Integrations

Providers & Models

Access 50+ top AI models from 6 leading providers through one unified API. Switch providers without changing your code.

OpenAI

GPT-5 series, GPT-4.1, and O-series reasoning models

gpt-5.2

Latest GPT-5.2 model - highest quality in GPT-5 series

$1.75 / 1M in $14.00 / 1M out

gpt-5.2-pro

Top-tier GPT-5.2 Pro - professional grade

$21.00 / 1M in $168.00 / 1M out

gpt-5-mini

Efficient GPT-5 variant - cost optimized

$0.25 / 1M in $2.00 / 1M out

o3

Advanced reasoning - excels at coding, math & science

$2.00 / 1M in $8.00 / 1M out

o1-pro

Professional-grade reasoning model - top performance

$150.00 / 1M in $600.00 / 1M out

gpt-4.1

Enhanced coding & instruction following

$2.00 / 1M in $8.00 / 1M out

gpt-5.1

GPT-5.1 - incremental improvement over GPT-5

$1.25 / 1M in $10.00 / 1M out

gpt-5

GPT-5 base model

$1.25 / 1M in $10.00 / 1M out

gpt-5-pro

Professional GPT-5 variant

$15.00 / 1M in $120.00 / 1M out

gpt-5-nano

Lightweight GPT-5 model - ultra efficient

$0.05 / 1M in $0.40 / 1M out

gpt-5-chat

Optimized for conversations

$1.25 / 1M in $10.00 / 1M out

gpt-5-codex

Specialized for coding tasks

$1.25 / 1M in $10.00 / 1M out

gpt-4.1-mini

Efficient GPT-4.1 variant

$0.40 / 1M in $1.60 / 1M out

gpt-4.1-nano

Lightweight GPT-4.1 model

$0.10 / 1M in $0.40 / 1M out

o3-pro

Most reliable reasoning model

$20.00 / 1M in $80.00 / 1M out

o4-mini

Fast reasoning model - math, coding & visual tasks

$3.00 / 1M in $12.00 / 1M out

Anthropic

Claude 4.5 Opus, Sonnet, Haiku, and Claude 3.5/3 Haiku

claude-opus-4-5-20251101

Claude Opus 4.5 - flagship model

$5.00 / 1M in $25.00 / 1M out

claude-sonnet-4-5-20250929

Claude Sonnet 4.5 - best for coding & agents

$3.00 / 1M in $15.00 / 1M out

claude-haiku-4-5

Claude Haiku 4.5 - low latency & cost-efficient

$1.00 / 1M in $5.00 / 1M out

claude-3-5-haiku-20241022

Claude Haiku 3.5 - fast and cost-efficient model

$0.25 / 1M in $1.25 / 1M out

claude-3-haiku-20240229

Claude Haiku 3 - efficient and affordable model

$0.25 / 1M in $1.25 / 1M out

Google

Gemini 2.5 Pro, Flash, Flash-Lite

gemini-2.5-pro

Gemini 2.5 Pro - high-capability multipurpose model

$1.25 / 1M in $10.00 / 1M out

gemini-2.5-flash

Gemini 2.5 Flash - fast high-throughput model

$0.30 / 1M in $2.50 / 1M out

gemini-2.5-flash-lite

Gemini 2.5 Flash-Lite - ultra cost-efficient model

$0.10 / 1M in $0.40 / 1M out

xAI

Grok 4, Grok 4 Fast, Grok Vision

grok-4

Grok 4 - latest flagship reasoning model

$3.00 / 1M in $15.00 / 1M out

grok-4-fast

Grok 4 Fast - speed optimized cost-efficient version

$0.20 / 1M in $0.50 / 1M out

grok-vision

Grok Vision - multimodal vision-capable model

$5.00 / 1M in $15.00 / 1M out

grok-4-fast-reasoning

Grok 4 Fast Reasoning - fast reasoning model with optimized pricing

$0.20 / 1M in $0.50 / 1M out

grok-4-1-fast-reasoning

Grok 4.1 Fast Reasoning - fast reasoning model with optimized pricing

$0.20 / 1M in $0.50 / 1M out

grok-4-1-fast-non-reasoning

Grok 4.1 Fast Non-Reasoning - fast non-reasoning model with optimized pricing

$0.20 / 1M in $0.50 / 1M out

grok-code-fast-1

Grok Code Fast 1 - fast code generation model with optimized pricing

$0.20 / 1M in $1.50 / 1M out

Cohere

Command A - advanced instruction-following model

command-a-03-2025

Command A - advanced instruction-following model (March 2025)

$2.50 / 1M in $10.00 / 1M out

Mistral AI

Mistral Large/Medium/Small (latest)

mistral-large-latest

Most capable Mistral model

$2.00 / 1M in $6.00 / 1M out

mistral-medium-latest

Balanced performance

$0.40 / 1M in $2.00 / 1M out

mistral-small-latest

Fast and efficient

$0.10 / 1M in $0.30 / 1M out

Start using all providers today

One API key, one endpoint. Switch between models and providers without changing your code.

Start free View docs