Last refreshed 2026-11-14. Next refresh: weekly.
Why use MiniMax H3 Image Highspeed on Vercel AI Gateway?
Vercel AI Gateway offers MiniMax H3 Image Highspeed with pay-as-you-go pricing at $2.30/1M 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 MiniMax H3 Image Highspeed across 6 providers to find the best fit for your use caseSetup recipe
Python + curlpip install openaiexport AI_GATEWAY_API_KEY=...import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ["AI_GATEWAY_API_KEY"],minimax/minimax-h3-image-highspeedRequest 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="minimax/minimax-h3-image-highspeed",
messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)Gotchas
- Use provider model ID "minimax/minimax-h3-image-highspeed", not the LLMReference slug "minimax-h3-image-highspeed".
- 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 MiniMax H3 Image Highspeed Across Providers
| Provider | Input (per 1M) | Output (per 1M) |
|---|---|---|
| MiniMax | $2.30 | $7.60 |
| fal API | $2.30 | $7.60 |
| OpenRouter | $2.30 | $7.60 |
| Vercel AI Gateway | $2.30 | $7.60 |
| Runware | $2.30 | $7.60 |
Pricing
| Type | Price (per 1M) |
|---|---|
| Input tokens | $2.30 |
| Output tokens | $7.60 |
Capabilities
About MiniMax H3 Image Highspeed
MiniMax H3 Image Highspeed is the high-speed version of MiniMax H3 Image, offered on the MiniMax API as MiniMax-H3-Image-Highspeed since the H3 Image launch on November 10, 2026. It takes the same parameters and limits as the standard model: text-to-image and image editing with 1 to 16 reference images, output up to 20,000,000 pixels and 1 to 10 images per request. MiniMax's separate H3-Image-Context-IR prompt-enhancement endpoint supports only the standard model. MiniMax published weights only for the standard MiniMax-H3-Image, so the Highspeed version is available through the API only.