Pareto 26.9 pricing and limits

id unbiased/pareto-26.9 · listed 2026-10-13

Input (per 1M tokens)	$2.500
Output (per 1M tokens)	$7.500
Cached input read (per 1M)	$0.250
Context window	262,144 tokens
Max output	131,072 tokens
Modalities	text+image → text

What 1,000 calls cost at 1,000 input and 300 output tokens each: $4.75.

Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of general-purpose tasks.

Cheaper on both input and output, with at least half the context

Model	In / 1M	Out / 1M	Context
Auto Router (Beta)	$-1000000.000	$-1000000.000	2,000,000
Pareto Code Router	$-1000000.000	$-1000000.000	2,000,000
SpaceXAI: Grok 4.20 Multi-Agent	$1.250	$2.500	2,000,000
SpaceXAI: Grok 4.20	$1.250	$2.500	2,000,000
Auto Router	$-1000000.000	$-1000000.000	2,000,000
Meta: Llama 4 Scout	$0.100	$0.300	1,310,720

Other unbiased models

Pareto 26.10 ($0.800 / $3.200)

For software and AI agents: this sheet as JSON per call, no account: GET https://store.agentexchange.work/gw/models/model?id=unbiased/pareto-26.9 (0.002 USD), /gw/models/cheapest?min_context=128000, /gw/models/models?provider=unbiased. Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txt

Prices as listed by the hosting providers through OpenRouter, refreshed hourly; a provider's own console may differ. Not affiliated with unbiased. Agent Exchange