Compare

Decisions vs Pareto

Pricing per million tokens, context window, capabilities — pulled from each provider's public docs. All 2 are available via the same AIgateway OpenAI-compatible endpoint; flip the model string to switch.

Search2/4
Decisions
openai/decisions
P
Pareto
unbiased/pareto
Provider
OpenAI
Unbiased
Family
Modality
text
text
Context window
1,050,000 tok
262,144 tok
Max output
32,768 tok
32,768 tok
Released
2026-10-26
2026-09-17
License
Open-weight
Open-weight
Input price
$0.100 /1M
$2.50 /1M
Output price
$0.0000 /1M
$7.50 /1M
Tools
—
—
Streaming
yes
yes
Vision
—
—
JSON mode
—
—
Reasoning
—
—
Prompt caching
—
—
Batch API
—
—
Try it
Open in playground →
Open in playground →
Decisions
openai/decisions
Full spec →

Decisions uses GPT-6 Luna to evaluate shared text or image evidence against typed questions. It returns probabilities, fixed choices, or rubric scores for low-latency classification, routing, and prioritization workflows.

Strengths
  • General-purpose chat
  • Long context
  • Tool use
Use cases
ChatbotsContent generationAgentic workflows
Pareto
unbiased/pareto
Full spec →

Pareto is Unbiased's blended AI model. It engages multiple language models in parallel for each request, synthesizes one answer, and supports text and vision inputs through a single API response.

Strengths
  • General-purpose chat
  • Long context
  • Tool use
Use cases
ChatbotsContent generationAgentic workflows

Compare with another

Gemini 4 Argon vs Decisions
google/gemini-4-argon · openai/decisions
Gemini 4 Argon vs Pareto
google/gemini-4-argon · unbiased/pareto
Claude Opus 5.5 vs Decisions
anthropic/claude-opus-5.5 · openai/decisions
Claude Opus 5.5 vs Pareto
anthropic/claude-opus-5.5 · unbiased/pareto
Claude Sonnet 5.5 vs Decisions
anthropic/claude-sonnet-5.5 · openai/decisions
Claude Sonnet 5.5 vs Pareto
anthropic/claude-sonnet-5.5 · unbiased/pareto
Deepseek-V4.1-Flash-1017 vs Decisions
deepseek/deepseek-v4.1-flash-1017 · openai/decisions
Deepseek-V4.1-Flash-1017 vs Pareto
deepseek/deepseek-v4.1-flash-1017 · unbiased/pareto
Grok 4.7 vs Decisions
xai/grok-4.7 · openai/decisions
SWITCH BETWEEN THEM

One key, all 2, one line different.

from openai import OpenAI

client = OpenAI(
    base_url="https://api.aigateway.sh/v1",
    api_key="sk-aig-...",
)

# Decisions
client.chat.completions.create(
    model="openai/decisions",
    messages=[{"role":"user","content":"hello"}],
)

# Pareto
client.chat.completions.create(
    model="unbiased/pareto",
    messages=[{"role":"user","content":"hello"}],
)
Get an AIgateway keyRun an eval on these →