AI model directory
AI models through one API
Compare supported AI models by provider, pricing, context window and capabilities. Access them through one OpenAI-compatible TokenGate integration.
- 32 models
- 5 providers
- OpenAI-compatible
- USDT payments
Current models
GPT-6 Astra
OpenAI's flagship model for complex reasoning, coding, research, computer use and demanding professional workflows.
- Input / 1M
- $10.00
- Output / 1M
- $50.00
- Context
- 1.05M
- Generation
- 6
Streaming · Function calling · Structured outputs
GPT-6 Astra API pricingGPT-5.6 Luna
Cost-focused GPT-5.6 model for high-volume workloads, routine automation and applications where API efficiency matters.
- Input / 1M
- $0.20
- Output / 1M
- $1.20
- Context
- 1.05M
- Generation
- 5.6
Streaming · Function calling · Structured outputs
GPT-5.6 Luna API pricingGPT-5.6 Sol
OpenAI's GPT-5.6 flagship tier for complex professional work, coding and agentic workflows.
- Input / 1M
- $4.00
- Output / 1M
- $20.00
- Context
- 1.05M
- Generation
- 5.6
Streaming · Function calling · Structured outputs
GPT-5.6 Sol API pricingGPT-5.6 Terra
GPT-5.6 model designed to balance intelligence, capability and API cost for production workloads.
- Input / 1M
- $2.00
- Output / 1M
- $12.00
- Context
- 1.05M
- Generation
- 5.6
Streaming · Function calling · Structured outputs
GPT-5.6 Terra API pricingClaude Fable 5.1
Anthropic's most capable generally available model for ambitious coding, long-running agents, research and complex knowledge work.
- Input / 1M
- $10.00
- Output / 1M
- $50.00
- Context
- —
- Generation
- 5.1
Streaming · Function calling · Vision
Claude Fable 5.1 API pricingClaude Sonnet 5
Anthropic's production-focused Sonnet model combining strong agentic and coding capabilities with lower API cost.
- Input / 1M
- $2.00
- Output / 1M
- $10.00
- Context
- —
- Generation
- 5
Streaming · Function calling · Vision
Claude Sonnet 5 API pricingClaude Opus 5
Anthropic's Opus model for advanced coding, reasoning, long-running agents and professional knowledge work.
- Input / 1M
- $5.00
- Output / 1M
- $25.00
- Context
- —
- Generation
- 5
Streaming · Function calling · Vision
Claude Opus 5 API pricingGrok 4.6
xAI's current flagship model for coding, agentic tasks, tool use and general knowledge work.
- Input / 1M
- $2.00
- Output / 1M
- $6.00
- Context
- 500K
- Generation
- 4.6
Function calling · Structured outputs · Vision
Grok 4.6 API pricingDeepSeek V4.1 Flash
DeepSeek's current Flash model with native multimodal support and strong coding, reasoning and agentic capabilities.
- Input / 1M
- Variable pricing
- Output / 1M
- —
- Context
- —
- Generation
- 4.1
Streaming · Function calling · Structured outputs
DeepSeek V4.1 Flash API pricingGemini 3.8 Flash
Google's current production Flash model for long-horizon software engineering, autonomous agents and complex multimodal workflows.
- Input / 1M
- $0.75
- Output / 1M
- $3.75
- Context
- 1.05M
- Generation
- 3.8
Streaming · Function calling · Structured outputs
Gemini 3.8 Flash API pricingClaude Opus 4.8
Previous-generation Opus model for advanced coding, agents and professional knowledge work.
- Input / 1M
- $5.00
- Output / 1M
- $25.00
- Context
- —
- Generation
- 4.8
Streaming · Function calling · Vision
Claude Opus 4.8 API pricingClaude Sonnet 4.6
Previous-generation Sonnet model with strong coding, agent planning, computer-use and long-context capabilities.
- Input / 1M
- $3.00
- Output / 1M
- $15.00
- Context
- 1M
- Generation
- 4.6
Streaming · Function calling · Vision
Claude Sonnet 4.6 API pricingClaude Haiku 4.5
Anthropic's fast and cost-efficient Haiku model for high-volume workloads and lightweight agentic tasks.
- Input / 1M
- $1.00
- Output / 1M
- $5.00
- Context
- —
- Generation
- 4.5
Streaming · Function calling · Vision
Claude Haiku 4.5 API pricingGrok 4.5
Previous-generation xAI model with a 500K context window for coding and agentic tasks.
- Input / 1M
- $2.00
- Output / 1M
- $6.00
- Context
- 500K
- Generation
- 4.5
Function calling · Structured outputs · Vision
Grok 4.5 API pricingGrok 4.3
xAI model with a 1M-token context window for long-context coding and agentic workloads.
- Input / 1M
- $1.25
- Output / 1M
- $2.50
- Context
- 1M
- Generation
- 4.3
Function calling · Structured outputs · Vision
Grok 4.3 API pricingGemini 3.7 Flash
Previous-generation Google Flash model with multimodal input and a large context window.
- Input / 1M
- $0.75
- Output / 1M
- $3.75
- Context
- 1.05M
- Generation
- 3.7
Streaming · Function calling · Structured outputs
Gemini 3.7 Flash API pricingGemini 3.6 Flash
Previous-generation Google Flash model for everyday coding and agentic tasks.
- Input / 1M
- $0.75
- Output / 1M
- $3.75
- Context
- —
- Generation
- 3.6
Streaming · Function calling · Structured outputs
Gemini 3.6 Flash API pricingGemini 3.5 Flash
Google Flash model with a large context window for high-volume multimodal workloads.
- Input / 1M
- $1.50
- Output / 1M
- $9.00
- Context
- 1.05M
- Generation
- 3.5
Streaming · Function calling · Structured outputs
Gemini 3.5 Flash API pricingGemini 3.5 Flash-Lite
Google's cost-efficient model for high-volume agentic tasks, translation and simple data processing.
- Input / 1M
- $0.30
- Output / 1M
- $2.50
- Context
- —
- Generation
- 3.5
Streaming · Function calling · Structured outputs
Gemini 3.5 Flash-Lite API pricingGemini 3.1 Pro Preview
Google's Pro preview model for complex reasoning, coding and multimodal agentic work.
- Input / 1M
- Variable pricing
- Output / 1M
- —
- Context
- 1.05M
- Generation
- 3.1
Streaming · Function calling · Structured outputs
Gemini 3.1 Pro Preview API pricingPrevious & legacy models
Historical pricing and specifications, preserved for reference and migration.
GPT-4o
OpenAI's earlier multimodal model, kept here for historical API pricing and specification reference.
- Input / 1M
- $2.50
- Output / 1M
- $10.00
- Context
- 128K
- Generation
- 4o
Historical pricing
Streaming · Function calling · Vision
GPT-4o API pricingGPT-4o mini
Small and inexpensive earlier OpenAI model, kept for historical pricing and specification reference.
- Input / 1M
- $0.15
- Output / 1M
- $0.60
- Context
- 128K
- Generation
- 4o
Historical pricing
Streaming · Function calling · Vision
GPT-4o mini API pricingDeepSeek-V3
Earlier DeepSeek chat model, kept for historical API pricing and specification reference.
- Input / 1M
- $0.50
- Output / 1M
- $2.00
- Context
- 64K
- Generation
- 3
Historical pricing
Streaming · Function calling · JSON mode
DeepSeek-V3 API pricingGrok 2
Earlier xAI chat model, kept for historical API pricing and specification reference.
- Input / 1M
- $5.00
- Output / 1M
- $15.00
- Context
- 131K
- Generation
- 2
Historical pricing
Streaming · Function calling · Vision
Grok 2 API pricingGrok 2 Mini
Smaller earlier xAI model, kept for historical API pricing and specification reference.
- Input / 1M
- $0.60
- Output / 1M
- $2.00
- Context
- 131K
- Generation
- 2
Historical pricing
Streaming · Function calling · Vision
Grok 2 Mini API pricingGemini 1.5 Pro
Earlier Google Pro model with a very large context window, kept for historical reference.
- Input / 1M
- $1.25
- Output / 1M
- $5.00
- Context
- 2M
- Generation
- 1.5
Historical pricing
Streaming · Function calling · Vision
Gemini 1.5 Pro API pricingDeepSeek-R1
Earlier DeepSeek reasoning model, kept for historical API pricing and specification reference.
- Input / 1M
- $0.55
- Output / 1M
- $2.19
- Context
- 64K
- Generation
- R1
Historical pricing
Streaming · Function calling · JSON mode
DeepSeek-R1 API pricingo1
Earlier OpenAI reasoning model, kept for historical API pricing and specification reference.
- Input / 1M
- $15.00
- Output / 1M
- $60.00
- Context
- 200K
- Generation
- o1
Historical pricing
Function calling · JSON mode · Reasoning
o1 API pricingo3-mini
Compact earlier OpenAI reasoning model, kept for historical API pricing and specification reference.
- Input / 1M
- $1.10
- Output / 1M
- $4.40
- Context
- 200K
- Generation
- o3
Historical pricing
Streaming · Function calling · JSON mode
o3-mini API pricingClaude 3.7 Sonnet
Retired Anthropic coding and reasoning model. This page preserves its historical API pricing and specifications.
- Input / 1M
- $3.00
- Output / 1M
- $15.00
- Context
- 200K
- Generation
- 3.7
Historical pricing
Streaming · Function calling · Vision
Claude 3.7 Sonnet API pricingClaude 3.5 Haiku
Retired fast and affordable Anthropic model. This page preserves its historical API pricing and specifications.
- Input / 1M
- $0.80
- Output / 1M
- $4.00
- Context
- 200K
- Generation
- 3.5
Historical pricing
Streaming · Function calling · Vision
Claude 3.5 Haiku API pricingGemini 2.0 Flash
Retired Google Flash model. This page preserves its historical API pricing and specifications.
- Input / 1M
- $0.10
- Output / 1M
- $0.40
- Context
- 1M
- Generation
- 2.0
Historical pricing
Streaming · Function calling · Vision
Gemini 2.0 Flash API pricingOne API for multiple AI providers
TokenGate is an AI API gateway for accessing supported models from multiple providers through one integration. Instead of maintaining separate API integrations for each provider, developers can use a unified OpenAI-compatible interface and pay through TokenGate using USDT.