Vercel AI Gateway LLM API pricing
Every model Vercel AI Gateway serves, with its pricing per 1M tokens and the exact model ID to copy. Sorted cheapest input first. Verified against LiteLLM and OpenRouter daily.
Models served
93
on this provider
Cheapest input
$0.02
per 1M tokens
Cheapest output
$0.00
per 1M tokens
Max context
1M
tokens
| Model ID | |||||
|---|---|---|---|---|---|
| Titan Embed Text | Amazon | 0 | $0.02 | $0.00 | vercel_ai_gateway/amazon/titan-embed-text-v2 |
| Nova Micro 1.0 | Amazon | 128K | $0.04 | $0.14 | vercel_ai_gateway/amazon/nova-micro |
| Ministral 3B | Mistral | 128K | $0.04 | $0.04 | vercel_ai_gateway/mistral/ministral-3b |
| Llama 3 8B | Meta | 8K | $0.05 | $0.08 | vercel_ai_gateway/meta/llama-3-8b |
| Llama 3.1 8B | Meta | 131K | $0.05 | $0.08 | vercel_ai_gateway/meta/llama-3.1-8b |
| Nova Lite 1.0 | Amazon | 300K | $0.06 | $0.24 | vercel_ai_gateway/amazon/nova-lite |
| Devstral Small | Mistral | 128K | $0.07 | $0.28 | vercel_ai_gateway/mistral/devstral-small |
| Gemini 2.0 Flash Lite | 1M | $0.07 | $0.30 | vercel_ai_gateway/google/gemini-2.0-flash-lite | |
| Qwen 3 14B | Alibaba | 41K | $0.08 | $0.24 | vercel_ai_gateway/alibaba/qwen-3-14b |
| Qwen 3 30B | Alibaba | 41K | $0.10 | $0.30 | vercel_ai_gateway/alibaba/qwen-3-30b |
| Qwen 3 32B | Alibaba | 128K | $0.10 | $0.30 | vercel_ai_gateway/alibaba/qwen-3-32b |
| Llama 3.2 1B | Meta | 128K | $0.10 | $0.10 | vercel_ai_gateway/meta/llama-3.2-1b |
| Llama 4 Scout | Meta | 131K | $0.10 | $0.30 | vercel_ai_gateway/meta/llama-4-scout |
| Ministral 8B | Mistral | 128K | $0.10 | $0.10 | vercel_ai_gateway/mistral/ministral-8b |
| Mistral Small | Mistral | 32K | $0.10 | $0.30 | vercel_ai_gateway/mistral/mistral-small |
| GPT-4.1 Nano | OpenAI | 1M | $0.10 | $0.40 | vercel_ai_gateway/openai/gpt-4.1-nano |
| Mistral Embed | Mistral | 0 | $0.10 | $0.00 | vercel_ai_gateway/mistral/mistral-embed |
| Embed V4 0 | Cohere | 0 | $0.12 | $0.00 | vercel_ai_gateway/cohere/embed-v4.0 |
| Command R | Cohere | 128K | $0.15 | $0.60 | vercel_ai_gateway/cohere/command-r |
| Gemini 2.0 Flash | 1M | $0.15 | $0.60 | vercel_ai_gateway/google/gemini-2.0-flash | |
| Llama 3.2 3B | Meta | 131K | $0.15 | $0.15 | vercel_ai_gateway/meta/llama-3.2-3b |
| Codestral Embed | Mistral | 0 | $0.15 | $0.00 | vercel_ai_gateway/mistral/codestral-embed |
| Pixtral 12B | Mistral | 128K | $0.15 | $0.15 | vercel_ai_gateway/mistral/pixtral-12b |
| GPT-4o-mini | OpenAI | 131K | $0.15 | $0.60 | vercel_ai_gateway/openai/gpt-4o-mini |
| Llama 3.2 11B | Meta | 128K | $0.16 | $0.16 | vercel_ai_gateway/meta/llama-3.2-11b |
| Qwen 3 235B | Alibaba | 41K | $0.20 | $0.60 | vercel_ai_gateway/alibaba/qwen-3-235b |
| Gemma 2 9B | 8K | $0.20 | $0.20 | vercel_ai_gateway/google/gemma-2-9b | |
| Llama 4 Maverick | Meta | 131K | $0.20 | $0.60 | vercel_ai_gateway/meta/llama-4-maverick |
| GLM 4.5 Air | Zhipu | 131K | $0.20 | $1.10 | vercel_ai_gateway/zai/glm-4.5-air |
| Claude 3 Haiku | Anthropic | 200K | $0.25 | $1.25 | vercel_ai_gateway/anthropic/claude-3-haiku |
| Mercury Coder Small | Inception | 32K | $0.25 | $1.00 | vercel_ai_gateway/inception/mercury-coder-small |
| Gemini 2.5 Flash | 1M | $0.30 | $2.50 | vercel_ai_gateway/google/gemini-2.5-flash | |
| Grok 3 Mini | xAI | 131K | $0.30 | $0.50 | vercel_ai_gateway/xai/grok-3-mini |
| Codestral | Mistral | 256K | $0.30 | $0.90 | vercel_ai_gateway/mistral/codestral |
| Qwen3 Coder 480B A35B | Alibaba | 262K | $0.40 | $1.60 | vercel_ai_gateway/alibaba/qwen3-coder |
| GPT-4.1 Mini | OpenAI | 1M | $0.40 | $1.60 | vercel_ai_gateway/openai/gpt-4.1-mini |
| GLM 4.6 | Zhipu | 205K | $0.45 | $1.80 | vercel_ai_gateway/zai/glm-4.6 |
| Magistral Small | Mistral | 128K | $0.50 | $1.50 | vercel_ai_gateway/mistral/magistral-small |
| GPT-3.5 Turbo | OpenAI | 16K | $0.50 | $1.50 | vercel_ai_gateway/openai/gpt-3.5-turbo |
| R1 | DeepSeek | 164K | $0.55 | $2.19 | vercel_ai_gateway/deepseek/deepseek-r1 |
| Kimi K2 0711 | Moonshot | 131K | $0.55 | $2.20 | vercel_ai_gateway/moonshotai/kimi-k2 |
| Llama 3 70B | Meta | 8K | $0.59 | $0.79 | vercel_ai_gateway/meta/llama-3-70b |
| GLM 4.5 | Zhipu | 131K | $0.60 | $2.20 | vercel_ai_gateway/zai/glm-4.5 |
| Grok 3 Mini Fast | xAI | 131K | $0.60 | $4.00 | vercel_ai_gateway/xai/grok-3-mini-fast |
| Llama 3.1 70B | Meta | 128K | $0.72 | $0.72 | vercel_ai_gateway/meta/llama-3.1-70b |
| Llama 3.2 90B | Meta | 128K | $0.72 | $0.72 | vercel_ai_gateway/meta/llama-3.2-90b |
| Llama 3.3 70B | Meta | 128K | $0.72 | $0.72 | vercel_ai_gateway/meta/llama-3.3-70b |
| R1 Distill Llama 70B | DeepSeek | 131K | $0.75 | $0.99 | vercel_ai_gateway/deepseek/deepseek-r1-distill-llama-70b |
| Mistral Saba 24B | Mistral | 33K | $0.79 | $0.79 | vercel_ai_gateway/mistral/mistral-saba-24b |
| Nova Pro 1.0 | Amazon | 300K | $0.80 | $3.20 | vercel_ai_gateway/amazon/nova-pro |
1–50 of 93
Page 1 of 2
Pricing verified against LiteLLM + OpenRouter + provider pages · refreshed daily
Every weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI