What is the token pricing for GPT-6 Luna on API100?

GPT-6 Luna costs $0.2 per 1 million input tokens and $0.8 per 1 million output tokens with no markup over provider baseline rates.

What is the context window for GPT-6 Luna?

GPT-6 Luna supports a maximum context window of 128k tokens (1,28,000 tokens total).

Does API100 store prompts when using GPT-6 Luna?

No. API100 operates a strict 100% Zero-Retention Privacy policy. Prompts and completions are processed in memory and never logged to disk or used for training.

Back to all models

Last Verified: September 2026

OpenAI

Included in Free Plan

● High Availability (99.9% Upstream SLA)

GPT-6 Luna

Model ID:gpt-6-luna•Company:OpenAI

Ultra-fast, high-throughput micro-task model with sub-180ms TTFT for semantic routing, classification, and real-time chat.

Context Length

128k

Tokens total window

Max Output

8,192

Tokens per response

Prompt Pricing

$0.2

Per 1,000,000 input tokens

Output Pricing

$0.8

Per 1,000,000 output tokens

Key Capabilities

routing

classification

high throughput

budget friendly

Enterprise Reliability

• 100% OpenAI-compatible Chat Completions API endpoint
• Zero prompt data retention — never used for model training
• Sub-50ms gateway routing overhead with prompt caching support
• Atomic multi-provider failover ensures zero service interruptions

OpenAI SDK Drop-in Call

# Python — drop-in replacement for OpenAI SDK

from openai import OpenAI

client = OpenAI(
    base_url="https://apihundred.com/v1",
    api_key="your-api100-key"
)

response = client.chat.completions.create(
    model="gpt-6-luna",
    messages=[
        {"role": "user", "content": "Explain transactional RLS in Postgres"}
    ]
)
print(response.choices[0].message.content)

# cURL API Request

curl https://apihundred.com/v1/chat/completions \
  -H "Authorization: Bearer $API100_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-6-luna",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Gateway Performance & Verification Telemetry

Measured across 10,000 requests routed through API100 multi-region edge nodes.

Official OpenAI Docs Full Benchmarks

Median TTFT

285 ms

Time to first token

Throughput

68 t/s

Output stream velocity

Routing Overhead

< 42 ms

API100 proxy latency

Audit Status

Verified

September 2026 Direct Lab

Frequently Asked Questions about GPT-6 Luna

How do I call GPT-6 Luna with the OpenAI SDK?

Initialize your standard OpenAI client with baseURL="https://api.apihundred.com/v1" and use your API100 key. Pass model="gpt-6-luna" into client.chat.completions.create().

What are the token prices for GPT-6 Luna?

On API100, GPT-6 Luna is priced at $0.2 per million input tokens and $0.8 per million output tokens with direct pass-through rates and unified wallet billing.

Does API100 store prompts when calling GPT-6 Luna?

Zero prompts or outputs are stored on disk. All requests are streamed via TLS 1.3 in ephemeral volatile memory. Prompts are never saved to server logs or used for training.

What happens if OpenAI has an outage?

API100 provides automated multi-provider failover. You can configure fallback models or enable our intelligent router to automatically re-route requests without application errors.

Alternative & Related Models

View Full Catalog

deepseek$0.27/1M

DeepSeek V3

671B parameter Mixture-of-Experts (MoE) activating 37B parameters per token using Multi-Head Latent Attention (MLA).

128k context

openai$3.25/1M

GPT-4o

OpenAI flagship omni model with high-speed intelligence across text, vision, and structured schema generation.

128k context

openai$5/1M

GPT-6 Astra

OpenAI's frontier agentic model engineered for autonomous computer use, desktop GUI interaction, and repository refactoring.

128k context

Key Capabilities

routing

classification

high throughput

budget friendly

Enterprise Reliability

• 100% OpenAI-compatible Chat Completions API endpoint
• Zero prompt data retention — never used for model training
• Sub-50ms gateway routing overhead with prompt caching support
• Atomic multi-provider failover ensures zero service interruptions

OpenAI SDK Drop-in Call

# Python — drop-in replacement for OpenAI SDK

from openai import OpenAI

client = OpenAI(
    base_url="https://apihundred.com/v1",
    api_key="your-api100-key"
)

response = client.chat.completions.create(
    model="gpt-6-luna",
    messages=[
        {"role": "user", "content": "Explain transactional RLS in Postgres"}
    ]
)
print(response.choices[0].message.content)

# cURL API Request

curl https://apihundred.com/v1/chat/completions \
  -H "Authorization: Bearer $API100_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-6-luna",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Frequently Asked Questions about GPT-6 Luna

How do I call GPT-6 Luna with the OpenAI SDK?

Initialize your standard OpenAI client with baseURL="https://api.apihundred.com/v1" and use your API100 key. Pass model="gpt-6-luna" into client.chat.completions.create().

What are the token prices for GPT-6 Luna?

On API100, GPT-6 Luna is priced at $0.2 per million input tokens and $0.8 per million output tokens with direct pass-through rates and unified wallet billing.

Does API100 store prompts when calling GPT-6 Luna?

Zero prompts or outputs are stored on disk. All requests are streamed via TLS 1.3 in ephemeral volatile memory. Prompts are never saved to server logs or used for training.

What happens if OpenAI has an outage?

API100 provides automated multi-provider failover. You can configure fallback models or enable our intelligent router to automatically re-route requests without application errors.