Available Models

One API key works for all models. Just change the model parameter.

DeepSeek V3

Popular

by DeepSeek

Fast, capable general-purpose model. Great for chat, coding, and content generation.

Input: $0.42/M
Output: $0.63/M
Context: 64K
Fast responsesStrong coding abilityGood multilingual support
model="deepseek/deepseek-chat"

DeepSeek R1

Reasoning

by DeepSeek

Advanced reasoning model with chain-of-thought. Best for math, logic, and complex analysis.

Input: $0.42/M
Output: $0.63/M
Context: 64K
Chain-of-thought reasoningMath & logicStep-by-step analysis
model="deepseek/deepseek-reasoner"

Qwen Turbo

Cheapest

by Alibaba

Fastest and most affordable model. Ideal for high-volume tasks and simple queries.

Input: $0.10/M
Output: $0.39/M
Context: 128K
Lowest costFast speed128K context
model="qwen/qwen-turbo"

Qwen Plus

Flagship

by Alibaba

Alibaba's flagship model. Strong reasoning and 128K context for long documents.

Input: $0.17/M
Output: $2.34/M
Context: 128K
Strong reasoningLong contextMultilingual
model="qwen/qwen-plus"

MiniMax Text 01

1M Context

by MiniMax

Massive 1 million token context window. Perfect for analyzing entire codebases or books.

Input: $0.45/M
Output: $1.80/M
Context: 1M
1M token contextDocument analysisStrong multilingual
model="minimax/minimax-text-01"

GPT-4o

Industry Standard

by OpenAI

OpenAI's flagship model. Best for complex reasoning, creative writing, and multi-modal tasks.

Input: $3.75/M
Output: $15.00/M
Context: 128K
Complex reasoningCreative writingMulti-modal
model="openai/gpt-4o"

GPT-4o Mini

Value

by OpenAI

Fast and affordable OpenAI model. Great balance of cost and quality for everyday tasks.

Input: $0.23/M
Output: $0.90/M
Context: 128K
Low costFast128K context
model="openai/gpt-4o-mini"

Claude Sonnet 4

Best for Code

by Anthropic

Anthropic's best balance of speed and intelligence. Excellent at coding, analysis, and writing.

Input: $4.50/M
Output: $22.50/M
Context: 200K
Top-tier coding200K contextDetailed analysis
model="anthropic/claude-sonnet"

Claude Opus 4.6

Most Powerful

by Anthropic

Most powerful Anthropic model. Best for complex research, deep analysis, and difficult tasks.

Input: $7.50/M
Output: $37.50/M
Context: 200K
Deepest reasoning200K contextResearch-grade
model="anthropic/claude-opus"

GPT-4o

Industry Standard

by OpenAI

OpenAI's flagship model. Best for complex reasoning, creative writing, and multi-modal tasks.

Input: $3.75/M
Output: $15.00/M
Context: 128K
Complex reasoningCreative writingMulti-modal
model="openai/gpt-4o"

GPT-4o Mini

Value

by OpenAI

Fast and affordable OpenAI model. Great balance of cost and quality for everyday tasks.

Input: $0.23/M
Output: $0.90/M
Context: 128K
Low costFast128K context
model="openai/gpt-4o-mini"

GPT-4.1

Latest

by OpenAI

Latest OpenAI model with 1M token context window. Strong reasoning and long-document analysis.

Input: $3.00/M
Output: $12.00/M
Context: 1M
1M contextLatest modelStrong reasoning
model="openai/gpt-4.1"