Skip to main content

Vercel AI Gateway

Aggregator

Vercel AI Gateway routes one API key to many upstream providers, so you can switch models without new accounts.

PricingDocs
Models296
Cheapest for
10 models
Serves
5 model types
Monthly visits—
Models by type

Models on Vercel AI Gateway

ModelInputOutputvs officialContext
OpenAI GPT-5 Nano$0.05/1MFrom$0.40/1M
from $0.32 at APIMart
±0%400K
OpenAI GPT-5.2$1.75/1MFrom$14/1M
from $11.20 at APIMart
±0%400K
OpenAI GPT-5.2 Pro$21/1M$168/1M
from $134.40 at APIMart
±0%400K
OpenAI GPT-5.3 Codex$1.75/1MFrom$14/1M
from $11.20 at APIMart
+25%400K
OpenAI GPT-5.4$2.50/1MFrom$15/1M
from $12 at APIMart
±0%1.05M
OpenAI GPT-5.4 Mini$0.75/1MFrom$4.50/1M
from $3.60 at APIMart
±0%400K
OpenAI GPT-5.4 Nano$0.20/1MFrom$1.25/1M
from $1 at APIMart
±0%400K
OpenAI GPT-5.4 Pro$30/1M$180/1M
from $144 at APIMart
±0%1.05M
OpenAI GPT-5.5$5/1MFrom$30/1M
from $24 at APIMart
±0%1M
OpenAI o1$15/1M$60/1M
from $48 at APIMart
±0%200K
OpenAI o3$2/1MFrom$8/1M
from $6.40 at APIMart
±0%200K
OpenAI o3 mini$1.10/1M$4.40/1M
from $3.52 at APIMart
±0%200K
Qwen3 235B A22B Instruct 2507$0.22/1M$0.88/1M
from $0.10 at Requesty
+780%262K
Qwen3 Max$1.20/1M$6/1M
from $1.43 at Ofox
+320%256K
Qwen3 Next 80B A3B Instruct$0.15/1M$1.20/1M
from $1.10 at Deep Infra
+9%262K
Qwen3 Next 80B A3B Thinking$0.15/1M$1.20/1M—262K
Qwen3.5 Flash$0.10/1M$0.40/1M
from $0.26 at OpenRouter
+39%1M
Qwen3.5 Plus$0.40/1M$2.40/1M
from $0.658 at AIHubMix
+249%1M
Qwen3.6 Plus$0.50/1M$3/1M
from $1.37 at APIMart
+82%1M
Qwen3.7 Flash$0.03/1M$0.13/1M
from $0.091 at APIMart
+18%991K
Qwen3.8 Max Preview$2/1M$6/1M±0%262K
Recraft V4.1 Pro—From$0.30/img
from $0.21 at Fal
——
Recraft V4.1 Utility—From$0.08/img
from $0.04 at Replicate
——
Sakana Namazu$0.95/1M$4/1M—256K
Schematron V2 Small$0.05/1M$0.23/1M—128K
Schematron V2 Turbo$0.03/1M$0.15/1M—128K
Seed 1.6$0.25/1M$2/1M
from $0.285 at APIYI
+602%256K
Seed 2.1 Turbo$0.50/1M$2.50/1M
from $1.67 at CometAPI
±0%262K
Seedance v1.0 Pro Fast—From$0.01/sec
from $0.009 at APIMart
——
Step 3.7 Flash$0.20/1M$1.15/1M
from $0.925 at APIMart
+24%256K
Step 5 Preview$1/1M$2.70/1M±0%1.05M
Tencent Hy-MT2-LiteOnly here$0.044/1M$0.177/1M—8K
Tencent Hy-MT2-ProOnly here$0.074/1M$0.295/1M—8K
Toast 1Only here$0.30/1M$0.72/1M—131K
Veo 3.0Cheapest—From$0.20/sec——
Veo 3.0 Fast GenerateOnly here—From$0.10/sec——
wan 3.0 video—From$0.05/sec
from $0.04 at Atlas Cloud
——
Wan v2.5 Text-to-Video Preview—From$0.05/sec——
Wan v2.6 Image-to-Video—From$0.10/sec
from $0.066 at APIMart
——
Wan v2.6 Image-to-Video Flash—From$0.05/sec
from $0.017 at APIMart
——
Wan v2.6 Reference-to-VideoOnly here—From$0.10/sec——
Wan v2.6 Reference-to-Video FlashOnly here—From$0.05/sec——
Wan v2.6 Text-to-Video—From$0.10/sec——
Wan2.7 R2V—From$0.10/sec
from $0.066 at APIMart
——
Wan2.7 T2V—From$0.10/sec
from $0.085 at AIHubMix
——
wan3.0 video primeCheapest—From$0.068/sec——

Vercel AI Gateway at a glance

296 models in total: 222 text, 34 image, 27 video, 11 audio, 2 moderation. The cheapest is Mistral Nemo at $0.03 /1M. Llama 4 Scout 17B Instruct has the largest context window, 1.31M tokens. The most searched is Gemini 4 Argon, with about 2M Google searches a month. The newest is Kimi K3.1 Pro Highspeed, released Oct 23, 2026.

Cheapest

  1. Mistral Nemo$0.03/1M
  2. Ling 3.0 Flash (free)$0.063/1M
  3. Ministral 3B$0.10/1M
  4. Qwen3.7 Flash$0.13/1M
  5. GPT OSS 20B$0.14/1M

Largest context

  1. Llama 4 Scout 17B Instruct1.31M
  2. GPT-6 Astra1.05M
  3. GPT-6.1 Sol1.05M
  4. GPT-6 Sol1.05M
  5. GPT-6 Luna1.05M

Most searched

  1. Gemini 4 Argon2M
  2. Kimi K3658K
  3. MiniMax H3582K
  4. GPT-6 Astra580K
  5. Muse Wonder569K

Newest

  1. Kimi K3.1 Pro HighspeedOct 23, 2026
  2. Mercury 3Oct 19, 2026
  3. Ling 3.0 Flash SanteOct 19, 2026
  4. DeepSeek V4 Flash Vision ExpOct 17, 2026
  5. MiniMax-M3.1-FlashOct 17, 2026