Last refreshed 2026-07-09. Next refresh: weekly.
Why use Llama 3.2 90B Vision Instruct on Vercel AI Gateway?
Vercel AI Gateway offers Llama 3.2 90B Vision Instruct with pay-as-you-go pricing at $0.72/1M input tokens. Vercel AI Gateway is a unified AI proxy providing a single OpenAI-compatible API endpoint to 275+ models from 25+ providers including Anthropic, OpenAI, Google, Meta, Mistral, DeepSeek, xAI, Alibaba, Amazon, ByteDance, Cohere, MiniMax, MoonshotAI, KwaiPilot, Black Forest Labs, Recraft, Voyage AI, NVIDIA, and more.
Compare Llama 3.2 90B Vision Instruct across 6 providers to find the best fit for your use caseInput / 1M
$0.72
Output / 1M
$0.72
Cache
Not sourced
Batch
Not sourced
Setup recipe
Python + curlInstall
pip install openaiAuth
export AI_GATEWAY_API_KEY=...Call
import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ["AI_GATEWAY_API_KEY"],Model ID
meta/llama-3.2-90bRequest example
import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ["AI_GATEWAY_API_KEY"],
base_url="https://ai-gateway.vercel.sh/v1"
)
response = client.chat.completions.create(
model="meta/llama-3.2-90b",
messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)Gotchas
- Use provider model ID "meta/llama-3.2-90b", not the LLMReference slug "llama-3.2-90b-vision-instruct".
- creator/model-name e.g. kwaipilot/kat-coder-pro-v2
- The examples expect AI_GATEWAY_API_KEY; rename it only if your application config maps the new variable.
Compare Llama 3.2 90B Vision Instruct Across Providers
| Provider | Input (per 1M) | Output (per 1M) |
|---|---|---|
| Fireworks AI | $0.90 | $0.90 |
| NVIDIA NIM | — | — |
| Bitdeer AI | $0.15 | $0.45 |
| AWS Bedrock | $1.35 | $1.80 |
| Microsoft Foundry | $2.04 | $2.04 |
Pricing
| Type | Price (per 1M) |
|---|---|
| Input tokens | $0.72 |
| Output tokens | $0.72 |
Capabilities
VisionMultimodal
About Llama 3.2 90B Vision Instruct
Instruction-tuned 90B Llama 3.2 Vision model for higher-capability image reasoning, visual question answering, visual grounding, and captioning. NVIDIA NIM lists text plus image input, text output, and a 128K context window for the Llama 3.2 Vision collection.
Get Started
Model Specs
Released2024-09-25
Parameters88.8B
Context128k
ArchitectureDecoder Only
Knowledge cutoff2024-03