Skip to main content

​
Available Models

The Agentic Research API supports direct access to models from multiple providers. All models are accessed directly from first-party providers with transparent token-based pricing. Pricing rates are updated monthly and reflect direct first-party provider pricing with no markup. All charges are based on actual token consumption, and every API response includes exact token counts so you know your costs per request.
Not all third-party models support all features (e.g., reasoning, tools). Check model documentation for specific capabilities.
ModelInput PriceOutput PriceCache Read PriceProvider Documentation
Perplexity Models
perplexity/sonar$0.25 / 1M tokens$2.50 / 1M tokens$0.0625 / 1M tokensSonar
Anthropic Models
anthropic/claude-opus-4-5$5 / 1M tokens$25 / 1M tokens$0.50 / 1M tokensClaude Opus 4.5
anthropic/claude-sonnet-4-5$3 / 1M tokens$15 / 1M tokens$0.30 / 1M tokensClaude Sonnet 4.5
anthropic/claude-haiku-4-5$1 / 1M tokens$5 / 1M tokens$0.10 / 1M tokensClaude Haiku 4.5
OpenAI Models
openai/gpt-5.2$1.75 / 1M tokens$14 / 1M tokens$0.175 / 1M tokensGPT-5.2
openai/gpt-5.1$1.25 / 1M tokens$10 / 1M tokens$0.125 / 1M tokensGPT-5.1
openai/gpt-5-mini$0.25 / 1M tokens$2 / 1M tokens$0.025 / 1M tokensGPT-5 Mini
Google Models
google/gemini-3-pro-preview$2.00 / 1M tokens (≤200k context)
$4.00 / 1M tokens (>200k context)		$12.00 / 1M tokens (≤200k context)
$18.00 / 1M tokens (>200k context)		90% discountGemini 3.0 Pro
google/gemini-3-flash-preview$0.50 / 1M tokens$3.00 / 1M tokens90% discountGemini 3.0 Flash
google/gemini-2.5-pro$1.25 / 1M tokens (≤200k context)
$2.50 / 1M tokens (>200k context)		$10.00 / 1M tokens (≤200k context)
$15.00 / 1M tokens (>200k context)		90% discountGemini 2.5 Pro
google/gemini-2.5-flash$0.30 / 1M tokens$2.50 / 1M tokens90% discountGemini 2.5 Flash
xAI Models
xai/grok-4-1-fast-non-reasoning$0.20 / 1M tokens$0.50 / 1M tokens$0.05 / 1M tokensGrok 4.1
See Your Costs in Real-Time: Every response includes a usage field with exact input tokens, output tokens, and cache read tokens. Calculate your cost instantly using the pricing table above.Example response:
{
  "usage": {
    "input_tokens": 150,
    "output_tokens": 320,
    "total_tokens": 470
  }
}

​
Configuration Options

The Agentic Research API supports two ways to configure models:
  1. Presets: Pre-configured model setups optimized for specific use cases.
  2. Models: Direct model selection, including third-party models

​
Model Fallback

For high-availability applications, you can specify multiple models in a fallback chain. When one model fails or is unavailable, the API automatically tries the next model in the chain.

Model Fallback Chain

Learn how to use model fallback chains to ensure high availability and reliability by automatically trying multiple models when one fails.
Example:
response = client.responses.create(
    models=["openai/gpt-5.2", "openai/gpt-5.1", "openai/gpt-5-mini"],
    input="Your question here"
)
For detailed examples, pricing information, and best practices, see the Model Fallback documentation.

​
Next Steps

Model Fallback

Learn how to use model fallback chains for higher availability.

Presets

Explore available presets and their configurations.

Agentic Research API Quickstart

Get started with your first Agentic Research API call.

API Reference

View complete endpoint documentation.