Models

Choose a V4 model and understand its token pricing.

Omit model to use GPT-5.6 Luna, or pass a model ID when creating a run. These are the recommended Browser Use-hosted models with published token pricing:

Model	API string	Input	Cache read	Output	BYOK
GPT-5.6 Luna (recommended)	gpt-5.6-luna	$0.24	$0.024	$1.44	OpenAI
Claude Opus 5	claude-opus-5	$6.00	$0.60	$30.00	Anthropic
Grok 4.5	grok-4.5	$2.40	$0.36	$7.20	—
GPT-5.6 Sol	gpt-5.6-sol	$6.00	$0.60	$36.00	OpenAI
MiniMax M3	minimax-m3	$0.36	$0.072	$1.44	—

Token prices are USD per 1 million tokens. Browser sessions ($0.02/hour) and network traffic ($5/GB managed proxy or $0.20/GB proxyless/BYOP) are charged separately. See full pricing.

See Thinking levels for V4 modelParams and the normalized thinkingLevel values available in V2 and V3.

We recommend GPT-5.6 Luna for most tasks. It combines near-Opus benchmark performance with the lowest token price and fastest median response time in current V4 production traffic.

All supported V4 model IDs

The V4 request schema accepts the following model IDs. The Cloud dashboard may show a smaller curated set; availability can also depend on your account’s rollout and configured provider key.

Provider	Model IDs	BYOK provider
Anthropic	claude-opus-4.7, claude-opus-4.8, claude-opus-5, claude-fable-5, claude-sonnet-5	Anthropic
OpenAI	gpt-5.5, gpt-5.6, gpt-5.6-sol, gpt-5.6-terra, gpt-5.6-luna	OpenAI
Google	gemini-3-flash, gemini-3.1-pro, gemini-3.5-flash, gemini-3.6-flash	Google
xAI	grok-4.5	—
Z.ai	glm-5.2	—
Moonshot AI	kimi-k3	—
MiniMax	minimax-m3	—

See Thinking levels for the reasoning controls accepted by each model. Not every model accepts modelParams.

The current generated SDK request types predate this contract. The TypeScript model union does not yet include GPT-5.6 Luna or every model on this page, and neither generated V4 request model exposes modelParams. Use POST /api/v4/runs directly for those fields until the follow-up SDK regeneration is released.

Python

from browser_use_sdk.v4 import BrowserUse

client = BrowserUse()
run = client.runs.create(
    "Compare three project-management tools",
    model="gpt-5.6-luna",
)

Bring your own key

On plans with BYOK, add an Anthropic, OpenAI, or Google key under Settings → API Keys → Bring Your Own Key. V4 uses it automatically for matching models; no request flag is needed. You pay the provider directly, plus a 0.2× Browser Use orchestration fee. Models from other providers use Browser Use-managed keys.