- 1M context
- Multimodal
- Reasoning
- Responses API
Claude Opus 5 on QuickSilver Pro
Claude Opus 5: $1.25 input / $6.25 output per 1M tokens, 75% below Anthropic list ($5.00 / $25.00). Context: 1M tokens. Maximum output: 128K tokens.
- 1M context
- 128K max output
- Vision
- Tools
- Reasoning · on by default
- Streaming
- No JSON Schema output
You pay · input / output per 1M
$1.25 / $6.25
75% lower
on both legs vs Anthropic list price
Pricing comparison ($/1M tokens)
Bar length = price relative to the list price
| Provider | Input | Output | vs QSP |
|---|---|---|---|
| QuickSilver Pro | $1.25 | $6.25 | lowest-cost |
| Anthropic list price(Anthropic API) | $5.00 | $25.00 | 75% lower |
Anthropic list source: anthropic.com/pricing
At a glance
- Context
- 1M tokens
- Input / 1M
- $1.25
- Output / 1M
- $6.25
- Thinks by default
- Yes
- Max output
- 128K
- Latency · live
- —
- AA Intelligence Index
- 54
For developers building coding agents and multi-step knowledge workflows.
When is Claude Opus 5 the right call?
Curated from catalog capabilities and published prices, not a benchmark.
When to use
Use Claude Opus 5 for reasoning, coding and long-horizon agents. Context: 1M tokens; maximum output: 128K tokens. It retains forced tool_choice, while Claude Opus 5.5 steers it to auto; both rewrite assistant prefill and drop temperature/top_p.
- Long documents and codebases, up to 1M tokens of context
- Agents that call tools
- Prompts that include images
- Multi-step reasoning, on by default
When to use something else
Switch to the successor Claude Opus 5.5: it has 1M context / 128K maximum output tokens, with base output priced at 0.8× this model. For base output savings, use Claude Sonnet 5.5: 1M context / 128K maximum output tokens at 0.4× this model’s output price. This model has no separate long-context price tier.
Quickstart (curl)
Get an API key →curl https://api.quicksilverpro.io/v1/chat/completions \
-H "Authorization: Bearer $QSP_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "claude-opus-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",
messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.quicksilverpro.io/v1",
apiKey: process.env.QSP_KEY,
});
const response = await client.chat.completions.create({
model: "claude-opus-5",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);curl https://api.quicksilverpro.io/v1/responses \
-H "Authorization: Bearer $QSP_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "claude-opus-5",
"input": "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",
messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)OpenAI-compatible. One-line migration via base_url.
Gateway behavior
Compatibility notes for this model.
temperature, top_p- Dropped before the request is forwarded.
assistant prefill- This model rejects a trailing assistant prefill, so the gateway rewrites it as a user continuation turn carrying the prefix.
tool_choice (forced)- Retained on this model: a forced tool choice can require that tool call.
image_url (remote)- Public remote URLs are fetched and inlined. An inaccessible or rejected URL fails the request; inline base64 is also supported.
prompt- Prompts up to 1M tokens.
max_tokens- Up to 128K output tokens.
- /v1/chat/completions: Supported
- /v1/responses: Supported
- streaming: Supported
- tools: Supported
- image input: Supported
- JSON Schema: Not listed for this model
- reasoning: Supported
Where the price comes from
- Provider reference
- $5.00 / $25.00anthropic.com/pricing
- Catalog verified
- Prompt cache · not compared
- $0.125 read · $1.5625 5m write · $2.50 1h write
usage.cost = prompt_tokens × $1.25/1M + completion_tokens × $6.25/1M
FAQ
Common questions
Claude Opus 5 costs $1.25 input / $6.25 output per 1M tokens. Anthropic list is $5.00 / $25.00; the discount is 75% on both base rates.
The catalog has no separate long-context tier for Claude Opus 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.
The gateway retains a forced tool_choice on this model. Claude response_format with json_schema is advisory. Use a tool with strict: true for enforced argument shape; forced tool choice can require that 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.