Models

Put the model name into the model field of your request; the same endpoint serves every model. This page is generated from the live pricing API: 317 models from 19 vendors. Actual availability depends on your account and the routing mode of your key.

Legend

• Type：chat / image / video / decision (Jev)
• Protocol：OpenAI-compatible = /v1/chat/completions; Claude native = /v1/messages; Gemini native = /v1beta/models/{model}:generateContent; Responses = /v1/responses; Images = /v1/images/generations; Video = /v1/video/generations
• Groups：Pricing groups the model belongs to. Enterprise official full-strength · Economy discounted pools · Workflow official list price · Plan coding plans · Multimedia (unreviewed image/video) / Unlimited special third-party pools. Keys in "by vendor" or "all models" mode pick the cheapest available group automatically.

Flagship models by vendor

Anthropic 11

Available over both the OpenAI-compatible and the native Claude protocol (/v1/messages). Prompt caching (incl. 1h TTL), tools, vision and 1M context are supported.

OpenAI 9

GPT models work over Chat Completions and the Responses API; Codex clients use Responses.

OpenAI Image 2

Per-image billed GPT image models on /v1/images/generations and /v1/images/edits; see Image generation.

Google Gemini 1

Available over the OpenAI-compatible and the native Gemini protocol.

Nano Banana 6

Gemini image models. gemini-nano-banana-* are token-billed via Gemini native / OpenAI-compatible; nano-banana-* (Economy) are billed per image.

xAI 10

Zhipu GLM 5

DeepSeek 1

Kimi 5

Kimi models are reasoning models: thinking tokens are generated before the reply and are billed as output. For kimi-k3.1-pro use max_tokens >= 3000, otherwise the reply may contain thinking only and end with empty content. kimi-k3.1-pro-highspeed has no such limit.

MiniMax 4

MiniMax M series. minimax-m3.1-flash supports roughly 1M context (beyond the upstream ceiling the API returns context window exceeds limit), prompt caching, tools and image input.

Alibaba Qwen 3

Tencent Hunyuan 2

Xiaomi MiMo 4

TypeSafe 3

Structured decision models on /v1/decisions (alias /v1/systemone), not chat-compatible; see Jev decision model.

Workflow groups (official list price)

Workflow groups expose each vendor's full catalogue at official list price — for non-coding toolchains, legacy model compatibility and batch jobs. Use the names below verbatim.

GPT Workflow 94

TA/openai/gpt-oss-120b TA/openai/gpt-oss-20b babbage-002 chatgpt-4o-latest davinci-002 fireworks/models/gpt-oss-120b fireworks/models/gpt-oss-20b gpt-3.5-turbo gpt-3.5-turbo-0125 gpt-3.5-turbo-1106 gpt-3.5-turbo-16k gpt-3.5-turbo-instruct gpt-3.5-turbo-instruct-0914 gpt-4 gpt-4-0125-preview gpt-4-0613 gpt-4-1106-preview gpt-4-turbo gpt-4-turbo-2024-04-09 gpt-4-vision-preview gpt-4.1 gpt-4.1-2025-04-14 gpt-4.1-mini gpt-4.1-mini-2025-04-14 gpt-4.1-nano gpt-4.1-nano-2025-04-14 gpt-4o gpt-4o-2024-05-13 gpt-4o-2024-08-06 gpt-4o-2024-11-20 gpt-4o-audio-preview gpt-4o-audio-preview-2024-10-01 gpt-4o-audio-preview-2024-12-17 gpt-4o-mini gpt-4o-mini-2024-07-18 gpt-4o-mini-audio-preview gpt-4o-mini-audio-preview-2024-12-17 gpt-4o-mini-realtime-preview gpt-4o-mini-realtime-preview-2024-12-17 gpt-4o-mini-search-preview gpt-4o-mini-search-preview-2025-03-11 gpt-4o-realtime-preview gpt-4o-realtime-preview-2024-10-01 gpt-4o-realtime-preview-2024-12-17 gpt-4o-search-preview gpt-4o-search-preview-2025-03-11 gpt-5 gpt-5-2025-08-07 gpt-5-chat-latest gpt-5-codex gpt-5-mini gpt-5-mini-2025-08-07 gpt-5-nano gpt-5-nano-2025-08-07 gpt-5-pro gpt-5-pro-2025-10-06 gpt-5.1 gpt-5.1-2025-11-13 gpt-5.1-codex gpt-5.1-codex-max gpt-5.1-codex-mini gpt-5.2 gpt-5.2-codex gpt-5.3-codex gpt-5.4-nano gpt-audio gpt-audio-2025-08-28 gpt-audio-mini gpt-audio-mini-2025-10-06 gpt-image-1 gpt-image-1-mini gpt-realtime gpt-realtime-2025-08-28 gpt-realtime-mini gpt-realtime-mini-2025-10-06 o1 o1-2024-12-17 o1-preview o1-preview-2024-09-12 o3 o3-2025-04-16 o3-mini o3-mini-2025-01-31 o3-pro o3-pro-2025-06-10 o4-mini o4-mini-2025-04-16 text-embedding-3-large text-embedding-3-small text-embedding-ada-002 tts-1 tts-1-1106 tts-1-hd tts-1-hd-1106

Claude Workflow 31

claude-2 claude-2.0 claude-2.1 claude-3-5-haiku claude-3-5-haiku-20241022 claude-3-5-haiku-latest claude-3-5-sonnet claude-3-5-sonnet-20240620 claude-3-5-sonnet-20241022 claude-3-5-sonnet-latest claude-3-7-sonnet-20250219 claude-3-7-sonnet-latest claude-3-haiku claude-3-haiku-20240307 claude-3-haiku-latest claude-3-opus claude-3-opus-20240229 claude-3-opus-latest claude-3-sonnet claude-3-sonnet-20240229 claude-3-sonnet-latest claude-opus-4-0 claude-opus-4-1 claude-opus-4-1-20250805 claude-opus-4-20250514 claude-opus-4-5 claude-opus-4-5-20251101 claude-sonnet-4-0 claude-sonnet-4-20250514 claude-sonnet-4-5 claude-sonnet-4-5-20250929

GLM Workflow 27

fireworks/glm-5 glm-3-turbo glm-4 glm-4-air glm-4-airx glm-4-flash glm-4-flashx glm-4-long glm-4-plus glm-4.5 glm-4.5-air glm-4.5-airx glm-4.5-flash glm-4.5-x glm-4.5v glm-4.6 glm-4.6v glm-4.6v-flash glm-4.6v-flashx glm-4.7 glm-4.7-flash glm-4.7-flashx glm-4v glm-4v-plus glm-5 glm-5-turbo glm-5v-turbo

Cohere Workflow 14

c4ai-aya-expanse-32b c4ai-aya-expanse-8b c4ai-aya-vision-32b c4ai-aya-vision-8b command-a-03-2025 command-r command-r-03-2024 command-r-08-2024 command-r-online command-r-plus command-r-plus-04-2024 command-r-plus-08-2024 command-r-plus-online command-r7b-12-2024

Gemini Workflow 11

gemini-2.5-flash gemini-2.5-flash-lite gemini-3-flash-preview gemini-3.1-flash-lite-preview gemini-3.1-pro-preview gemini-3.5-flash gemini-3.7-flash gemini-3.8-flash gemini-nano-banana-2 gemini-nano-banana-2.1 gemini-nano-banana-pro

Doubao Workflow 6

ark-doubao-seed-1.6-250615 ark-doubao-seed-1.6-flash-250615 ark-doubao-seed-1.6-vision-250815 doubao-1.5-pro-32k-250115 doubao-embedding-large-text-240915 doubao-embedding-text-240715

Misc Workflow 3

TA/Qwen/Qwen2.5-7B-Instruct-Turbo fireworks/kimi-k2p5 fireworks/models/llama-v3p3-70b-instruct

01.AI Workflow 2

yi-lightning yi-vision-v2

Mistral Workflow 2

mistral-large-latest open-mistral-nemo

Multimedia image & video (unreviewed)

Third-party unreviewed image and video models — NSFW allowed, minors strictly prohibited. Callable from keys routed to the Multimedia vendor or in "all models" mode. Images use Image generation (synchronous); videos use Video generation (submit → poll → download). Each mode of a series (text-to-video / image-to-video / reference-to-video …) is a separate model name with its own price. The console also has a Media Workbench for generating in the browser.

Video models 42

Image models 10

Unlimited

Uncensored and abliterated models, only available in the Unlimited group; they are not picked by smart routing except as a last-resort fallback. The model descriptions in the console list measured first-token latency and output speed.

Snapshot: 2026-11-03

All docs

• XycAi API Reference
• Endpoints
• API keys & routing
• Authentication
• Models
• Model status & pricing API
• Errors
• Chat Completions
• Responses API
• Claude Messages
• Image Generation
• Video Generation
• Text-to-Speech
• Embeddings
• Gemini Native
• Jev Judgment Model
• Midjourney
• Suno Music
• OpenClaw
• Hermes Agent
• Claude Code
• OpenCode
• Cursor
• Codex CLI
• Qwen Office Assistant
• Qwen Code
• DeepSeek Harness
• QwenPaw
• Cherry Studio
• Chatbox
• Cline
• Qoder
• Qoder CN (formerly Lingma)
• Kilo CLI
• Postman
• Dify
• Gemini CLI
• TRAE SOLO
• Node.js Setup
• More tools