Home/Migrate/From DeepInfra
Migration guide · 5 minutes

DeepInfra → QuickSilver Pro

DeepInfra is already the budget option among DeepSeek resellers — QuickSilver Pro is lower still: ~30% cheaper on V3 output, ~9% on R1 output (R1 input is at parity). Both APIs are OpenAI-compatible, so the move is a base-URL swap. For the full side-by-side analysis, see /vs/deepinfra.

The steps

  1. 1

    Get a QuickSilver Pro API key

    Sign up at quicksilverpro.io/dashboard. Launch bonus: top up between $5 and $50 and we match it 100% — pay $5, get $10; pay $50, get $100.

  2. 2

    Change the base URL

    In your OpenAI SDK init, swap the base_url. Note DeepInfra's OpenAI-compatible path ends in /v1/openai.

    - base_url="https://api.deepinfra.com/v1/openai"
    + base_url="https://api.quicksilverpro.io/v1"
  3. 3

    Swap the API key

    Replace your DeepInfra token with a QuickSilver Pro key.

    - api_key=os.environ["DEEPINFRA_TOKEN"],
    + api_key=os.environ["QSP_KEY"],
  4. 4

    Rename model IDs

    DeepInfra prefixes model IDs with the originating org. Drop the prefix and use the QuickSilver Pro short name.

    DeepInfraQuickSilver Pro
    deepseek-ai/DeepSeek-V3deepseek-v3
    deepseek-ai/DeepSeek-R1deepseek-r1
  5. 5

    Test your core flows end-to-end

    Run one representative request for each feature you use — chat, streaming, tool / function calling, and json_schema strict mode. Any behavioral difference is a bug — report it.

Full before/after

Before · DeepInfra
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.deepinfra.com/v1/openai",
    api_key=os.environ["DEEPINFRA_TOKEN"],
)

r = client.chat.completions.create(
    model="deepseek-ai/DeepSeek-V3",
    messages=[{"role": "user", "content": "Hi"}],
)
After · QuickSilver Pro
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.quicksilverpro.io/v1",
    api_key=os.environ["QSP_KEY"],
)

r = client.chat.completions.create(
    model="deepseek-v3",
    messages=[{"role": "user", "content": "Hi"}],
)

What you'll pay after switching

Per 1M tokens, input / output. QuickSilver Pro rates vs DeepInfra's published per-token pricing.

ModelQuickSilver ProDeepInfraSavings
DeepSeek V3$0.16 / $0.616$0.28 / $0.88~30%
DeepSeek R1$0.56 / $2.00$0.55 / $2.19~9% output

Common migration pitfalls

Cached-input pricing changes the math
Both providers discount cached input. DeepInfra applies a cached-input discount on DeepSeek V3 / V3.1, and QuickSilver Pro bills cached-input tokens at a separate, lower cache-read rate on DeepSeek V3/V4 (and the Qwen/Kimi models). For workloads with a high cache-hit ratio, compare effective per-request cost — not list price alone — before switching.
Non-chat modalities don't move
QuickSilver Pro is chat completions only. Embeddings, audio transcription, and image models stay on DeepInfra — keep both SDKs in your codebase if you use them.
Model revision may differ
DeepInfra and QuickSilver Pro each pin their own DeepSeek revisions. Re-run evals after switching if your prompts are tuned to a specific output style.
Rate limits work differently
QuickSilver Pro applies per-key throughput caps (default 600 req/min, 1M tok/min, 8 parallel). For bursty traffic, enable retry-on-429 and request a higher limit if needed.

Migrating from DeepInfra — FAQ

How much cheaper is it?
On list pricing: ~43% cheaper input + ~30% cheaper output on DeepSeek V3. On DeepSeek R1, input is roughly at parity (QSP $0.56 vs DeepInfra $0.55 — QSP is marginally higher) while output is ~9% cheaper ($2.00 vs $2.19). Cached-input pricing on DeepInfra can change the math; compare effective per-request cost for cache-heavy workloads.
How do I migrate?
Two lines: swap base_url to api.quicksilverpro.io/v1, new API key, drop the deepseek-ai/ or Qwen/ prefix.
Does QuickSilver Pro support prompt caching?
Yes — cached-input tokens bill at a separate, lower cache-read rate on DeepSeek V3/V4 and the Qwen/Kimi models, so repeat prompts cost less than fresh input. Both providers discount cached input; benchmark effective per-request cost if cache-hit ratio is material for your workload.
What about embeddings / audio / images?
Not offered. QuickSilver Pro is chat completions only on 7 LLMs. DeepInfra covers those modalities.

Other migration guides

Need help?

Email hello@quicksilverpro.io — a human replies usually within 4 hours. For the broader analysis, see QuickSilver Pro vs DeepInfra.

Start saving in 5 minutes

Launch bonus: first deposit matched 100%, up to $50 free. Keep your code on the OpenAI SDK — only the base URL and key change.

Get API Key