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
Mistral Medium 3.5$1.50/1M$7.50/1M—262K
Qwen3 14B$0.12/1M$0.24/1M
from $0.20 at Hugging Face
+20%41K
Veo 3.1 Fast—From$0.10/sec
from $0.08 at APIMart
——
Mercury 2$0.25/1M$0.75/1M—128K
Qwen3 Coder 480B A35B Instruct$0.22/1M$1.80/1M
from $0.95 at Helicone
+89%262K
Llama 3.1 8B Instruct$0.22/1M$0.22/1M
from $0.05 at Helicone
+340%128K
Qwen3.7 Max$2.50/1M$7.50/1M
from $3.75 at DevPass (LLM Gateway)
+51%991K
Recraft V4.1—From$0.08/img
from $0.035 at Fal
——
Qwen3-Coder 30B-A3B Instruct$0.15/1M$0.60/1M
from $0.27 at DevPass (LLM Gateway)
+122%262K
GLM-4.5-Air$0.20/1M$1.10/1M
from $0.291 at ZenMux
±0%128K
Qwen3.8 Max 0902$2/1M$6/1M
from $4.11 at APIMart
±0%991K
Gemma 4 26B A4B IT$0.15/1M$0.60/1M
from $0.225 at OpenRouter
±0%262K
Qwen3 32B$0.15/1M$0.60/1M
from $0.25 at Hugging Face
+140%128K
Qwen3.7 Plus$0.40/1M$1.60/1M
from $0.30 at CrazyRouter
+45%1M
Grok Imagine Video 1.5—From$0.08/sec
from $0.064 at APIMart
——
Qwen 3.8 Max Prime$4/1M$12/1M—1M
Ministral 3B$0.10/1M$0.10/1M—131K
Grok Imagine Image 2.0—From$0.04/img
from $0.032 at APIMart
——
Nemotron 3 Super 120B A12B$0.15/1M$0.65/1M
from $0.40 at Deep Infra
—256K
Seedance v1.5 ProCheapest—From$0.012/sec——
GPT Image 1.5$5/1M$32/1M
from $10 at AIHubMix
+220%—
Grok Imagine Video 1.5 Lite—From$0.02/sec——
MiniMax M2.1$0.30/1M$1.20/1M
from $0.864 at APIMart
+39%205K
Nemotron 3 Ultra 550B A55B$0.60/1M$2.40/1M
from $2.20 at Deep Infra
—1M
Seedance 1.0 Pro—From$0.024/sec
from $0.014 at Kie.ai
——
Fugu Max$2/1M$6/1M—1M
Codestral (latest)Only here$0.30/1M$0.90/1M—128K
Recraft V4 Pro—From$0.30/img
from $0.25 at Fal
——
Decider V1.2 27BOnly here$0.02/1MFree/1M—262K
Nemotron 3 Nano 30B A3B$0.05/1M$0.20/1M±0%262K
Ministral 8B$0.15/1M$0.15/1M
from $0.143 at AI/ML API
+5%262K
Ministral 14B (Arkanecloud)Only here$0.20/1M$0.20/1M—262K
Arcee Trinity Large Thinking (Public Preview)$0.25/1M$0.80/1M—262K
Arrow 2Only here$4/1M$20/1M—131K
Arrow 2 TelosOnly here$6/1M$30/1M—131K
Beam 1.0 501B A23BFree/1MFree/1M-100%1.05M
Claude Haiku 4.5 (latest)$1/1MFrom$5/1M
from $4 at APIMart
±0%200K
Claude Opus 4.5 (latest)$5/1MFrom$25/1M
from $20 at APIMart
±0%200K
Claude Opus 4.6$5/1MFrom$25/1M
from $20 at APIMart
±0%1M
Claude Opus 4.7$5/1MFrom$25/1M
from $20 at APIMart
±0%1M
Claude Opus 4.8$5/1MFrom$25/1M
from $20 at APIMart
±0%1M
Claude Sonnet 4.5 (latest)$3/1MFrom$15/1M
from $12 at APIMart
±0%1M
Coding MiniMax M2.7 Highspeed$0.60/1M$2.40/1M
from $0.10 at AIHubMix
+2300%205K
Command A$2.50/1M$10/1M—256K
Decider Flash V1.2 4BOnly here$0.01/1MFree/1M—262K
Decision-1$0.042/1MFree/1M—33K
Deepseek 3.2$0.62/1M$1.85/1M
from $0.308 at APIMart
+500%128K
DeepSeek V4 Flash Vision Exp$0.216/1M$0.647/1M
from $0.48 at CometAPI
+35%1.05M
DeepSeek V4 Pro$0.66/1M$1.98/1M
from $1.58 at CometAPI
±0%1M
DeepSeek-V3.1$0.25/1M$0.95/1M
from $0.798 at Poe
+19%164K

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