.openai.com.

.env

ENABLE_OPENAI=true
OPENAI_API_KEY=sk-...
LLM_KEY=OPENAI_GPT5_5

Available models

LLM_KEY	Notes
GPT-5.5
`OPENAI_GPT5_5`	Latest flagship, recommended for complex tasks
GPT-5 Series
`OPENAI_GPT5_4`
`OPENAI_GPT5`
`OPENAI_GPT5_MINI`
`OPENAI_GPT5_MINI_FLEX`	Flex service tier, 15min timeout
`OPENAI_GPT5_NANO`
`OPENAI_GPT5_1`
`OPENAI_GPT5_2`
GPT-4 Series
`OPENAI_GPT4O`
`OPENAI_GPT4O_MINI`
`OPENAI_GPT4_1`
`OPENAI_GPT4_1_MINI`
`OPENAI_GPT4_1_NANO`
`OPENAI_GPT4_5`
`OPENAI_GPT4_TURBO`	Legacy
`OPENAI_GPT4V`	Legacy alias
O-Series (Reasoning)
`OPENAI_O4_MINI`	Vision support
`OPENAI_O3`	Vision support
`OPENAI_O3_MINI`	No vision

Optional settings

.env

# Use a custom API endpoint (for proxies or compatible services)
OPENAI_API_BASE=https://your-proxy.com/v1

# Specify organization ID
OPENAI_ORGANIZATION=org-...

Anthropic

Claude models from anthropic.com.

.env

ENABLE_ANTHROPIC=true
ANTHROPIC_API_KEY=sk-ant-...
LLM_KEY=ANTHROPIC_CLAUDE4.7_OPUS

Available models

LLM_KEY	Notes
Claude 4.7
`ANTHROPIC_CLAUDE4.7_OPUS`	Latest, most capable
Claude 4.6
`ANTHROPIC_CLAUDE4.6_OPUS`
`ANTHROPIC_CLAUDE4.6_SONNET`	Recommended for secondary use
Claude 4.5
`ANTHROPIC_CLAUDE4.5_OPUS`
`ANTHROPIC_CLAUDE4.5_SONNET`
`ANTHROPIC_CLAUDE4.5_HAIKU`	Fastest
Claude 4
`ANTHROPIC_CLAUDE4_OPUS`
`ANTHROPIC_CLAUDE4_SONNET`
Claude 3.7
`ANTHROPIC_CLAUDE3.7_SONNET`
Claude 3.5
`ANTHROPIC_CLAUDE3.5_SONNET`
`ANTHROPIC_CLAUDE3.5_HAIKU`
Claude 3 (Legacy)
`ANTHROPIC_CLAUDE3_OPUS`
`ANTHROPIC_CLAUDE3_SONNET`
`ANTHROPIC_CLAUDE3_HAIKU`

Azure OpenAI

Microsoft-hosted OpenAI models. Requires an Azure subscription with OpenAI service provisioned.

.env

ENABLE_AZURE=true
LLM_KEY=AZURE_OPENAI
AZURE_DEPLOYMENT=your-deployment-name
AZURE_API_KEY=your-azure-api-key
AZURE_API_BASE=https://your-resource.openai.azure.com/
AZURE_API_VERSION=2024-08-01-preview

Setup steps

Create an Azure OpenAI resource in the Azure Portal
Open the Azure AI Foundry portal from your resource’s overview page
Go to Shared Resources → Deployments
Click Deploy Model → Deploy Base Model → select GPT-4o or GPT-4
Note the Deployment Name. Use this for AZURE_DEPLOYMENT
Copy your API key and endpoint from the Azure Portal

The AZURE_DEPLOYMENT is the name you chose when deploying the model, not the model name itself.

Google Gemini

Skyvern supports Gemini through two paths: the Gemini API (simpler, uses an API key) and Vertex AI (enterprise, uses a GCP service account).

Gemini API

The quickest way to use Gemini. Get an API key from Google AI Studio.

.env

ENABLE_GEMINI=true
GEMINI_API_KEY=your-gemini-api-key
LLM_KEY=GEMINI_2.5_PRO

Available Gemini API models

LLM_KEY	Notes
Gemini 3
`GEMINI_3_PRO`	Recommended for primary use
`GEMINI_3.0_FLASH`	Recommended for secondary use
`GEMINI_3.1_FLASH_LITE`	Fastest, most cost-efficient
Gemini 2.5
`GEMINI_2.5_PRO`
`GEMINI_2.5_PRO_PREVIEW`
`GEMINI_2.5_PRO_EXP_03_25`	Experimental
`GEMINI_2.5_FLASH`
`GEMINI_2.5_FLASH_PREVIEW`
Gemini 2.0
`GEMINI_FLASH_2_0`
`GEMINI_FLASH_2_0_LITE`
Gemini 1.5 Legacy
`GEMINI_PRO`
`GEMINI_FLASH`

Vertex AI

For enterprise deployments through Vertex AI. Requires a GCP project with Vertex AI enabled.

.env

ENABLE_VERTEX_AI=true
LLM_KEY=VERTEX_GEMINI_3_PRO
GOOGLE_APPLICATION_CREDENTIALS=/path/to/service-account.json
GCP_PROJECT_ID=your-gcp-project-id
VERTEX_LOCATION=us-central1

If you’re migrating from an older Skyvern version, VERTEX_LOCATION replaces the previous GCP_REGION variable. Update your .env accordingly.

Vertex AI setup steps:

Create a GCP project with billing enabled
Enable the Vertex AI API in your project
Create a service account with the Vertex AI User role
Download the service account JSON key file
Set GOOGLE_APPLICATION_CREDENTIALS to the path of that file

For global endpoint access, set VERTEX_LOCATION=global and ensure VERTEX_PROJECT_ID is set. Not all models support the global endpoint.

Available Vertex AI models

LLM_KEY	Notes
Gemini 3
`VERTEX_GEMINI_3_PRO`	Recommended for primary use
`VERTEX_GEMINI_3.0_FLASH`	Recommended for secondary use
`VERTEX_GEMINI_3.1_FLASH_LITE`	Fastest, most cost-efficient
Gemini 2.5
`VERTEX_GEMINI_2.5_PRO`
`VERTEX_GEMINI_2.5_PRO_PREVIEW`
`VERTEX_GEMINI_2.5_FLASH`
`VERTEX_GEMINI_2.5_FLASH_LITE`
`VERTEX_GEMINI_2.5_FLASH_PREVIEW`
Gemini 2.0
`VERTEX_GEMINI_FLASH_2_0`
Gemini 1.5 Legacy
`VERTEX_GEMINI_PRO`
`VERTEX_GEMINI_FLASH`

Amazon Bedrock

Run Anthropic Claude through your AWS account.

.env

ENABLE_BEDROCK=true
LLM_KEY=BEDROCK_ANTHROPIC_CLAUDE4.7_OPUS_INFERENCE_PROFILE
AWS_REGION=us-west-2
AWS_ACCESS_KEY_ID=AKIA...
AWS_SECRET_ACCESS_KEY=...

Setup steps

Create an IAM user with AmazonBedrockFullAccess policy
Generate access keys for the IAM user
In the Bedrock console, go to Model Access
Enable access to Claude Opus 4.7

Available models

LLM_KEY	Notes
Amazon Nova (AWS Native)
`BEDROCK_AMAZON_NOVA_PRO`
`BEDROCK_AMAZON_NOVA_LITE`
Claude 4.7
`BEDROCK_ANTHROPIC_CLAUDE4.7_OPUS_INFERENCE_PROFILE`	Cross-region, latest
Claude 4.6
`BEDROCK_ANTHROPIC_CLAUDE4.6_OPUS_INFERENCE_PROFILE`	Cross-region
`BEDROCK_ANTHROPIC_CLAUDE4.6_SONNET_INFERENCE_PROFILE`	Cross-region
Claude 4.5
`BEDROCK_ANTHROPIC_CLAUDE4.5_OPUS_INFERENCE_PROFILE`	Cross-region
`BEDROCK_ANTHROPIC_CLAUDE4.5_SONNET_INFERENCE_PROFILE`	Cross-region
Claude 4
`BEDROCK_ANTHROPIC_CLAUDE4_OPUS_INFERENCE_PROFILE`	Cross-region
`BEDROCK_ANTHROPIC_CLAUDE4_SONNET_INFERENCE_PROFILE`	Cross-region
Claude 3.7
`BEDROCK_ANTHROPIC_CLAUDE3.7_SONNET_INFERENCE_PROFILE`	Cross-region
Claude 3.5
`BEDROCK_ANTHROPIC_CLAUDE3.5_SONNET`	v2
`BEDROCK_ANTHROPIC_CLAUDE3.5_SONNET_V1`
`BEDROCK_ANTHROPIC_CLAUDE3.5_SONNET_INFERENCE_PROFILE`	Cross-region
`BEDROCK_ANTHROPIC_CLAUDE3.5_HAIKU`
Claude 3 (Legacy)
`BEDROCK_ANTHROPIC_CLAUDE3_OPUS`
`BEDROCK_ANTHROPIC_CLAUDE3_SONNET`
`BEDROCK_ANTHROPIC_CLAUDE3_HAIKU`

Bedrock inference profile keys (*_INFERENCE_PROFILE) use cross-region inference and require AWS_REGION only. No access keys needed if running on an IAM-authenticated instance.

MiniMax

MiniMax models with vision support.

.env

ENABLE_MINIMAX=true
MINIMAX_API_KEY=your-minimax-api-key
LLM_KEY=MINIMAX_M2_5

Available models

LLM_KEY	Notes
`MINIMAX_M2_5`
`MINIMAX_M2_5_HIGHSPEED`	Faster variant

Optional settings

.env

# Use a custom API endpoint
MINIMAX_API_BASE=https://api.minimax.io/v1

VolcEngine (ByteDance Doubao)

VolcEngine provides access to ByteDance’s Doubao models with vision support.

.env

ENABLE_VOLCENGINE=true
VOLCENGINE_API_KEY=your-volcengine-api-key
LLM_KEY=VOLCENGINE_DOUBAO_SEED_1_6

Available models

LLM_KEY	Notes
`VOLCENGINE_DOUBAO_SEED_1_6`	Recommended for general use
`VOLCENGINE_DOUBAO_SEED_1_6_FLASH`	Faster variant
`VOLCENGINE_DOUBAO_1_5_THINKING_VISION_PRO`	Reasoning model

Optional settings

.env

# Use a custom API endpoint
VOLCENGINE_API_BASE=https://ark.cn-beijing.volces.com/api/v3

Novita

Novita AI provides access to DeepSeek, Llama, and other open-source models.

.env

ENABLE_NOVITA=true
NOVITA_API_KEY=your-novita-api-key
LLM_KEY=NOVITA_LLAMA_3_2_11B_VISION

Available models

LLM_KEY	Notes
DeepSeek
`NOVITA_DEEPSEEK_R1`	Reasoning model
`NOVITA_DEEPSEEK_V3`
Llama 3.3
`NOVITA_LLAMA_3_3_70B`
Llama 3.2
`NOVITA_LLAMA_3_2_11B_VISION`	Vision support
`NOVITA_LLAMA_3_2_3B`
`NOVITA_LLAMA_3_2_1B`
Llama 3.1
`NOVITA_LLAMA_3_1_405B`
`NOVITA_LLAMA_3_1_70B`
`NOVITA_LLAMA_3_1_8B`
Llama 3
`NOVITA_LLAMA_3_70B`
`NOVITA_LLAMA_3_8B`

Moonshot

Moonshot AI provides the Kimi series models with long context support.

.env

ENABLE_MOONSHOT=true
MOONSHOT_API_KEY=your-moonshot-api-key
LLM_KEY=MOONSHOT_KIMI_K2

Available models

LLM_KEY	Notes
`MOONSHOT_KIMI_K2`

Optional settings

.env

# Use a custom API endpoint
MOONSHOT_API_BASE=https://api.moonshot.cn/v1

Inception

Inception AI provides the Mercury series models.

.env

ENABLE_INCEPTION=true
INCEPTION_API_KEY=your-inception-api-key
LLM_KEY=INCEPTION_MERCURY_2

Available models

LLM_KEY	Notes
`INCEPTION_MERCURY_2`

Optional settings

.env

# Use a custom API endpoint
INCEPTION_API_BASE=https://api.inception.ai/v1

Ollama (Local Models)

Run open-source models locally with Ollama. No API costs, but requires sufficient local compute.

.env

ENABLE_OLLAMA=true
LLM_KEY=OLLAMA
OLLAMA_MODEL=gemma4
OLLAMA_SERVER_URL=http://host.docker.internal:11434
OLLAMA_SUPPORTS_VISION=false

Setup steps

Install Ollama
Pull a model: ollama pull gemma4
Start Ollama: ollama serve
Configure Skyvern to connect

Most Ollama models don’t support vision. Set OLLAMA_SUPPORTS_VISION=false. Without vision, Skyvern relies on DOM analysis instead of screenshot analysis, which may reduce accuracy on complex pages.

Docker networking

When running Skyvern in Docker and Ollama on the host:

Host OS	OLLAMA_SERVER_URL
macOS/Windows	`http://host.docker.internal:11434`
Linux	`http://172.17.0.1:11434` (Docker bridge IP)

OpenAI-Compatible Endpoints

Connect to any service that implements the OpenAI API format, including LiteLLM, LocalAI, vLLM, and text-generation-inference.

.env

ENABLE_OPENAI_COMPATIBLE=true
OPENAI_COMPATIBLE_MODEL_NAME=gemma4
OPENAI_COMPATIBLE_API_KEY=sk-test
OPENAI_COMPATIBLE_API_BASE=http://localhost:4000/v1
LLM_KEY=OPENAI_COMPATIBLE

This is useful for:

Running local models with a unified API
Using LiteLLM as a proxy to switch between providers
Connecting to self-hosted inference servers

OpenRouter

Access multiple models through a single API at openrouter.ai.

.env

ENABLE_OPENROUTER=true
LLM_KEY=OPENROUTER
OPENROUTER_API_KEY=sk-or-...
OPENROUTER_MODEL=mistralai/mistral-small-3.1-24b-instruct

Groq

Inference on open-source models at groq.com.

.env

ENABLE_GROQ=true
LLM_KEY=GROQ
GROQ_API_KEY=gsk_...
GROQ_MODEL=llama-3.1-8b-instant

Groq specializes in fast inference for open-source models. Response times are typically much faster than other providers, but model selection is limited.

Using multiple models

Primary and secondary models

Configure a cheaper model for lightweight operations:

.env

# Main model for complex decisions
LLM_KEY=ANTHROPIC_CLAUDE4.7_OPUS
# or: OPENAI_GPT5_5
# or: GEMINI_3_PRO

# Faster model for simple tasks like dropdown selection
SECONDARY_LLM_KEY=ANTHROPIC_CLAUDE4.6_SONNET
# or: OPENAI_GPT5_4
# or: GEMINI_3.0_FLASH

Recommended primary models (latest):

Anthropic Claude 4.7 Opus (ANTHROPIC_CLAUDE4.7_OPUS) - Most capable
OpenAI GPT-5.5 (OPENAI_GPT5_5) - Latest
Google Gemini 3 Pro (GEMINI_3_PRO) - Latest

Recommended secondary models (latest):

Claude 4.6 Sonnet (ANTHROPIC_CLAUDE4.6_SONNET) - Balanced
GPT-5.4 (OPENAI_GPT5_4) - Fast reasoning
Gemini 3.0 Flash (GEMINI_3.0_FLASH) - Faster Gemini 3

Task-specific models

For fine-grained control, you can override models for specific operations:

.env

# Model for data extraction from pages (defaults to LLM_KEY if not set)
EXTRACTION_LLM_KEY=ANTHROPIC_CLAUDE4.5_SONNET

# Model for generating code/scripts in code blocks (defaults to LLM_KEY if not set)
SCRIPT_GENERATION_LLM_KEY=OPENAI_GPT5

Most deployments don’t need task-specific models. Start with LLM_KEY and SECONDARY_LLM_KEY.

Troubleshooting

”To enable svg shape conversion, please set the Secondary LLM key”

Some operations require a secondary model. Set SECONDARY_LLM_KEY in your environment:

.env

SECONDARY_LLM_KEY=OPENAI_GPT5_4

“Context window exceeded”

The page content is too large for the model’s context window. Options:

Use a model with larger context support (GPT-5.5, Gemini 2.5 Pro, or Claude 4.7 Opus)
Simplify your prompt to require less page analysis
Start from a more specific URL with less content

”LLM caller not found”

The configured LLM_KEY doesn’t match any enabled provider. Verify:

The provider is enabled (ENABLE_OPENAI=true, etc.)
The LLM_KEY value matches a supported model name exactly
Model names are case-sensitive: OPENAI_GPT5_5 not openai_gpt5_5

Container logs show authentication errors

Check your API key configuration:

Ensure the key is set correctly without extra whitespace
Verify the key hasn’t expired or been revoked
For Azure, ensure AZURE_API_BASE includes the full URL with https://

Slow response times

LLM calls typically take 2-10 seconds. Longer times may indicate:

Network latency to the provider
Rate limiting (the provider may be throttling requests)
For Ollama, insufficient local compute resources

Next steps

Browser Configuration

Configure browser modes, locales, and display settings

Docker Setup

Return to the main Docker setup guide

​How Skyvern uses LLMs

​Quick Start Recommendations

​OpenAI

​Available models

​Optional settings

​Anthropic

​Available models

​Azure OpenAI

​Setup steps

​Google Gemini

​Gemini API

​Available Gemini API models

​Vertex AI

​Available Vertex AI models

​Amazon Bedrock

​Setup steps

​Available models

​MiniMax

​Available models

​Optional settings

​VolcEngine (ByteDance Doubao)

​Available models

​Optional settings

​Novita

​Available models

​Moonshot

​Available models

​Optional settings

​Inception

​Available models

​Optional settings

​Ollama (Local Models)

​Setup steps

​Docker networking

​OpenAI-Compatible Endpoints

​OpenRouter

​Groq

​Using multiple models

​Primary and secondary models

​Task-specific models

​Troubleshooting

​”To enable svg shape conversion, please set the Secondary LLM key”

​“Context window exceeded”

​”LLM caller not found”

​Container logs show authentication errors

​Slow response times

​Next steps

Browser Configuration

Docker Setup

How Skyvern uses LLMs

Quick Start Recommendations

OpenAI

Available models

Optional settings

Anthropic

Available models

Azure OpenAI

Setup steps

Google Gemini

Gemini API

Available Gemini API models

Vertex AI

Available Vertex AI models

Amazon Bedrock

Setup steps

Available models

MiniMax

Available models

Optional settings

VolcEngine (ByteDance Doubao)

Available models

Optional settings

Novita

Available models

Moonshot

Available models

Optional settings

Inception

Available models

Optional settings

Ollama (Local Models)

Setup steps

Docker networking

OpenAI-Compatible Endpoints

OpenRouter

Groq

Using multiple models

Primary and secondary models

Task-specific models

Troubleshooting

”To enable svg shape conversion, please set the Secondary LLM key”

“Context window exceeded”

”LLM caller not found”

Container logs show authentication errors

Slow response times

Next steps