Model Catalog · Updated May 2026
AI Models 62 models from 14 providers · Prices shown per million tokens · 33 new models added
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 now Seed3D 2.0 (CN)+70% Seedance 2.0 (CN)+62% Seed3D 2.0 (International)+60% All Providers OpenAI Anthropic Google DeepSeek xAI (Grok) Alibaba Meta Mistral Cohere Perplexity Moonshot Zhipu AI Tencent ByteDance
All capabilities chat vision code reasoning function calling video 3d New in 202662 models shown
Sort: Spotlight Quality Speed Trending
Model Provider
Input /M Output /M Context Quality Speed Weekly Use
Claude Sonnet 5 NEW Latest
Latest Sonnet — claude-sonnet-latest routes here. Intro pricing through Aug 2026.
chat vision code reasoningAnthropic
$1.90
$9.50
1M
GPT-5.6 Sol NEW GPT-5.6 Flagship
OpenAI GPT-5.6 flagship — highest intelligence in the 5.6 family
chat reasoning vision code function callingOpenAI
$5.00
$30.00
1M
GPT-5.6 Terra NEW Balanced
GPT-5.6 balanced tier — strong quality at mid price
chat reasoning vision code function callingOpenAI
$2.50
$15.00
1M
GPT-5.6 Luna NEW Fast GPT-5.6
GPT-5.6 fast/efficient tier for high-volume workloads
chat reasoning vision code function callingOpenAI
$1.00
$6.00
1M
Claude Opus 4.8 NEW Live
Use claude-opus-4-8 or claude-opus-latest — platform routes to ArkLin automatically.
chat vision code reasoningAnthropic
$4.75
$23.75
1M
Claude Opus 4.7 BYOK / Soon
Anthropic catalog + BYOK direct API. Opus 4.7 on the US pool rolls out when enabled on the platform.
chat vision code reasoningAnthropic
$4.75
$23.75
200K
GPT-5.5 Pro Most Powerful
OpenAI's most powerful frontier model for the most complex tasks
chat reasoning vision codeOpenAI
$5.00
$30.00
256K
GPT-5.5 Latest
OpenAI's flagship model for professional workloads (Apr 2026)
chat reasoning vision code function callingOpenAI
$2.50
$10.00
256K
Gemini 3.1 Pro NEW Latest
Google's most capable model, 2M context, multimodal (Feb 2026)
chat vision code reasoningGoogle
$2.00
$12.00
1M
Claude Fable 5 NEW Restricted
Anthropic 第五代旗舰 — 上游限制许可,暂不可调用。请用 Sonnet 5 / Opus 4.8。
chat vision code reasoningAnthropic
$10.00
$50.00
1M
DeepSeek V4 Pro NEW 75% OFF
Advanced reasoning, 75% launch discount until May 31 — list price $1.74/$3.48
DeepSeek
$0.500
$1.00
1M
GPT-5.4 Recommended
Current flagship GPT — powerful, 1M context, fast
chat vision code function callingOpenAI
$2.50
$10.00
128K
DeepSeek V4 Flash NEW Cheapest
Fastest DeepSeek model — ultra-cheap for high-volume tasks
DeepSeek
$0.140
$0.280
1M
GPT-5.4 Mini
Cost-efficient GPT-5.4 class model, great for most tasks
chat vision code function callingOpenAI
$0.150
$0.600
128K
Hy3 Preview NEW Hunyuan 3
Tencent Hunyuan 3 (混元 3) — 295B MoE, agent-first, open-sourced Apr 2026
chat reasoning code function callingTencent
$0.190
$0.620
262K
Seedance 2.0 (CN) NEW Video · 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
Seedance 2.0 Fast (CN) NEW Video · CN
Faster CN route for prompt iteration — 720p
ByteDance
$0.0000
$0.0000
0K
Seedance 2.0 (International) NEW Video · Intl
BytePlus ModelArk international region — same API, base URL routed automatically
ByteDance
$0.0000
$0.0000
0K
Seedance 2.0 Fast (Intl) NEW Video · Intl
International fast variant for draft renders
ByteDance
$0.0000
$0.0000
0K
Seed3D 2.0 (CN) NEW 3D · CN
Volcengine Ark CN — image/text-to-3D asset generation. API: POST /v1/contents/generations/tasks
ByteDance
$0.0000
$0.0000
0K
Seed3D 1.0 (CN) NEW 3D · CN
Seed3D 1.0 — image/text-to-3D (China region)
ByteDance
$0.0000
$0.0000
0K
Grok 4.3 NEW Latest
xAI flagship — 1M context, configurable reasoning effort
chat reasoning vision codexAI
$1.25
$2.50
1M
Claude Sonnet 4.6 Most Popular
Best balance of Claude intelligence and speed — 1M context
chat vision code reasoningAnthropic
$2.85
$14.25
1M
Gemini 3.1 Flash-Lite NEW Best Value
Best price-performance in Gemini family, retains free tier
Google
$0.250
$1.50
1M
Qwen3.7 Max NEW Latest
Alibaba Qwen3.7 flagship — Bailian verified, 1M context
chat code reasoning function callingAlibaba
$0.800
$3.20
1M
GLM-5.1 NEW Latest
Zhipu GLM-5.1 — Bailian/ArkLin verified live
Zhipu AI
$1.00
$3.20
200K
Kimi K2.7 Code NEW Latest
Moonshot coding flagship — 256K context, best for agentic code
Moonshot
$0.950
$4.00
256K
Grok 4.1 Fast Legacy
Legacy slug — xAI redirects to Grok 4.3 (none reasoning effort)
xAI
$1.25
$2.50
1M
Gemini 3.0 Flash
Fast next-gen model, proven stability, free tier available
Google
$0.575
$3.45
1M
DeepSeek R1
Reasoning alias → V4 Pro (replaces deepseek-reasoner)
DeepSeek
$0.550
$2.19
1M
Mistral Large
Top European AI — strong multilingual, GDPR-compliant
chat code function callingMistral
$2.00
$6.00
131K
Sonar Pro Web Search
Real-time web search + reasoning — live internet access
Perplexity
$3.00
$15.00
127K
Qwen3.7 Plus NEW New
Qwen3.7 plus — strong balance of quality and cost
chat code reasoning function callingAlibaba
$0.400
$1.60
1M
Qwen3.6 Plus
Qwen3.6 long-context — still widely used
Alibaba
$0.325
$1.95
1M
Kimi K2.6
Multimodal general model — vision, thinking, and agents
chat code reasoning visionMoonshot
$0.550
$2.65
256K
Command R+
Enterprise RAG specialist — retrieval-augmented generation
chat code reasoning function callingCohere
$2.50
$10.00
128K
GPT-5.4 Nano Cheapest GPT
Ultra-fast, ultra-cheap — high-volume tasks and simple queries
OpenAI
$0.230
$1.44
1M
GPT-5
Base GPT-5 — excellent balance of capability and cost
chat vision code function callingOpenAI
$0.720
$5.75
1M
GPT-4o
Proven multimodal model — stable for existing integrations
chat vision code function callingOpenAI
$2.88
$11.50
128K
Sonar
Fast web-grounded answers — great for factual Q&A
Perplexity
$1.00
$1.00
127K
Claude Haiku 4.5 Fast
Near-instant responses, high throughput, full 1M context
Anthropic
$0.950
$4.75
200K
Mistral Small
Lightweight, fast, EU-based for compliance-sensitive use
Mistral
$0.115
$0.345
33K
Llama 4 Maverick Open Source
Open-source multimodal — 512K context, strong for its price
Meta
$0.220
$0.880
524K
Llama 4 Scout
Efficient open-source, long context, ultra-low cost
Meta
$0.092
$0.345
524K
GLM-5.2 NEW Alias
GLM-5.2 catalog id — routes to live glm-5.1 until Bailian paid quota is enabled
Zhipu AI
$1.00
$4.00
1M
Qwen Max Best Chinese
Alibaba's most powerful model — excels at Chinese tasks
Alibaba
$0.400
$1.20
33K
Qwen Plus
Balanced performance and cost in the Qwen family
Alibaba
$0.092
$0.299
131K
Qwen Turbo
Fastest, cheapest Qwen — high-volume Chinese language tasks
Alibaba
$0.050
$0.200
131K
GLM-4
Legacy alias — routes to GLM-5.1
Zhipu AI
$0.140
$0.140
128K
Claude Opus 4.8 Rsc NEW Rsc · VIP
ArkLin VIP Rsc channel — Opus 4.8, dedicated high-priority route.
chat vision code reasoning function callingArkLin
$2.00
$10.00
200K
Claude Opus 4.7 Rsc NEW Rsc · VIP
ArkLin VIP Rsc channel — Opus 4.7.
chat vision code reasoning function callingArkLin
$2.00
$10.00
200K
Claude Sonnet 5 Rsc NEW Rsc · VIP
ArkLin VIP Rsc channel — Sonnet 5, speed + intelligence balance.
chat vision code reasoning function callingArkLin
$0.800
$4.00
1M
Claude Sonnet 4.6 Rsc NEW Rsc · VIP
ArkLin VIP Rsc channel — Sonnet 4.6.
chat vision code reasoning function callingArkLin
$1.20
$6.00
200K
DeepSeek Chat Legacy
Legacy alias → V4 Flash (DeepSeek retires 2026-07-24)
DeepSeek
$0.140
$0.280
1M
Seed3D 2.0 (International) NEW 3D · Intl
BytePlus ModelArk international region — same API, base URL routed automatically
ByteDance
$0.0000
$0.0000
0K
Seed3D 1.0 (International) NEW 3D · Intl
Seed3D 1.0 international — coming when intl key is configured
ByteDance
$0.0000
$0.0000
0K
Kimi K2.7 Code Highspeed NEW Fast
Same K2.7 Code quality with ~180 tok/s output
Moonshot
$0.950
$4.00
256K
Kimi K2.5
Proven stable release — strong at coding and Chinese tasks
Moonshot
$0.300
$1.50
131K
Grok Build 0.1 NEW Code
Agentic coding model (replaces grok-code-fast-1)
xAI
$1.00
$2.00
256K
MiniMax M2.7 NEW Catalog
MiniMax latest — catalog listed; API routes when MINIMAX_API_KEY is configured
MiniMax
$0.300
$1.20
205K
MiniMax M2.7 Highspeed NEW Fast
M2.7 highspeed variant — ~100 tok/s
MiniMax
$0.300
$1.20
205K
GLM-5
Legacy alias — routes to GLM-5.1
Zhipu AI
$1.00
$4.00
200K
Prices shown per million tokens Quality/Speed scores from AMA composite benchmark, updated weekly Prompt caching: save up to 90% on repeated inputs Batch API: 50% discount on async workloads
Accepted Payment Methods 256-bit TLS PCI DSS via Stripe Credits never expire Multi-currency
ModelAPI One endpoint for 100+ frontier models. Transparent pricing, pay-as-you-go, WeChat · Alipay · Stripe supported.
Virginia (US East) Shanghai (CN) Singapore (SEA) Frankfurt (EU) Riyadh (ME)
ModelAPI is a multi-model AI algorithm & orchestration cloud (SaaS) — Harness Control, Nexus routing, session budgets, and compaction on licensed B2B channels — not reverse-engineered APIs, account pooling, or subscription splitting. Not offered to mainland-China-registered entities ; you must meet upstream geo Terms and are solely responsible for your data and cross-border compliance.Compliance
© 2026 ModelAPI. All rights reserved.
0% per-token markup · Official API prices · 5% infra fee only · Credits never expire