Pareto

unbiased/pareto

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.

Modalities
In / out per 1M$2.50 / $7.50
Context256K
ReleasedSep 17, 2026

Pricing

List rates per 1M tokens — what Pareto costs pay-as-you-go elsewhere, not what you pay here.

Input
$2.50
per 1M tokens
Output
$7.50
per 1M tokens
Cache read
$0.25
per 1M cached tokens
Included in every pass
Pareto is included in every ProjectCOZY pass at no extra cost — one flat rate, no per-token metering. The rates above are there for comparison.

Performance

Time to first token and output speed across every provider.

No measurements published

This measurement has not been published for the model yet. It appears as soon as it is.

Uptime

Share of requests that at least one provider served successfully.

No uptime published

This measurement has not been published for the model yet. It appears as soon as it is.

Apps

Tools that most often run Pareto, by tokens this week.

No apps published

This measurement has not been published for the model yet. It appears as soon as it is.

Activity

15.2B tokens processed market-wide in the last month.

02.0B4.0B6.0B8.0B
Sep 17Sep 22Sep 27Oct 2Oct 7Oct 12
Tokens

FAQ

Which model id do I use for Pareto?
unbiased/pareto. Send it as the model field from any OpenAI-compatible client, against http://192.168.1.55/v1.
How much context does Pareto hold?
262,144 tokens per request, of which up to 131,072 can be the response.
What can it accept and return?
Input: text, image. Output: text.
What does Pareto cost on a pass?
Nothing beyond the pass itself. Pay-as-you-go elsewhere it lists at $2.50 per 1M input tokens and $7.50 per 1M output tokens.

Explore

Other models your pass can call.