AIsa LLM Model Catalog - API Endpoints, Capabilities, Context Windows

Complete AIsa LLM and media model catalog for llms.txt: exact model IDs, providers, API endpoints, capabilities, context windows, and billing for all 124 models — GPT, Claude, Gemini, Grok, DeepSeek, Qwen, Kimi, MiniMax, GLM, Seed, Seedream, Dreamina, Wan, Hunyuan, StepFun, MiMo, and Jina — through https://api.aisa.one/v1.

AIsa’s Model Gateway routes LLM and media-generation requests through one API key. This guide is the stable Markdown source for agents that read llms.txt and need to understand which AIsa model IDs exist, which endpoint each model uses, and what each model can do.

The live catalog is aisa.one/models. The tables below cover all 124 models in the gateway as of September 30, 2026, and list how each model is billed, not its price. Current prices and availability are on the live catalog; use it as the final source of truth before production routing.

How to call models

Use your AISA_API_KEY as a Bearer token. For OpenAI-compatible SDKs, set the base URL to https://api.aisa.one/v1.

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_AISA_API_KEY",
    base_url="https://api.aisa.one/v1"
)

response = client.chat.completions.create(
    model="qwen3.7-max",
    messages=[{"role": "user", "content": "Compare these model options for a coding agent."}]
)
print(response.choices[0].message.content)

Endpoint types

Endpoint	Current model count
POST /v1/chat/completions	101
POST /v1/messages	89
POST /v1/responses	80
POST /v1/video/generations	9
POST /v1/images/generations	6
POST /v1/images/edits	5
POST /v1/embeddings	4
POST /v1beta/models/{model}:generateContent	1
POST /v1/classify	1
POST /v1/rerank	1
POST /v1/systemone	1

Most text, vision, and coding models accept both OpenAI-style chat/completions and Anthropic-compatible messages, so the same model ID works from either SDK. POST /v1/responses is now served by most text models — the table above counts the routes from the August 5, 2026 metadata export combined with those reported by the live gateway pricing feed on September 30, 2026. The live feed can omit routes a model actually serves, so newly added models may be missing messages or responses in their Endpoint(s) column. Calling a model on a route it does not serve returns 400 model_route_not_supported with the supported routes listed, so probe before switching protocols. Gemini models additionally expose generateContent. Image models use images/generations and images/edits. Video models are asynchronous: submit the job to POST /v1/video/generations, then poll /v1/video/generations/{task_id} for the result. Embedding models use /v1/embeddings; the Jina reranker uses /v1/rerank. Always pass the exact model string shown below.

Capability vocabulary

Capability	What it means in AIsa Model Gateway
Text	Natural-language generation, summarization, analysis, translation, and long-context reasoning.
Coding	Code reasoning, code completion, software-agent planning, and tool-use workflows.
Vision	Image/document understanding, visual coding, and spatial reasoning over visual inputs.
Audio	Audio understanding or speech-to-speech style interaction where supported by the upstream model.
Image	Image generation, image editing, image consistency, or rendering text in images.
Video	Video understanding, temporal reasoning, long-video work, image-to-video, or omni/video workflows.

Provider summary

Provider	Models	Types	Example model IDs
OpenAI	29	Embeddings, Image, Text	gpt-4.1-mini, gpt-4o, gpt-4o-mini, gpt-5-nano …
Anthropic	13	Text	claude-fable-5, claude-fable-5-1, claude-haiku-4-5-20251001, claude-opus-4-5-20251101 …
Google Gemini	1	Text	gemini-3.5-flash
xAI	7	Text	grok-4.20-0309-non-reasoning, grok-4.20-0309-reasoning, grok-4.3, grok-4.5 …
DeepSeek	10	Text	deepseek-r1, deepseek-v3, deepseek-v3.1, deepseek-v3.2 …
Alibaba	24	Image, Text, Video	qwen-flash, qwen-mt-flash, qwen-mt-lite, qwen-plus-2025-12-01 …
Moonshot	5	Text	kimi-k2-thinking, kimi-k2.5, kimi-k2.6, kimi-k2.7-code …
MiniMax	4	Text	MiniMax-M2.5, MiniMax-M2.7, MiniMax-M2.7-highspeed, MiniMax-M3
Zhipu GLM	6	Text	glm-5, glm-5.1, glm-5.2, glm-5.3 …
ByteDance	10	Image, Text, Video	dreamina-seedance-2-0-260128, dreamina-seedance-2-0-fast-260128, dreamina-seedance-2-5, seed-1-6-250915 …
Tencent	2	Text	hy3, hy4-preview
Xiaomi	3	Text	mimo-v2.6-flash, mimo-v2.6-pro, mimo-v2.6-pro-ultraspeed
StepFun	3	Text	step-3.5-flash, step-3.5-flash-2603, step-3.7-flash
HappyHorse	3	Video	happyhorse-1.1-i2v, happyhorse-1.1-r2v, happyhorse-1.1-t2v
Jina	3	Embeddings	jina-embeddings-v3, jina-embeddings-v5-text-small, jina-reranker-v3
TypeSafe	1	Text	jev-latest

Complete model details

Context windows and capability tags come from the last Model Gateway metadata export. Models added since then show — for context and only their base type in Capabilities — check aisa.one/models for their current limits and capability tags.

OpenAI

Model ID	Context	Capabilities	Endpoint(s)	Billed by
gpt-4.1-mini	—	Text	/v1/chat/completions, /v1/messages, /v1/responses	Per 1M tokens: input, output, cache read
gpt-4o	—	Text	/v1/chat/completions, /v1/messages, /v1/responses	Per 1M tokens: input, output, cache read
gpt-4o-mini	—	Text	/v1/chat/completions, /v1/messages, /v1/responses	Per 1M tokens: input, output, cache read
gpt-5-nano	—	Text	/v1/chat/completions, /v1/messages, /v1/responses	Per 1M tokens: input, output, cache read
gpt-5-pro	—	Text	/v1/chat/completions, /v1/messages, /v1/responses	Per 1M tokens: input, output
gpt-5-search-api	—	Text	/v1/chat/completions, /v1/messages, /v1/responses	Per 1M tokens: input, output, cache read
gpt-5.1	—	Text	/v1/chat/completions, /v1/messages, /v1/responses	Per 1M tokens: input, output, cache read
gpt-5.2	400,000	Coding, Text, Vision; reasoning, long context, translation, creative writing, spatial vision, document vision, code reasoning, code completion, agentic coding	/v1/chat/completions, /v1/messages, /v1/responses	Per 1M tokens: input, output, cache read
gpt-5.2-chat-latest	400,000	Coding, Text, Vision; reasoning, long context, translation, creative writing, spatial vision, document vision, visual coding, code reasoning, code completion, agentic coding	/v1/chat/completions, /v1/messages, /v1/responses	Per 1M tokens: input, output, cache read
gpt-5.2-pro	—	Text	/v1/chat/completions, /v1/messages, /v1/responses	Per 1M tokens: input, output
gpt-5.3-chat-latest	—	Text	/v1/chat/completions, /v1/messages, /v1/responses	Per 1M tokens: input, output, cache read
gpt-5.3-codex	1,000,000	Coding, Text; reasoning, long context, code reasoning, code completion, agentic coding	/v1/chat/completions, /v1/messages, /v1/responses	Per 1M tokens: input, output, cache read
gpt-5.4	1,050,000	Coding, Text, Vision; reasoning, long context, translation, creative writing, spatial vision, document vision, visual coding, code reasoning, code completion, agentic coding	/v1/chat/completions, /v1/messages, /v1/responses	Per 1M tokens: input, output, cache read
gpt-5.4-mini	—	Text	/v1/chat/completions, /v1/messages, /v1/responses	Per 1M tokens: input, output, cache read
gpt-5.4-nano	—	Text	/v1/chat/completions, /v1/messages, /v1/responses	Per 1M tokens: input, output, cache read
gpt-5.4-pro	—	Text	/v1/chat/completions, /v1/messages, /v1/responses	Per 1M tokens: input, output
gpt-5.5	400,000	Coding, Text, Vision; code reasoning, long context, reasoning, vision	/v1/chat/completions, /v1/messages, /v1/responses	Per 1M tokens: input, output, cache read
gpt-5.5-pro	—	Text	/v1/chat/completions, /v1/messages, /v1/responses	Per 1M tokens: input, output
gpt-5.6-luna	—	Text	/v1/chat/completions, /v1/messages, /v1/responses	Per 1M tokens: input, output, cache read, cache write
gpt-5.6-sol	—	Text	/v1/chat/completions, /v1/messages, /v1/responses	Per 1M tokens: input, output, cache read, cache write
gpt-5.6-terra	—	Text	/v1/chat/completions, /v1/messages, /v1/responses	Per 1M tokens: input, output, cache read, cache write
gpt-6-astra	—	Text	/v1/chat/completions, /v1/messages, /v1/responses	Per 1M tokens: input, output, cache read, cache write
gpt-6-luna	—	Text	/v1/chat/completions, /v1/messages, /v1/responses	Per 1M tokens: input, output, cache read, cache write
gpt-6-sol	—	Text	/v1/chat/completions, /v1/messages, /v1/responses	Per 1M tokens: input, output, cache read, cache write
gpt-image-2	N/A	Image, Vision; image editing, image generation, text in images, vision	/v1/images/generations, /v1/images/edits	Per 1M tokens: input, output, cache write; Per request; Per image, by size
gpt-image-2.5-flare	—	Image	/v1/images/generations, /v1/images/edits	Per 1M tokens: input, output, cache read
gpt-image-2.5-sunburst	—	Image	/v1/images/generations, /v1/images/edits	Per 1M tokens: input, output, cache read
text-embedding-3-large	—	Embeddings	/v1/embeddings	Per 1M tokens: input
text-embedding-3-small	—	Embeddings	/v1/embeddings	Per 1M tokens: input

Anthropic

Model ID	Context	Capabilities	Endpoint(s)	Billed by
claude-fable-5	—	Text	/v1/chat/completions, /v1/messages	Per 1M tokens: input, output, cache read, cache write
claude-fable-5-1	—	Text	/v1/messages	Per 1M tokens: input, output, cache write
claude-haiku-4-5-20251001	200,000	Coding, Text, Vision; reasoning, long context, spatial vision, document vision, visual coding, code reasoning, agentic coding	/v1/chat/completions, /v1/messages	Per 1M tokens: input, output, cache read, cache write
claude-opus-4-5-20251101	1,000,000	Coding, Text, Vision; reasoning, long context, creative writing, document vision, visual coding, code reasoning, code completion, agentic coding	/v1/chat/completions, /v1/messages	Per 1M tokens: input, output, cache read, cache write
claude-opus-4-6	1,000,000	Coding, Text, Vision; reasoning, long context, creative writing, document vision, visual coding, code reasoning, code completion, agentic coding	/v1/chat/completions, /v1/messages	Per 1M tokens: input, output, cache read, cache write
claude-opus-4-7	1,000,000	Coding, Text, Vision; reasoning, long context, creative writing, spatial vision, document vision, visual coding, code reasoning, code completion, agentic coding	/v1/chat/completions, /v1/messages, /v1/responses	Per 1M tokens: input, output, cache read, cache write
claude-opus-4-8	1,000,000	Coding, Text, Vision; reasoning, long context, creative writing, spatial vision, document vision, visual coding, code reasoning, code completion, agentic coding	/v1/chat/completions, /v1/messages	Per 1M tokens: input, output, cache read, cache write
claude-opus-5	—	Text	/v1/chat/completions, /v1/messages	Per 1M tokens: input, output, cache read, cache write
claude-opus-5-5	—	Text	/v1/messages	Per 1M tokens: input, output, cache read, cache write
claude-sonnet-4-5-20250929	200,000	Coding, Text, Vision; reasoning, long context, creative writing, spatial vision, document vision, visual coding, code reasoning, code completion, agentic coding	/v1/chat/completions, /v1/messages	Per 1M tokens: input, output, cache read, cache write
claude-sonnet-4-6	—	Text	/v1/chat/completions, /v1/messages	Per 1M tokens: input, output, cache read, cache write
claude-sonnet-5	—	Text	/v1/chat/completions, /v1/messages	Per 1M tokens: input, output, cache read, cache write
claude-sonnet-5-5	—	Text	/v1/chat/completions, /v1/messages, /v1/responses	Per 1M tokens: input, output, cache read, cache write

Google Gemini

Model ID	Context	Capabilities	Endpoint(s)	Billed by
gemini-3.5-flash	N/A	Text; long context, creative writing	/v1/chat/completions, /v1beta/models/{model}:generateContent	Per 1M tokens: input, output, cache read

xAI

Model ID	Context	Capabilities	Endpoint(s)	Billed by
grok-4.20-0309-non-reasoning	1,000,000	Text, Vision; long context, creative writing, spatial vision, document vision	/v1/chat/completions	Per 1M tokens: input, output
grok-4.20-0309-reasoning	1,000,000	Text, Vision; reasoning, long context, creative writing, spatial vision, document vision	/v1/chat/completions	Per 1M tokens: input, output
grok-4.3	1,000,000	Text, Vision; reasoning, long context, creative writing, spatial vision, document vision	/v1/chat/completions	Per 1M tokens: input, output
grok-4.5	—	Text	/v1/chat/completions, /v1/messages, /v1/responses	Per 1M tokens: input, output, cache write
grok-4.6	—	Text	/v1/chat/completions, /v1/messages, /v1/responses	Per 1M tokens: input, output, cache read
grok-4.7	—	Text	/v1/chat/completions, /v1/messages, /v1/responses	Per 1M tokens: input, output, cache read
grok-build-0.1	256,000	Coding, Text, Vision; reasoning, long context, visual coding, code reasoning, code completion, agentic coding	/v1/chat/completions	Per 1M tokens: input, output

DeepSeek

Model ID	Context	Capabilities	Endpoint(s)	Billed by
deepseek-r1	262,144	Coding, Text; code reasoning, long context, reasoning	/v1/chat/completions, /v1/messages, /v1/responses	Per 1M tokens: input, output, cache read
deepseek-v3	262,144	Coding, Text; code reasoning, long context, reasoning	/v1/chat/completions, /v1/messages, /v1/responses	Per 1M tokens: input, output, cache read
deepseek-v3.1	262,144	Coding, Text; code reasoning, long context, reasoning	/v1/chat/completions, /v1/messages, /v1/responses	Per 1M tokens: input, output, cache read
deepseek-v3.2	128,000	Coding, Text; reasoning, long context, creative writing, code reasoning, code completion, agentic coding	/v1/chat/completions, /v1/messages, /v1/responses	Per 1M tokens: input, output, cache read
deepseek-v4-flash	262,144	Coding, Text; code reasoning, long context, reasoning	/v1/chat/completions, /v1/messages, /v1/responses	Per 1M tokens: input, output, cache read
deepseek-v4-flash-0731	—	Text	/v1/chat/completions, /v1/messages, /v1/responses	Per 1M tokens: input, output, cache write
deepseek-v4-flash-vision-exp	—	Text	/v1/chat/completions, /v1/messages, /v1/responses	Per 1M tokens: input, output, cache write
deepseek-v4-pro	262,144	Coding, Text; code reasoning, long context, reasoning	/v1/chat/completions, /v1/messages, /v1/responses	Per 1M tokens: input, output, cache read
deepseek-v4-pro-0813	—	Text	/v1/chat/completions, /v1/messages, /v1/responses	Per 1M tokens: input, output, cache write
deepseek-v4.1-flash	—	Text	/v1/chat/completions, /v1/messages, /v1/responses	Per 1M tokens: input, output, cache write

Alibaba

Model ID	Context	Capabilities	Endpoint(s)	Billed by
qwen-flash	1,000,000	Audio, Coding, Text, Video, Vision; reasoning, long context, translation, creative writing, spatial vision, document vision, visual coding, speech-to-speech, omni/video understanding, long video, temporal video, code reasoning, code completion, agentic coding	/v1/chat/completions, /v1/messages, /v1/responses	Per 1M tokens: input, output, cache read, cache write
qwen-mt-flash	1,000,000	Text; long context, translation	/v1/chat/completions, /v1/messages, /v1/responses	Per 1M tokens: input, output, cache read
qwen-mt-lite	1,000,000	Text; translation	/v1/chat/completions, /v1/messages, /v1/responses	Per 1M tokens: input, output, cache read
qwen-plus-2025-12-01	1,000,000	Audio, Coding, Text, Video, Vision; reasoning, long context, translation, creative writing, spatial vision, document vision, visual coding, speech-to-speech, omni/video understanding, long video, temporal video, code reasoning, code completion, agentic coding	/v1/chat/completions	Per 1M tokens: input, output, cache read
qwen3-coder-480b-a35b-instruct	262,144	Coding, Text; reasoning, long context, code reasoning, agentic coding	/v1/chat/completions, /v1/messages, /v1/responses	Per 1M tokens: input, output, cache read
qwen3-coder-flash	1,000,000	Coding, Text; reasoning, long context, code reasoning, code completion, agentic coding	/v1/chat/completions, /v1/messages, /v1/responses	Per 1M tokens: input, output, cache read
qwen3-coder-plus	1,000,000	Coding, Text; reasoning, long context, code reasoning, code completion, agentic coding	/v1/chat/completions, /v1/messages, /v1/responses	Per 1M tokens: input, output, cache read
qwen3-max	262,144	Audio, Coding, Text, Video, Vision; reasoning, long context, translation, creative writing, spatial vision, document vision, visual coding, speech-to-speech, omni/video understanding, long video, temporal video, code reasoning, code completion, agentic coding	/v1/chat/completions, /v1/messages, /v1/responses	Per 1M tokens: input, output, cache read
qwen3-vl-flash	131,072	Coding, Text, Video, Vision; reasoning, long context, translation, creative writing, spatial vision, document vision, omni/video understanding, long video, temporal video, code reasoning, code completion, agentic coding	/v1/chat/completions, /v1/messages, /v1/responses	Per 1M tokens: input, output, cache read
qwen3-vl-flash-2025-10-15	131,072	Coding, Text, Video, Vision; reasoning, long context, translation, spatial vision, document vision, omni/video understanding, long video, temporal video, code reasoning, code completion, agentic coding	/v1/chat/completions, /v1/messages, /v1/responses	Per 1M tokens: input, output, cache read
qwen3-vl-plus	131,072	Coding, Text, Video, Vision; reasoning, long context, translation, creative writing, spatial vision, document vision, omni/video understanding, long video, temporal video, code reasoning, code completion, agentic coding	/v1/chat/completions, /v1/messages, /v1/responses	Per 1M tokens: input, output, cache read
qwen3.6-plus	1,000,000	Coding, Text, Video, Vision; reasoning, long context, translation, creative writing, spatial vision, document vision, visual coding, omni/video understanding, long video, temporal video, code reasoning, agentic coding	/v1/chat/completions, /v1/messages, /v1/responses	Per 1M tokens: input, output, cache read
qwen3.6-plus-2026-04-02	262,144	Coding, Text, Vision; code reasoning, long context, reasoning, vision	/v1/chat/completions, /v1/messages, /v1/responses	Per 1M tokens: input, output, cache read
qwen3.7-flash	—	Text	/v1/chat/completions, /v1/messages, /v1/responses	Per 1M tokens: input, output, cache read, cache write
qwen3.7-flash-2026-07-15	—	Text	/v1/chat/completions, /v1/messages, /v1/responses	Per 1M tokens: input, output, cache read, cache write
qwen3.7-max	1,000,000	Coding, Text; reasoning, long context, translation, creative writing, code reasoning, agentic coding	/v1/chat/completions, /v1/messages, /v1/responses	Per 1M tokens: input, output, cache read, cache write
qwen3.7-max-2026-06-08	—	Text	/v1/chat/completions, /v1/messages, /v1/responses	Per 1M tokens: input, output, cache read
qwen3.7-plus	—	Text	/v1/chat/completions, /v1/messages, /v1/responses	Per 1M tokens: input, output, cache read, cache write
qwen3.8-max	—	Text	/v1/chat/completions, /v1/messages, /v1/responses	Per 1M tokens: input, output, cache read, cache write
wan2.7-i2v	—	Video	/v1/video/generations	Per output second, by resolution
wan2.7-image	N/A	Image, Text, Vision; reasoning, vision, image generation, image editing, text in images, image consistency	/v1/images/generations, /v1/images/edits	Per request
wan2.7-image-pro	N/A	Image, Text, Video, Vision; reasoning, long context, vision, image generation, image editing, text in images, image consistency, image-to-video	/v1/images/generations, /v1/images/edits	Per request
wan2.7-r2v	—	Video	/v1/video/generations	Per output second, by resolution
wan2.7-t2v	—	Video	/v1/video/generations	Per output second, by resolution

Moonshot

Model ID	Context	Capabilities	Endpoint(s)	Billed by
kimi-k2-thinking	256,000	Coding, Text; reasoning, long context, code reasoning, agentic coding	/v1/chat/completions, /v1/messages, /v1/responses	Per 1M tokens: input, output, cache read
kimi-k2.5	262,144	Coding, Text, Video, Vision; reasoning, long context, spatial vision, document vision, visual coding, omni/video understanding, long video, code reasoning, agentic coding	/v1/chat/completions, /v1/messages, /v1/responses	Per 1M tokens: input, output, cache read
kimi-k2.6	128,000	Text; long context, reasoning	/v1/chat/completions, /v1/messages, /v1/responses	Per 1M tokens: input, output, cache read
kimi-k2.7-code	—	Text	/v1/chat/completions, /v1/messages, /v1/responses	Per 1M tokens: input, output, cache read, cache write
kimi-k3	—	Text	/v1/chat/completions, /v1/messages, /v1/responses	Per 1M tokens: input, output, cache read

MiniMax

Model ID	Context	Capabilities	Endpoint(s)	Billed by
MiniMax-M2.5	262,144	Coding, Text; reasoning, long context, creative writing, code reasoning, agentic coding	/v1/chat/completions, /v1/messages, /v1/responses	Per 1M tokens: input, output, cache read
MiniMax-M2.7	—	Text	/v1/chat/completions, /v1/responses	Per 1M tokens: input, output, cache read, cache write
MiniMax-M2.7-highspeed	—	Text	/v1/chat/completions, /v1/responses	Per 1M tokens: input, output, cache read, cache write
MiniMax-M3	1,000,000	Coding, Text, Video, Vision; reasoning, long context, code reasoning, agentic coding, vision, long video	/v1/chat/completions, /v1/messages, /v1/responses	Per 1M tokens: input, output, cache read

Zhipu GLM

Model ID	Context	Capabilities	Endpoint(s)	Billed by
glm-5	128,000	Coding, Text; reasoning, long context, code reasoning, code completion, agentic coding	/v1/chat/completions, /v1/messages, /v1/responses	Per 1M tokens: input, output, cache read
glm-5.1	—	Text	/v1/chat/completions, /v1/messages, /v1/responses	Per 1M tokens: input, output, cache read
glm-5.2	—	Text	/v1/chat/completions, /v1/messages, /v1/responses	Per 1M tokens: input, output, cache read
glm-5.3	—	Text	/v1/chat/completions, /v1/messages, /v1/responses	Per 1M tokens: input, output, cache read
glm-5.3-flash	—	Text	/v1/chat/completions, /v1/messages, /v1/responses	Per 1M tokens: input, output, cache read
glm-5v-turbo	—	Text	/v1/chat/completions, /v1/messages, /v1/responses	Per 1M tokens: input, output, cache read

ByteDance

Model ID	Context	Capabilities	Endpoint(s)	Billed by
dreamina-seedance-2-0-260128	—	Video	/v1/video/generations	Per 1M tokens, by resolution
dreamina-seedance-2-0-fast-260128	—	Video	/v1/video/generations	Per 1M tokens, by resolution
dreamina-seedance-2-5	—	Video	/v1/video/generations	Per 1M tokens, by resolution
seed-1-6-250915	262,144	Text, Video, Vision; reasoning, long context, creative writing, vision, omni/video understanding	/v1/chat/completions, /v1/messages, /v1/responses	Per 1M tokens: input, output, cache read
seed-1-6-flash-250715	262,144	Text, Video, Vision; reasoning, long context, spatial vision, omni/video understanding, temporal video	/v1/chat/completions, /v1/messages, /v1/responses	Per 1M tokens: input, output, cache read
seed-1-8-251228	262,144	Coding, Text, Video, Vision; reasoning, long context, creative writing, spatial vision, document vision, visual coding, long video, temporal video, code reasoning, code completion, agentic coding	/v1/chat/completions, /v1/messages, /v1/responses	Per 1M tokens: input, output, cache read
seed-2-0-lite-260228	262,144	Coding, Text, Video, Vision; reasoning, long context, creative writing, spatial vision, document vision, omni/video understanding, long video, temporal video, code reasoning, code completion, agentic coding	/v1/chat/completions, /v1/messages, /v1/responses	Per 1M tokens: input, output, cache read
seed-2-0-mini-260215	262,144	Coding, Text, Video, Vision; reasoning, long context, spatial vision, document vision, omni/video understanding, temporal video, code reasoning, code completion, agentic coding	/v1/chat/completions	Per 1M tokens: input, output, cache read
seed-2-0-pro-260328	262,144	Coding, Text, Video, Vision; reasoning, long context, creative writing, spatial vision, document vision, visual coding, omni/video understanding, long video, temporal video, code reasoning, code completion, agentic coding	/v1/chat/completions, /v1/messages, /v1/responses	Per 1M tokens: input, output, cache read
seedream-5-0-260128	262,144	Image, Vision; image editing, image generation, text in images, vision	/v1/images/generations	Per request

Tencent

Model ID	Context	Capabilities	Endpoint(s)	Billed by
hy3	—	Text	/v1/chat/completions, /v1/responses	Per 1M tokens: input, output, cache read
hy4-preview	—	Text	/v1/chat/completions, /v1/responses	Per 1M tokens: input, output, cache read

Xiaomi

Model ID	Context	Capabilities	Endpoint(s)	Billed by
mimo-v2.6-flash	—	Text	/v1/chat/completions	Per 1M tokens: input, output, cache read
mimo-v2.6-pro	—	Text	/v1/chat/completions	Per 1M tokens: input, output, cache read
mimo-v2.6-pro-ultraspeed	—	Text	/v1/chat/completions	Per 1M tokens: input, output, cache read

StepFun

Model ID	Context	Capabilities	Endpoint(s)	Billed by
step-3.5-flash	—	Text	/v1/chat/completions, /v1/messages	Per 1M tokens: input, output, cache read
step-3.5-flash-2603	—	Text	/v1/chat/completions, /v1/messages	Per 1M tokens: input, output, cache read
step-3.7-flash	—	Text	/v1/chat/completions, /v1/messages, /v1/responses	Per 1M tokens: input, output, cache read

HappyHorse

Model ID	Context	Capabilities	Endpoint(s)	Billed by
happyhorse-1.1-i2v	—	Video	/v1/video/generations	Per output second, by resolution
happyhorse-1.1-r2v	—	Video	/v1/video/generations	Per output second, by resolution
happyhorse-1.1-t2v	—	Video	/v1/video/generations	Per output second, by resolution

Jina

Model ID	Context	Capabilities	Endpoint(s)	Billed by
jina-embeddings-v3	—	Embeddings	/v1/embeddings, /v1/classify	Per 1M tokens: input (provider-reported total)
jina-embeddings-v5-text-small	—	Embeddings	/v1/embeddings	Per 1M tokens: input (provider-reported total)
jina-reranker-v3	—	Rerank	/v1/rerank	Per 1M tokens: input (provider-reported total)

TypeSafe

Model ID	Context	Capabilities	Endpoint(s)	Billed by
jev-latest	—	Text	/v1/systemone	Per 1M tokens: input

Choosing a model

Need	Start with	Why
Frontier text + vision	gpt-5.5, claude-opus-4-8, gpt-5.4	Strong reasoning and broad multimodal/coding coverage.
Agentic coding	gpt-5.3-codex, claude-opus-4-8, qwen3-coder-plus, MiniMax-M3	Coding, long-context, and agentic sub-capabilities.
Low-cost high-volume text	qwen-flash, deepseek-v4-flash, qwen-mt-flash	Very low input/output pricing for routine tasks.
Long-context Chinese or bilingual work	qwen3.6-plus, qwen3.7-max, MiniMax-M3	1M-token context options with Chinese-language strength.
Visual/document tasks	qwen3-vl-plus, claude-opus-4-8, gpt-5.4	Vision/document/spatial capability tags.
Image generation	gpt-image-2, seedream-5-0-260128, wan2.7-image-pro	Image-generation and image-editing model IDs with per-request billing.

Models added since the last capability export show only their base type in the Capabilities column above; check the live catalog for their full capability tags before routing production traffic to them.

Notes for agents

• Do not invent AIsa model IDs. Use the exact model strings in the tables.
• Do not assume a model supports every modality its upstream family supports. Use the capability tags listed here or check the live model page.
• If a model appears in aisa.one/models but not in a static table, the pricing API has likely enabled it at runtime; prefer the live catalog.
• This page does not list prices. Current prices are on aisa.one/models; the final billed amount appears in AIsa Usage Logs and may include workspace-level pricing rules.
• A — in the Context column means the current metadata export does not publish that model’s context window. Do not assume a default; read the live catalog.