Claude Instant 1.2 on Anthropic

Claude · Anthropic

Serverless

Last refreshed 2026-07-26. Next refresh: weekly.

Why use Claude Instant 1.2 on Anthropic?

Anthropic offers Claude Instant 1.2 with pay-as-you-go pricing at $0.80/1M input tokens. Anthropic is a safety-focused AI research company and creator of the Claude model family, offering API access through the Anthropic Console for text generation, analysis, and coding tasks.

Compare Claude Instant 1.2 across 2 providers to find the best fit for your use case
Input / 1M
$0.80
Output / 1M
$2.40
Cache
Not sourced
Batch
Not sourced

Setup recipe

Python + curl
Install
pip install anthropic
Auth
export ANTHROPIC_API_KEY=...
Call
import anthropic
client = anthropic.Anthropic()  # reads ANTHROPIC_API_KEY from env
message = client.messages.create(
    model="claude-instant-1.2",
Model ID
claude-instant-1.2

Request example

import anthropic

client = anthropic.Anthropic()  # reads ANTHROPIC_API_KEY from env
message = client.messages.create(
    model="claude-instant-1.2",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Hello"}]
)
print(message.content[0].text)

Gotchas

  • Use the versioned model ID, e.g. "claude-sonnet-4-6" or "claude-opus-4-7-20251101".
  • The examples expect ANTHROPIC_API_KEY; rename it only if your application config maps the new variable.

Compare Claude Instant 1.2 Across Providers

ProviderInput (per 1M)Output (per 1M)
AWS Bedrock$0.80$2.40
Anthropic$0.80$2.40

Pricing

TypePrice (per 1M)
Input tokens$0.80
Output tokens$2.40

Capabilities

Structured Outputs

About Claude Instant 1.2

Claude Instant 1.2, developed by Anthropic, is a large language model that offers a faster and more economical alternative to Claude 2. Although it is smaller, it supports a robust context window of 100,000 tokens, making it adept at handling lengthy documents. Significant upgrades from its predecessor include enhanced math and coding capabilities, illustrated by higher scores in Codex and GSM8K benchmarks. Additionally, it generates longer and more structured responses, with improved quote extraction and multilingual skills, while also being more resistant to safety threats and hallucinations.

Get Started

Model Specs

Released2023-08-09
Parameters20B
Context100k
ArchitectureDecoder Only
Knowledge cutoff2023-01