Skip to content
  • 1M context
  • Multimodal
  • Reasoning
  • Responses API
  • NEW · Nov 17

GPT-6.2 Astra on QuickSilver Pro

gpt-6.2-astra
OpenAILive availability—

GPT-6.2 Astra with a 1M-token context, image input. OpenAI list rates for prompts up to 200K tokens; longer prompts use QuickSilver's long-context rate.

  • 1M context
  • 128K max output
  • Vision
  • Tools
  • Reasoning · on by default
  • Streaming
  • JSON Schema output

You pay · input / output per 1M

$8.00 / $40.00

Prompts over 200K tokens: $16.00 / $60.00

OpenAI list source: developers.openai.com/api/docs/models/gpt-6.2-astra

At a glance

Context
1M tokens
Input / 1M
$8.00
Output / 1M
$40.00
Thinks by default
Yes
Max output
128K
Latency · live
—

Text and image workflows with streaming, tools and strict JSON Schema.

When is GPT-6.2 Astra the right call?

Curated from catalog capabilities and published prices, not a benchmark.

When to use

Use GPT-6.2 Astra for text and image requests, automatic or named function calls, and strict JSON Schema responses. Low reasoning effort passed launch probes; evaluate your own coding and document workloads before choosing it.

  • Long documents and codebases, up to 1M tokens of context
  • Agents that call tools, with strict JSON Schema output
  • Prompts that include images
  • Multi-step reasoning, on by default

When to use something else

Choose another model when you need reasoning disabled, temperature or top_p controls, audio or image generation. Launch probes verify API behavior, not comparative task quality.

Compare alternatives in Models

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": "gpt-6.2-astra",
    "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="gpt-6.2-astra",
    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: "gpt-6.2-astra",
  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": "gpt-6.2-astra",
    "input": "Hello!"
  }'
python (OpenAI SDK)
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="gpt-6.2-astra",
    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.
tool_choice (forced)
Retained on this model: a forced tool choice can require that tool call.
prompt
Prompts up to 1M tokens. Above 200K prompt tokens the request bills at $16.00 input / $60.00 output per 1M.
max_tokens
Up to 128K output tokens.
  • /v1/chat/completions: Supported
  • /v1/responses: Supported
  • streaming: Supported
  • tools: Supported
  • image input: Supported
  • JSON Schema: Supported
  • reasoning: Supported

Where the price comes from

Catalog v87 · long-context tier above 200K prompt tokens

Provider reference
No provider list price is compared for this model.developers.openai.com/api/docs/models/gpt-6.2-astra
Catalog verified
Prompt cache · not compared
$0.40 read
Long-context tier
$16.00 / $60.00 over 200K

usage.cost = prompt_tokens × $8.00/1M + completion_tokens × $40.00/1M

/pricing.json

Base rates; cached prompt tokens bill at the cache rates above.

FAQ

Common questions

$8.00 input / $40.00 output per million tokens. Prompt caching (automatic and explicit) is not available for these models at launch, so all input is billed at the applicable standard input rate, including the long-context tier above 200K prompt tokens. Reasoning tokens are billed as output.

GPT-6.2 Astra

Try GPT-6.2 Astra with double credits — up to $50 in bonus credits

Get API Key

$8.00 / $40.00in / out per 1M tokens

TryGet API Key