Last refreshed 2026-10-15. Next refresh: weekly.
Why use d1-ultra on Vercel AI Gateway?
Vercel AI Gateway offers d1-ultra with pay-as-you-go pricing at $0.04/1M 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 d1-ultra across 2 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"],liquid/d1-ultraRequest 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="liquid/d1-ultra",
messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)Gotchas
- Use provider model ID "liquid/d1-ultra", not the LLMReference slug "d1-ultra".
- 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 d1-ultra Across Providers
| Provider | Input (per 1M) | Output (per 1M) |
|---|---|---|
| Liquid AI | $0.04 | Free |
| Vercel AI Gateway | $0.04 | Free |
Pricing
| Type | Price (per 1M) |
|---|---|
| Input tokens | $0.04 |
| Output tokens | Free |
| Image input | $1.00 |
Capabilities
About d1-ultra
d1-ultra is a decision model from Liquid AI, released October 15, 2026 on the Liquid API. It reads text, images or both plus typed questions (noul yes/no, Choice, Score) in a single forward pass and returns probabilities without generating output tokens. Liquid states it is built on a larger open-weight base than d1 and targets tasks such as visual defect inspection and checking damage claims against photos. Billed on input tokens only ($0.042 per 1M input; output listed at $0). API-only; no public weights.