DeepInfra raises $107M Series B to scale the inference cloud — read the announcement

Real-time inference on DeepInfra is fast — but when a popular model is under heavy load, requests queue up and some get shed with an HTTP 429. The new Priority service tier lets your latency-critical traffic jump to the front of that queue and stay admitted through contention, for 1.5× the real-time price. It's a single OpenAI-compatible field on the request — no separate endpoint, no new API to learn.
Most traffic is happy to retry a 429 and move on. Some isn't. Priority is built for the workloads where waiting in line is the problem:
You opt in per request by setting service_tier to "priority". Leave it off and your request runs at the standard real-time rate, exactly as it does today — nothing changes for traffic that doesn't need to skip the line.
One field. Add "service_tier": "priority" to any chat or completions request. Priority requests:
service_tier field comes back "priority" when (and only when) priority was actually applied.When the model is idle, priority and normal requests look the same — there's no queue to jump. The difference shows up exactly when it matters: under load.
/v1/chat/completions/v1/completionsPriority-rated billing also applies to embeddings. Everything works through the standard OpenAI-compatible API you're already using.
Priority is billed at 1.5× the corresponding real-time price — applied automatically, with no extra configuration.
Here's the part worth reading twice: you only pay the priority rate when priority is actually delivered. If you request priority on a model that doesn't support it, the request is served normally, billed at the normal rate, and the response's service_tier comes back "default". What's billed always equals what's echoed — so you can verify exactly what you paid for by reading the service_tier field on the response. No silent upcharge for a tier you didn't get.
Priority is live now on models served on our vLLM stack, which covers the bulk of our text-generation catalog. Support for models served on SGLang and TensorRT-LLM is rolling out.
Priority is enabled on a per-model basis, and the set of priority-enabled models is growing continuously. You don't have to guess which ones qualify: every model that supports priority already carries a Priority tag on its model page, so you can see at a glance whether a model honors the tier before you send a request.
And you can always confirm it programmatically: send a request with service_tier="priority" and check the echoed service_tier on the response. If it comes back "priority", you're at the front of the queue; if it comes back "default", the model isn't priority-enabled yet and you weren't charged the premium.
Using the OpenAI Python client — just add service_tier="priority" and read it back off the response:
from openai import OpenAI
client = OpenAI(
api_key="$DEEPINFRA_TOKEN",
base_url="https://api.deepinfra.com/v1/openai",
)
resp = client.chat.completions.create(
model="meta-llama/Meta-Llama-3.1-8B-Instruct",
messages=[{"role": "user", "content": "Summarize this support ticket: ..."}],
service_tier="priority",
)
print(resp.choices[0].message.content)
print("served as:", resp.service_tier) # "priority" when priority was applied
Or with curl — service_tier is just another field in the JSON body:
curl https://api.deepinfra.com/v1/openai/chat/completions \
-H "Authorization: Bearer $DEEPINFRA_TOKEN" \
-H "Content-Type: application/json" \
-d '{
"model": "meta-llama/Meta-Llama-3.1-8B-Instruct",
"messages": [{"role": "user", "content": "Summarize this support ticket: ..."}],
"service_tier": "priority"
}'
The service_tier field on the response tells you which tier actually served the request.
See the Service Tier documentation for the full reference, and start sending your latency-critical traffic to the front of the queue.
DeepInfra Launches Access to NVIDIA Cosmos 3 World Foundation Models for Physical AIDeepInfra is serving NVIDIA Cosmos 3, the first open world foundation model for physical AI that reasons before it generates, from day zero of its release. Available as two variants—Cosmos 3 Nano and Cosmos 3 Super—these models give developers a cost-efficient foundation for building robots, autonomous vehicles, simulation workflows, and synthetic data generation at scale.
Top 6 GLM-5.2 Max API Providers Compared<p>Deploying the GLM-5.2 (max) Mixture-of-Experts model — 753B total parameters with roughly 40B active per token and a 1M context window — requires infrastructure that separates production-grade API providers from the rest. This guide breaks down the top providers by throughput, latency, pricing, and quantization architecture. GLM-5.2 (max) API Review Summary (2026-06-27) TL;DR: Best Providers […]</p>
MiMo-V2.5 Provider Pricing and Deployment Guide<p>MiMo-V2.5 is worth paying attention to because it puts three things developers usually have to trade off into the same conversation: open weights, a 1 million-token model design, and pricing that can be unusually low depending on where you buy it. On Xiaomi’s first-party API, Artificial Analysis lists MiMo-V2.5 at $0.14 per 1M input tokens […]</p>
© 2026 DeepInfra. All rights reserved.