Model Catalog · Updated May 2026

AI Models

79 models from 15 providers · Prices shown per million tokens · 46 new models added

View Model Rankings
AMA Smart Routes · Built by Us

One endpoint that picks the right model

Use nexus/* routes and let our system automatically select the optimal model for each task — no model-switching overhead.

✦Smart Auto
nexus/auto

Smart routing — picks the best quality/cost balance among all live models for your request.

✦Smart Routing
nexus/cheapest-west

Routes to the cheapest capable Western provider model — balanced capability, speed, and cost.

◈Lowest Cost
nexus/cheapest

Always routes to the cheapest capable model for your task. Great for high-volume workloads.

◉CN Provider Optimized
nexus/cheapest-cn

Routes to the cheapest China-based provider models for eligible users in permitted regions.

⬡Speed + Quality
nexus/best-reasoning

Optimizes for both response speed and output quality. Best for production chat apps.

▸Ultra-Fast
nexus/fastest

Always picks the fastest available model. Ideal for real-time streaming and low-latency apps.

⌘Best for Code
nexus/best-coding

Routes to the strongest coding-capable model available. Best for refactors, reviews, and complex logic.

⬚Long Context
nexus/long-context

Routes to the cheapest model with 500K+ context. Ideal for long documents and large codebases.

◎Web Search
nexus/web-search

Routes to Perplexity Sonar models with live web search built in. Best for research and current events.

Trending nowWan 3.0 Video+82%GPT-6 Astra+80%Wan 3.0 Video Prime+80%

79 models shown

Provider
Use
Claude Sonnet 5NEWLatest
Latest Sonnet — claude-sonnet-latest routes here. Intro pricing through Aug 2026.
Anthropic
$1.90
$9.50
1M
96
80
+45%
Get Key
Claude Opus 5NEWLatest Opus
Anthropic Opus flagship — ArkLin probed live 2026-08-16. Use claude-opus-5 or claude-opus-latest.
Anthropic
$4.75
$23.75
1M
99
64
+52%
Get Key
GPT-6 AstraNEWGPT-6 Flagship
OpenAI GPT-6 Astra — callable as gpt-6-astra (Bedrock Mantle us-west-2)
OpenAI
$10.00
$50.00
1M
100
62
+80%
Get Key
GPT-5.6 SolNEWGPT-5.6 Flagship
OpenAI GPT-5.6 flagship — highest intelligence in the 5.6 family
OpenAI
$3.80
$19.00
1M
99
68
+22.4%
Get Key
GPT-5.6 TerraNEWBalanced
GPT-5.6 balanced tier — strong quality at mid price
OpenAI
$1.90
$11.40
1M
96
76
+18.1%
Get Key
GPT-5.6 LunaNEWFast GPT-5.6
GPT-5.6 fast/efficient tier for high-volume workloads
OpenAI
$0.190
$1.14
1M
92
88
+16.5%
Get Key
Claude Fable 5NEWPending
Anthropic 第五代旗舰 — 平台待开通。请暂用 Claude Opus 5 / Sonnet 5。
Anthropic
$10.00
$50.00
1M
99
64
0%
Get Key
Grok 4.6NEWPending
xAI flagship — not enabled on the platform yet.
xAI
$2.00
$6.00
500K
95
74
+28%
Get Key
Wan 3.0 VideoNEW65% of list
Alibaba Wan 3.0 all-in-one video (Bailian wan3.0-video) — t2v/i2v/r2v, 480P/720P/1080P, 2–30s. Billed at 65% of DashScope Singapore list: $0.0325/$0.065/$0.13 per second. model=WAN-video-3.0, POST /v1/contents/generations/tasks.
Alibaba Wan
$0.065/s
65% list
0K
97
58
+82%
Get Key
Wan 3.0 Video PrimeNEW65% of list
Alibaba Wan 3.0 Prime (wan3.0-video-prime) — faster all-in-one video, same 65% list rates as WAN-video-3.0 ($0.0325/$0.065/$0.13 per second).
Alibaba Wan
$0.065/s
65% list
0K
96
70
+80%
Get Key
Wan 3.0 Text-to-VideoNEW65% of list
Wan 3.0 text-to-video alias (same upstream as WAN-video-3.0). 65% of Singapore list: $0.0325/$0.065/$0.13 per second.
Alibaba Wan
$0.065/s
65% list
0K
97
58
+78%
Get Key
Wan 3.0 Image-to-VideoNEW65% of list
Wan 3.0 image-to-video alias — first/last frame, reference image/video/audio. Same 65% list rates as WAN-video-3.0.
Alibaba Wan
$0.065/s
65% list
0K
96
58
+76%
Get Key
Wan 2.7 Text-to-VideoNEWVideo · Wan 2.7
阿里 Wan 2.7 文生视频（百炼 DashScope）— 720P/1080P，2–15s。model=WAN-t2v-2.7，POST /v1/contents/generations/tasks 后轮询 GET /v1/contents/generations/tasks/{id}。详见 /docs#video。
Alibaba Wan
$0.0000
$0.0000
0K
95
55
+70%
Get Key
Wan 2.7 Image-to-VideoNEWVideo · Wan 2.7 I2V
阿里 Wan 2.7 图生视频（百炼 DashScope）— 首帧 / 首尾帧 / 视频续写 + 可选驱动音频。720P/1080P，2–15s。尾帧参数 last_frame_image。详见 /docs#video。
Alibaba Wan
$0.0000
$0.0000
0K
94
58
+68%
Get Key
Wan 2.7 ImageNEWImage · Wan 2.7
Wan 2.7 文生图 / 图生图 / 改图。公开 ID IMG-bl-wan2.7-image。POST /v1/images/generations 或 /v1/images/edits，参数 prompt / n / size(1K|2K)，改图再传 image。详见 /docs#image。
Alibaba Wan
$0.0000
$0.0000
0K
92
70
+65%
Get Key
Wan 2.7 Image ProNEWImage · Wan Pro
Wan 2.7 Pro 文生图可 4K + thinking_mode；图生图 / 改图最高 2K。公开 ID IMG-bl-wan2.7-image-pro。详见 /docs#image。
Alibaba Wan
$0.0000
$0.0000
0K
95
58
+66%
Get Key
Claude Opus 5 RscNEWRsc · VIP
ArkLin VIP Rsc channel — Opus 5, probed live 2026-08-16.
ArkLin
$2.00
$10.00
1M
99
76
+55%
Get Key
Gemini 3.1 ProNEWLatest
Google's most capable model, 2M context, multimodal (Feb 2026)
Google
$2.00
$12.00
1M
94
72
+9.8%
Get Key
DeepSeek V4 ProNEW75% OFF
Advanced reasoning, 75% launch discount until May 31 — list price $1.74/$3.48
DeepSeek
$0.500
$1.00
1M
90
70
+44.5%
Get Key
DeepSeek V4 FlashNEWCheapest
Fastest DeepSeek model — ultra-cheap for high-volume tasks
DeepSeek
$0.140
$0.280
1M
78
95
+19.3%
Get Key
Hy3 PreviewNEWHunyuan 3
Tencent Hunyuan 3 (混元 3) — 295B MoE, agent-first, open-sourced Apr 2026
Tencent
$0.190
$0.620
262K
89
72
+52.1%
Get Key
Seedance 2.0 (CN)NEWVideo · CN
Volcengine Ark CN — text/image/video-to-video, up to 15s, 720p/1080p. API: POST /v1/contents/generations/tasks
ByteDance
$0.0000
$0.0000
0K
94
55
+62%
Get Key
Seedance 2.0 Fast (CN)NEWVideo · CN
Faster CN route for prompt iteration — 720p
ByteDance
$0.0000
$0.0000
0K
86
78
+48%
Get Key
Seedance 2.0 (International)NEWVideo · Intl
BytePlus ModelArk international region — same API, base URL routed automatically
ByteDance
$0.0000
$0.0000
0K
94
55
+55%
Get Key
Seedance 2.0 Fast (Intl)NEWVideo · Intl
International fast variant for draft renders
ByteDance
$0.0000
$0.0000
0K
86
78
+44%
Get Key
Seed3D 2.0 (CN)NEW3D · CN
Volcengine Ark CN — image/text-to-3D asset generation. API: POST /v1/contents/generations/tasks
ByteDance
$0.0000
$0.0000
0K
92
50
+70%
Get Key
Seed3D 1.0 (CN)NEW3D · CN
Seed3D 1.0 — image/text-to-3D (China region)
ByteDance
$0.0000
$0.0000
0K
85
55
+45%
Get Key
Qwen3.8 MaxNEWLatest
通义 Qwen3.8 Max，现网可调用。公开 ID qwen3.8-max，1M 上下文。
Alibaba
$2.00
$6.00
1M
94
74
+48%
Get Key
Claude Opus 4.8Previous
Previous Opus. Prefer claude-opus-5; claude-opus-latest now routes to Opus 5.
Anthropic
$4.75
$23.75
1M
98
66
+48.2%
Get Key
Claude Opus 4.7BYOK / Soon
Anthropic catalog + BYOK direct API. Opus 4.7 on the US pool rolls out when enabled on the platform.
Anthropic
$4.75
$23.75
200K
97
68
+18%
Get Key
GPT-5.5 ProMost Powerful
OpenAI's most powerful frontier model for the most complex tasks
OpenAI
$5.00
$30.00
256K
98
62
+4.2%
Get Key
GPT-5.5Latest
OpenAI's flagship model for professional workloads (Apr 2026)
OpenAI
$2.50
$10.00
256K
95
74
+18.6%
Get Key
GPT-5.4Recommended
Current flagship GPT — powerful, 1M context, fast
OpenAI
$2.50
$10.00
128K
91
81
+3.1%
Get Key
GPT-5.4 Mini
Cost-efficient GPT-5.4 class model, great for most tasks
OpenAI
$0.150
$0.600
128K
84
88
-1.2%
Get Key
Claude Sonnet 4.6Previous
Previous Sonnet. Prefer claude-sonnet-5.
Anthropic
$2.85
$14.25
1M
93
78
+11.4%
Get Key
Gemini 3.1 Flash-LiteNEWBest Value
Best price-performance in Gemini family, retains free tier
Google
$0.250
$1.50
1M
80
94
+31.2%
Get Key
Qwen3.7 MaxPrevious
Qwen3.7 Max — previous flagship, still callable. Prefer qwen3.8-max.
Alibaba
$0.800
$3.20
1M
91
76
+12%
Get Key
Kimi K2.7 CodeNEWLatest
Moonshot coding flagship — 256K context, best for agentic code
Moonshot
$0.950
$4.00
256K
90
78
+22.4%
Get Key
Grok 4.1 FastLegacy
Legacy slug — xAI redirects to Grok 4.3 (none reasoning effort)
xAI
$1.25
$2.50
1M
79
93
+6.3%
Get Key
Gemini 3.0 Flash
Fast next-gen model, proven stability, free tier available
Google
$0.575
$3.45
1M
79
91
-4.1%
Get Key
DeepSeek R1
Reasoning alias → V4 Pro (replaces deepseek-reasoner)
DeepSeek
$0.550
$2.19
1M
87
66
-6.3%
Get Key
Mistral Large
Top European AI — strong multilingual, GDPR-compliant
Mistral
$2.00
$6.00
131K
83
77
-1.8%
Get Key
Sonar ProWeb Search
Real-time web search + reasoning — live internet access
Perplexity
$3.00
$15.00
127K
86
71
+7.2%
Get Key
Qwen3.7 PlusNEWNew
Qwen3.7 plus — strong balance of quality and cost
Alibaba
$0.400
$1.60
1M
89
80
+26%
Get Key
Qwen3.6 Plus
Qwen3.6 long-context — still widely used
Alibaba
$0.325
$1.95
1M
88
79
+12.4%
Get Key
Kimi K2.6
Multimodal general model — vision, thinking, and agents
Moonshot
$0.550
$2.65
256K
86
75
+15.8%
Get Key
Command R+
Enterprise RAG specialist — retrieval-augmented generation
Cohere
$2.50
$10.00
128K
82
73
-3.5%
Get Key
GPT-5.4 NanoCheapest GPT
Ultra-fast, ultra-cheap — high-volume tasks and simple queries
OpenAI
$0.230
$1.44
1M
77
96
+2.4%
Get Key
GPT-5
Base GPT-5 — excellent balance of capability and cost
OpenAI
$0.720
$5.75
1M
88
84
-3%
Get Key
GPT-4o
Proven multimodal model — stable for existing integrations
OpenAI
$2.88
$11.50
128K
82
80
-8.4%
Get Key
Sonar
Fast web-grounded answers — great for factual Q&A
Perplexity
$1.00
$1.00
127K
77
88
+3.1%
Get Key
Claude Haiku 4.5Fast
Near-instant responses, high throughput, full 1M context
Anthropic
$0.950
$4.75
200K
83
93
+4.7%
Get Key
Mistral Small
Lightweight, fast, EU-based for compliance-sensitive use
Mistral
$0.115
$0.345
33K
72
91
-0.4%
Get Key
Llama 4 MaverickOpen Source
Open-source multimodal — 512K context, strong for its price
Meta
$0.220
$0.880
524K
81
82
+5.6%
Get Key
Llama 4 Scout
Efficient open-source, long context, ultra-low cost
Meta
$0.092
$0.345
524K
74
89
+2.9%
Get Key
GLM-5.2NEWLive
智谱 GLM-5.2，现网可调用。公开 ID glm-5.2，1M 上下文。
Zhipu AI
$1.00
$4.00
1M
92
75
+28.5%
Get Key
Qwen MaxPrevious
Previous Qwen Max. Prefer qwen3.8-max.
Alibaba
$0.400
$1.20
33K
85
76
+1.5%
Get Key
Qwen Plus
Balanced performance and cost in the Qwen family
Alibaba
$0.092
$0.299
131K
75
84
-2.1%
Get Key
Qwen Turbo
Fastest, cheapest Qwen — high-volume Chinese language tasks
Alibaba
$0.050
$0.200
131K
68
97
+0.8%
Get Key
GLM-4
Legacy alias — routes to GLM-5.1
Zhipu AI
$0.140
$0.140
128K
76
85
+1.1%
Get Key
Claude Opus 4.8 RscNEWRsc · VIP
ArkLin VIP Rsc channel — Opus 4.8, dedicated high-priority route.
ArkLin
$2.00
$10.00
200K
98
78
+52%
Get Key
Claude Opus 4.7 RscNEWRsc · VIP
ArkLin VIP Rsc channel — Opus 4.7.
ArkLin
$2.00
$10.00
200K
97
76
+44%
Get Key
Claude Sonnet 5 RscNEWRsc · VIP
ArkLin VIP Rsc channel — Sonnet 5, speed + intelligence balance.
ArkLin
$0.800
$4.00
1M
96
84
+46%
Get Key
Claude Sonnet 4.6 RscNEWRsc · VIP
ArkLin VIP Rsc channel — Sonnet 4.6.
ArkLin
$1.20
$6.00
200K
94
80
+36%
Get Key
DeepSeek ChatLegacy
Legacy alias → V4 Flash (DeepSeek retires 2026-07-24)
DeepSeek
$0.140
$0.280
1M
78
95
+5%
Get Key
Seed3D 2.0 (International)NEW3D · Intl
BytePlus ModelArk international region — same API, base URL routed automatically
ByteDance
$0.0000
$0.0000
0K
92
50
+60%
Get Key
Seed3D 1.0 (International)NEW3D · Intl
Seed3D 1.0 international — coming when intl key is configured
ByteDance
$0.0000
$0.0000
0K
85
55
+40%
Get Key
Wan 3.0 Reference-to-VideoNEW65% of list
Wan 3.0 reference-to-video alias (same upstream as WAN-video-3.0). 65% of Singapore list: $0.0325/$0.065/$0.13 per second.
Alibaba Wan
$0.065/s
65% list
0K
96
58
+74%
Get Key
Wan 2.5 Text-to-VideoNEWVideo · Wan T2V
阿里 Wan 2.5（PolarDB for AI 部署）— 文生视频，480P/720P，最长 30s。API: POST /v1/contents/generations/tasks（不是 /v1/videos）。详见 /docs#video。
Alibaba Wan
$0.0000
$0.0000
0K
93
60
+58%
Get Key
Wan 2.5 Image-to-VideoNEWVideo · Wan I2V
阿里 Wan 2.5 图生视频 — 支持首帧、首尾帧、视频续写。480P/720P，最长 30s。尾帧用 last_frame_image 或 content[].type=last_frame。详见 /docs#video。
Alibaba Wan
$0.0000
$0.0000
0K
92
62
+54%
Get Key
Wan 2.5 Reference-to-VideoNEWVideo · Wan R2V
阿里 Wan 2.5（PolarDB for AI 部署）— 参考视频+图生视频（模仿动作/风格），720P/1080P，最长 30s。模型能力已开白，中国以外客户不受限。高用量可联系本站管理员进一步洽谈。
Alibaba Wan
$0.0000
$0.0000
0K
91
58
+50%
Get Key
Kimi K2.7 Code HighspeedNEWFast
Same K2.7 Code quality with ~180 tok/s output
Moonshot
$0.950
$4.00
256K
90
92
+18%
Get Key
Kimi K2.5
Proven stable release — strong at coding and Chinese tasks
Moonshot
$0.300
$1.50
131K
83
73
-5.2%
Get Key
Grok 4.3Legacy
xAI previous flagship — 1M context. Platform listing stays on Grok 4.6.
xAI
$1.25
$2.50
1M
92
76
+17.9%
Get Key
Grok Build 0.1NEWCode
Agentic coding model (replaces grok-code-fast-1)
xAI
$1.00
$2.00
256K
88
85
+12%
Get Key
MiniMax M2.7NEWCatalog
MiniMax latest — catalog listed; API routes when MINIMAX_API_KEY is configured
MiniMax
$0.300
$1.20
205K
88
79
+12%
Get Key
MiniMax M2.7 HighspeedNEWFast
M2.7 highspeed variant — ~100 tok/s
MiniMax
$0.300
$1.20
205K
88
90
+10%
Get Key
GLM-5.1Previous
智谱 GLM-5.1 — 上一档，仍可调用。
Zhipu AI
$1.00
$3.20
200K
92
75
+30%
Get Key
GLM-5
Legacy alias — routes to GLM-5.1
Zhipu AI
$1.00
$4.00
200K
91
74
+8.5%
Get Key
Prices shown per million tokensQuality/Speed scores from AMA composite benchmark, updated weeklyPrompt caching: save up to 90% on repeated inputsWan 3.0 video is billed per second at 65% of DashScope Singapore list ($0.0325/$0.065/$0.13 per second)
Start for Free — No Credit Card RequiredModel Rankings