Skip to content

Popular Models

This page provides detailed information about the most popular AI models supported by Pydantic AI, including pricing, specifications, and available inference providers. Each model card lists the shorthand (ID) that can be passed to the Agent class to use that model and provider combination:

Learn about Gateway
from pydantic_ai import Agent

agent = Agent('gateway/anthropic:claude-opus-4-5')

from pydantic_ai import Agent

agent = Agent('anthropic:claude-opus-4-5')

All popular models can be used via the Gateway.

For an overview of all supported providers, see Models and Providers.

About Modalities

Unless otherwise specified, "Modalities" refer to the types of data a model can accept as input. Output modality is implicitly Text for all models unless noted otherwise.

Anthropic Claude

Claude Opus 4.5

ID: anthropic:claude-opus-4-5

Anthropic's most intelligent model for complex reasoning and research.

Specifications:

  • Context: 200K tokens
  • Modalities: Text
  • Release: November 2025

Performance:

  • Cost 5
  • Speed 2
  • Intelligence 5

Alternative Providers:

  • Gateway:
    'gateway/anthropic:claude-opus-4-5'
  • AWS Bedrock:
    'bedrock:us.anthropic.claude-opus-4-5-20251101-v1:0'
  • OpenRouter:
    'openrouter:anthropic/claude-opus-4.5'

Pricing: $5.00 / $25.00 per 1M tokens (in/out)

Claude Sonnet 4.5

ID: anthropic:claude-sonnet-4-5

Best balance of speed, cost, and capability. Ideal for agents and coding.

Specifications:

  • Context: 1M tokens
  • Modalities: Text
  • Release: September 2025

Performance:

  • Cost 3
  • Speed 4
  • Intelligence 4

Alternative Providers:

  • Gateway:
    'gateway/anthropic:claude-sonnet-4-5'
  • AWS Bedrock:
    'bedrock:us.anthropic.claude-sonnet-4-5-20250929-v1:0'
  • OpenRouter:
    'openrouter:anthropic/claude-sonnet-4.5'

Pricing: $3.00-6.00 / $15.00-22.50 per 1M tokens (in/out)

Claude Haiku 4.5

ID: anthropic:claude-haiku-4-5

Fastest and most cost-effective. Ideal for high-volume tasks.

Specifications:

  • Context: 200K tokens
  • Modalities: Text
  • Release: October 2025

Performance:

  • Cost 1
  • Speed 5
  • Intelligence 3

Alternative Providers:

  • Gateway:
    'gateway/anthropic:claude-haiku-4-5'
  • AWS Bedrock:
    'bedrock:us.anthropic.claude-haiku-4-5-20251001-v1:0'
  • OpenRouter:
    'openrouter:anthropic/claude-haiku-4.5'

Pricing: $1.00 / $5.00 per 1M tokens (in/out)

Google Gemini

Gemini 3 Pro

ID: google-gla:gemini-3-pro-preview

Google's most capable model for complex multimodal tasks.

Specifications:

  • Context: 1M tokens
  • Modalities: Text, Vision
  • Release: Preview 2025

Performance:

  • Cost 4
  • Speed 3
  • Intelligence 5

Alternative Providers:

  • Gateway:
    'gateway/google-gla:gemini-3-pro-preview'
  • Vertex AI:
    'google-vertex:gemini-3-pro-preview'
  • OpenRouter:
    'openrouter:google/gemini-3-pro-preview'

Pricing: $2.00-4.00 / $12.00-18.00 per 1M tokens (in/out)

Gemini 3 Flash

ID: google-gla:gemini-3-flash-preview

Fast and efficient with excellent performance-to-cost ratio.

Specifications:

  • Context: 1M tokens
  • Modalities: Text, Audio
  • Release: Preview 2025

Performance:

  • Cost 2
  • Speed 5
  • Intelligence 4

Alternative Providers:

  • Gateway:
    'gateway/google-gla:gemini-3-flash-preview'
  • Vertex AI:
    'google-vertex:gemini-3-flash-preview'
  • OpenRouter:
    'openrouter:google/gemini-3-flash-preview'

Pricing: $0.50 / $3.00 per 1M tokens (in/out)

Gemini 2.5 Flash Lite

ID: google-gla:gemini-2.5-flash-lite

Most cost-effective with ultra-low latency for high-volume apps.

Specifications:

  • Context: 1M tokens
  • Modalities: Text, Audio
  • Release: 2025

Performance:

  • Cost 1
  • Speed 5
  • Intelligence 2

Alternative Providers:

  • Gateway:
    'gateway/google-gla:gemini-2.5-flash-lite'
  • Vertex AI:
    'google-vertex:gemini-2.5-flash-lite'
  • OpenRouter:
    'openrouter:google/gemini-2.5-flash-lite'

Pricing: $0.10 / $0.40 per 1M tokens (in/out)

OpenAI GPT

GPT-5.2 Pro

ID: openai:gpt-5.2-pro

Most intelligent reasoning model for complex tasks.

Specifications:

  • Context: 400K tokens
  • Modalities: Text
  • Release: December 2025

Performance:

  • Cost 4
  • Speed 3
  • Intelligence 5

Alternative Providers:

  • Gateway:
    'gateway/openai:gpt-5.2-pro'
  • Azure:
    'azure:gpt-5.2-pro'
  • OpenRouter:
    'openrouter:openai/gpt-5.2-pro'

Pricing: $21.00 / $168.00 per 1M tokens (in/out)

GPT-5.2

ID: openai:gpt-5.2

Flagship general-purpose model with excellent balance.

Specifications:

  • Context: 400K tokens
  • Modalities: Text
  • Release: December 2025

Performance:

  • Cost 3
  • Speed 4
  • Intelligence 4

Alternative Providers:

Pricing: $1.75 / $14.00 per 1M tokens (in/out)

xAI Grok

Grok 4

ID: grok:grok-4

Flagship reasoning model with excellent math and reasoning.

Specifications:

  • Context: 256K tokens
  • Modalities: Text, Vision
  • Release: July 2025

Performance:

  • Cost 2
  • Speed 4
  • Intelligence 4

Alternative Providers:

Pricing: $3.00 / $15.00 per 1M tokens (in/out)

Grok 4.1 Fast

ID: grok:grok-4-1-fast

Optimized for agentic tool calling with massive 2M context.

Specifications:

  • Context: 2M tokens
  • Modalities: Text, Vision
  • Release: 2025

Performance:

  • Cost 1
  • Speed 5
  • Intelligence 3

Alternative Providers:

Pricing: $0.20 / $0.50 per 1M tokens (in/out)

Performance Ratings: 1 = lowest, 5 = highest. Cost based on $/1M tokens, Speed on tokens/sec, Intelligence on benchmarks.
Sources: OpenRouter Rankings, Artificial Analysis, pydantic/genai-prices