impulse

GPT-6 Luna Decisions

Frontier labOther
API id gpt-6-luna-decisions
Input / 1M
$0.10
at Vercel AI Gateway
Output / 1M
$0.00
at Vercel AI Gateway
Context window
1.1M
tokens
Max output
-
tokens per reply
Hosts
1
1 listings
Released
-
date not published

Pricing

List prices at Vercel AI Gateway, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$0.10$0.00
Cached input
90% off input
$0.01
Cache write, 5 minutes$0.125
Prompts over 272K tokens$0.20

What it costs a month

At Vercel AI Gateway list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$21.90
  • RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$26.40
  • Coding agent1,000 requests a day, 40K in / 2K out, cached$44.40
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$240
Use your own numbers

Where to run it

1 host serve GPT-6 Luna Decisions. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
gpt-6-luna-decisions
$0.10 / $0.00

Capabilities

Core

  • Streaming
  • Function calling
  • JSON mode
  • Structured outputs

Multimodal

  • Vision
  • Image input
  • Audio
  • Image generation
  • Video

Advanced

  • Reasoning
  • Tool calling
  • MCP
  • Prompt caching
  • Batch API
  • Embeddings
Takes in
Text
Produces
Text

Cheaper alternatives

Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.

Same model, cheaper host

No host sells it for less than Vercel AI Gateway.

Smaller OpenAI models

No cheaper OpenAI model keeps its key capabilities.

Other frontier labs

No cheaper match from another frontier lab.

Open-weight picks

No cheaper open-weight match.

Call it

Using Vercel AI Gateway's API.

Python
from litellm import completion

response = completion(
    model="vercel_ai_gateway/gpt-6-luna-decisions",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does GPT-6 Luna Decisions cost?

On Vercel AI Gateway, GPT-6 Luna Decisions costs $0.10 per million input tokens. Cached input costs $0.01 per million tokens.

Which APIs offer GPT-6 Luna Decisions?

GPT-6 Luna Decisions runs on 1 API: Vercel AI Gateway.

What is GPT-6 Luna Decisions's context window?

1.1M tokens.

Is GPT-6 Luna Decisions being retired?

No retirement date is scheduled for it on any API we track.

What is GPT-6 Luna Decisions's API model id?

Use gpt-6-luna-decisions with Vercel AI Gateway.

Sources

Raw catalog entry for gpt-6-luna-decisions on Vercel AI Gateway
{
  "cache_creation_input_token_cost": 1.25e-7,
  "cache_creation_input_token_cost_above_272k_tokens": 2.5e-7,
  "cache_read_input_token_cost": 1e-8,
  "cache_read_input_token_cost_above_272k_tokens": 2e-8,
  "input_cost_per_token": 1e-7,
  "input_cost_per_token_above_272k_tokens": 2e-7,
  "litellm_provider": "vercel_ai_gateway",
  "max_input_tokens": 1050000,
  "mode": "evaluation",
  "output_cost_per_token": 0,
  "source": "https://ai-gateway.vercel.sh/v1/models"
}