- 500K context
- Reasoning
- Responses API
Grok 4.5 on QuickSilver Pro
Grok 4.5 through one OpenAI-compatible API. Supported features: text input, text output, streaming, reasoning, tool calling and JSON Schema.
- 500K context
- Tools
- Reasoning · on by default
- Streaming
- JSON Schema output
You pay · input / output per 1M
$1.60 / $4.80
xAI list source: docs.x.ai/docs/models
At a glance
- Context
- 500K tokens
- Input / 1M
- $1.60
- Output / 1M
- $4.80
- Thinks by default
- Yes
- Latency · live
- —
- AA Intelligence Index
- 45
Coding, knowledge work and STEM tasks.
When is Grok 4.5 the right call?
Curated from catalog capabilities and published prices, not a benchmark.
When to use
Use Grok 4.5 when your application needs these capabilities: text input, text output, streaming, reasoning, tool calling and JSON Schema.
- Long documents and codebases, up to 500K tokens of context
- Agents that call tools, with strict JSON Schema output
- Multi-step reasoning, on by default
- Responses API clients as well as Chat Completions
When to use something else
Choose a different model if your workflow requires capabilities beyond those listed here. Test your workload before committing to a model.
- The task needs a stronger modelGrok 4.6 scores 51 on the AA Intelligence Index (45 here), at 1.25× the output price.Grok 4.6 $2.00 / $6.00 · 500K
- You need image inputGrok 4.7 accepts image input, at 1.25× the output price.Grok 4.7 $2.00 / $6.00 · 500K
- You need a longer contextGPT-6.1 Terra accepts 1M tokens, at 1.042× the output price.GPT-6.1 Terra $1.00 / $5.00 · 1M
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": "grok-4.5",
"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="grok-4.5",
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: "grok-4.5",
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": "grok-4.5",
"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="grok-4.5",
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.
prompt- Prompts up to 500K tokens.
- /v1/chat/completions: Supported
- /v1/responses: Supported
- streaming: Supported
- tools: Supported
- image input: Not listed for this model
- JSON Schema: Supported
- reasoning: Supported
Where the price comes from
- Provider reference
- $2.00 / $6.00docs.x.ai/docs/models
- Catalog verified
- Prompt cache · not compared
- $0.40 read
usage.cost = prompt_tokens × $1.60/1M + completion_tokens × $4.80/1M
FAQ
Common questions
$1.60 input / $4.80 output per million tokens.
500K context tokens. A separate maximum output limit is not published in the catalog.
APIs: Chat Completions and Responses. Capabilities: text input, text output, streaming, reasoning, tool calling and JSON Schema. Use model="grok-4.5" with base_url=https://api.quicksilverpro.io/v1.