Claude Opus 5.5 on QuickSilver Pro
Claude Opus 5.5: $1.60 input / $8.00 output per 1M tokens, 60% below Anthropic list ($4.00 / $20.00). Context: 1M tokens. Maximum output: 128K tokens. Available through Chat Completions and Responses. Capabilities: text input, text output, image input, streaming, reasoning and tool calling.
Unlocks with your first top-up from $5
At a glance
For developers building coding agents and multi-step knowledge workflows.
Pricing comparison ($/1M tokens)
| Provider | Input | Output | vs QSP |
|---|---|---|---|
| QuickSilver Pro | $1.60 | $8.00 | lowest-cost |
| Anthropic list price (Anthropic API) | $4.00 | $20.00 | 60% lower |
When to use
Use Claude Opus 5.5 for agentic coding, knowledge work and computer use. Context: 1M tokens; maximum output: 128K tokens. The gateway drops `temperature` and `top_p` and rewrites assistant prefill as a user continuation.
When to use something else
For base output savings, use Claude Sonnet 5.5: 1M context / 128K maximum output tokens at 0.625× this model’s output price. Choose Claude Opus 5 for native forced `tool_choice`; its base output costs 1.25× this model. This model has no separate long-context price tier.
Quickstart (curl)
curl https://api.quicksilverpro.io/v1/chat/completions \
-H "Authorization: Bearer $QSP_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "claude-opus-5-5",
"messages": [{"role": "user", "content": "Hello!"}]
}'import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.quicksilverpro.io/v1",
api_key=os.environ["QSP_KEY"],
)
response = client.chat.completions.create(
model="claude-opus-5-5",
messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)OpenAI-compatible. One-line migration via base_url.
FAQ
Claude Opus 5.5 costs $1.60 input / $8.00 output per 1M tokens. Anthropic list is $4.00 / $20.00; the discount is 60% on both base rates.
The catalog has no separate long-context tier for Claude Opus 5.5. Base rates apply within its 1M-token context.
The gateway drops `temperature` and `top_p`. This model rejects a trailing assistant prefill, so the gateway rewrites it as a user continuation turn carrying the prefix.
A forced `tool_choice` becomes `auto` plus an instruction to call the tool; a call is steered, not guaranteed. Claude `response_format` with `json_schema` is advisory. Use a tool with `strict: true` for enforced argument shape, and handle replies without a tool call.
Catalog capabilities: text input, text output, image input, streaming, reasoning and tool calling. For Claude image requests, the gateway fetches public remote image URLs and inlines the image data. An inaccessible or rejected URL fails the request; inline base64 is also supported.
Set `base_url="https://api.quicksilverpro.io/v1"`, use your QSP API key, and set `model="claude-opus-5-5"`. Supported APIs: Chat Completions and Responses. See the runnable quickstart on this page and the API docs.