Skip to main content

​
Supported AI Models

AIsa’s Unified LLM Gateway provides access to 50+ state-of-the-art AI models through a single API endpoint. Instead of managing multiple API keys, billing accounts, and rate limits across different providers, you can access the entire ecosystem with one integration. Our gateway supports models across all major modalities, including text generation, vision understanding, image generation, and audio processing.

​
Routing & Fallbacks

AIsa automatically handles rate limits and infrastructure failovers behind the scenes. When you request a model, our gateway routes your request to the optimal upstream provider or cloud deployment to ensure high availability and low latency. If a specific model deployment experiences downtime, AIsa can automatically fallback to alternative deployments of the same model without interrupting your application.

​
Model Catalog

The table below details every model currently supported by AIsa. For detailed pricing, see the aisa.one/models page.
Model NameDeveloperModalityContext Window
gpt-4.1OpenAIText, Vision1,048,576
gpt-4.1-miniOpenAIText, Vision1,048,576
gpt-4oOpenAIText, Vision, Audio128,000
gpt-4o-miniOpenAIText, Vision128,000
gpt-5OpenAIText, Vision400,000
gpt-5-miniOpenAIText, Vision400,000
gpt-5.2OpenAIText, Vision400,000
gpt-5.2-2025-12-11OpenAIText, Vision400,000
gpt-5.2-chat-latestOpenAIText, Vision400,000
gpt-5.3-codexOpenAIText, Code1,000,000
gpt-5.4OpenAIText, Vision1,050,000
gpt-oss-120bOpenAIText131,072
claude-3-7-sonnet-20250219AnthropicText, Vision200,000
claude-3-7-sonnet-20250219-thinkingAnthropicText, Vision200,000
claude-haiku-4-5-20251001AnthropicText, Vision200,000
claude-sonnet-4-20250514AnthropicText, Vision200,000
claude-sonnet-4-20250514-thinkingAnthropicText, Vision200,000
claude-sonnet-4-5-20250929AnthropicText, Vision200,000
claude-sonnet-4-6AnthropicText, Vision1,000,000
claude-sonnet-4-6-thinkingAnthropicText, Vision1,000,000
claude-opus-4-20250514AnthropicText, Vision200,000
claude-opus-4-20250514-thinkingAnthropicText, Vision200,000
claude-opus-4-1-20250805AnthropicText, Vision200,000
claude-opus-4-1-20250805-thinkingAnthropicText, Vision200,000
claude-opus-4-5-20251101AnthropicText, Vision1,000,000
claude-opus-4-6AnthropicText, Vision1,000,000
claude-opus-4-7AnthropicText, Vision1,000,000
gemini-2.5-flashGoogleText, Vision, Audio1,048,576
gemini-2.5-flash-liteGoogleText, Vision, Audio1,048,576
gemini-2.5-proGoogleText, Vision, Audio1,048,576
gemini-3-pro-previewGoogleText, Vision, Audio1,000,000
gemini-3.1-pro-previewGoogleText, Vision, Audio1,000,000
deepseek-r1DeepSeekText128,000
deepseek-v3.1DeepSeekText128,000
deepseek-v3.2DeepSeekText128,000
qwen-flashAlibabaText, Vision1,000,000
qwen-mt-flashAlibabaText (Translation)1,000,000
qwen-mt-liteAlibabaText (Translation)1,000,000
qwen-plus-2025-12-01AlibabaText, Vision, Audio1,000,000
qwen3-coder-480b-a35b-instructAlibabaText, Code262,144
qwen3-coder-flashAlibabaText, Code1,000,000
qwen3-coder-plusAlibabaText, Code1,000,000
qwen3-maxAlibabaText, Vision, Audio262,144
qwen3-vl-flashAlibabaText, Vision131,072
qwen3-vl-flash-2025-10-15AlibabaText, Vision131,072
qwen3-vl-plusAlibabaText, Vision131,072
qwen3.6-plusAlibabaText, Vision1,000,000
kimi-k2-thinkingMoonshotText256,000
kimi-k2.5MoonshotText, Vision, Video262,144
MiniMax-M2.5MiniMaxText262,144
glm-5Zhipu AIText128,000
seed-1-6-250915ByteDanceText, Vision262,144
seed-1-6-flash-250715ByteDanceText, Vision262,144
seed-1-8-251228ByteDanceText, Vision262,144
seed-2-0-mini-260215ByteDanceText, Vision262,144
seed-2-0-lite-260228ByteDanceText, Vision262,144
seed-2-0-pro-260328ByteDanceText, Vision262,144

​
Media Generation Models

Models that generate images or video are billed per asset rather than per token. For pricing details, see the AI Model Pricing page.
Model NameDeveloperModality
gemini-3-pro-image-previewGoogleImage Gen
seedream-4-5-251128ByteDanceImage Gen
wan2.7-imageAlibabaImage Gen
wan2.7-image-proAlibabaImage Gen
wan2.7-i2vAlibabaVideo Gen