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
DeepSeek R1$1.35/1M$5.40/1M
from $1.79 at APIMart
+201%128K
FLUX 3 Image—From$0.041/img
from $0.02 at Atlas Cloud
——
Kimi K2.5$0.60/1M$3/1M
from $0.555 at APIMart
+440%256K
Claude Sonnet 5$2/1MFrom$10/1M
from $6.90 at Kenari
±0%1M
Qwen3.8 Flash$0.15/1M$0.47/1M
from $0.309 at APIMart
+23%991K
LongCat 2.5 Preview$0.30/1M$1.20/1M
from $1.18 at ZenMux
+2%1.05M
Grok 4.6$2/1M$6/1M
from $4.80 at APIMart
±0%500K
GPT Image 2.5 Sunburst$5/1M$30/1M
from $24 at APIMart
+25%—
FLUX 3 Image Klein—From$0.008/img
from $0.007 at APIMart
——
Seedream 4.5—$0.04/img
from $0.026 at APIMart
±0%—
Qwen3 VL InstructOnly here$0.20/1M$0.88/1M—262K
Gemini 2.5 Pro$1.25/1MFrom$10/1M
from $8 at APIMart
±0%1.05M
GPT-4o (2024-11-20)$2.50/1MFrom$10/1M
from $8 at APIMart
±0%128K
GPT OSS 20B$0.03/1M$0.14/1M
from $0.09 at OpenRouter
+56%131K
Mercury 2.5$0.04/1M$0.15/1M—260K
Gemini 2.5 Flash$0.30/1MFrom$2.50/1M
from $2 at APIMart
±0%1M
Kimi K2.6$0.95/1M$4/1M
from $2.40 at APIYI
+7%262K
MiMo-V2.5$0.119/1M$0.238/1M
from $0.224 at CometAPI
+6%1.05M
GPT Image 2.5 Flare$5/1M$30/1M
from $1.75 at UnoRouter
+1614%—
Qwen3.8 Omni Flash$0.15/1M$0.47/1M
from $0.38 at AIHubMix
+23%1M
Mercury 3$0.10/1M$0.35/1M±0%1M
MiniMax M2.5$0.30/1M$1.20/1M
from $0.95 at Venice AI
+26%205K
Llama 4 Maverick$0.24/1M$0.97/1M
from $0.20 at AIHubMix
+385%128K
Gemini 3.8 Flash-Lite TTS$0.50/1M$6/1M
from $4.20 at Kie.ai
±0%—
Seedream 5.0 Lite—$0.035/img
from $0.028 at Kie.ai
±0%—
Qwen3-Coder-Next$0.50/1M$1.20/1M
from $0.548 at AIHubMix
+119%256K
Llama 4 Scout 17B Instruct$0.17/1M$0.66/1M
from $0.20 at AIHubMix
+230%128K
GLM-4.7-Flash$0.07/1M$0.40/1M±0%200K
kling 3.0 motion control—From$0.168/sec
from $0.07 at Replicate
——
GLM-5.1$1.40/1M$4.40/1M
from $1.44 at APIMart
±0%203K
Seedream 4.0—$0.03/img
from $0.003 at Kie.ai
±0%—
Ling 3.0 Flash (free)$0.021/1M$0.063/1M—256K
GLM-4.7$0.60/1M$2.20/1M
from $1.10 at AIHubMix
±0%200K
GLM-4.5$0.60/1M$2.20/1M
from $1.16 at ZenMux
±0%128K
GLM-4.6$0.60/1M$2.20/1M
from $1.10 at AIHubMix
±0%200K
Gemma 4$0.14/1M$0.40/1M
from $0.30 at FastRouter
+33%262K
Kimi K2.7 Code HighSpeed$0.95/1M$4/1M
from $2.76 at Kenari
+7%256K
LFM2.5-24B-A2B$0.05/1M$0.70/1M—128K
Recraft V4—From$0.08/img
from $0.04 at Fal
——
MiMo-V2.5-Pro$0.304/1M$0.609/1M—1.05M
Qwen3 30B A3B$0.12/1M$0.50/1M
from $0.29 at Helicone
+72%41K
Nemotron 3.5 Lightning 30B A3B$0.05/1MFrom$0.20/1M
from $0.16 at Deep Infra
—262K
Veo 3.1 LiteCheapest—From$0.03/sec——
Llama-3.3-70B-Instruct$0.72/1M$0.72/1M
from $0.32 at Deep Infra
+125%128K
Qwen3.6 27B$0.60/1M$3.60/1M
from $2 at OpenRouter
±0%256K
Mistral Nemo$0.029/1M$0.03/1M—131K
DeepSeek V4 Flash 0731$0.076/1M$0.153/1M
from $0.133 at OpenRouter
+15%1M
Recraft V4.1 Flash—$0.007/img——
Grok 4.5$2/1M$6/1M
from $3.20 at APIMart
±0%500K
Laguna S 2.1$0.09/1MFrom$0.18/1M—1M

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