Unbiased: Pareto
Pareto is a language model from Unbiased released on Sep 17, 2026. It reads text and images and writes text, with a 262K token context window and up to 131K tokens per reply.
Show moreShow less
It costs $3.44 per million input tokens and $10.32 per million output tokens. Cached input bills at $0.3439, 90% less than fresh input.
It supports tool calling and prompt caching.
2 providers serve it, including Cloudflare AI Gateway and AI/ML API. The lowest input price is $2.50 per million tokens at Cloudflare AI Gateway.
- Modalities
- In / out price
- $3.44 / $10.32 per 1M
- Context
- 262K
- Max output
- 131K
- Released
- Sep 17, 2026
- Knowledge cutoff
- n/a
- Tool calling
- Structured output
- Reasoning
- Prompt caching
- Open weights
- Free to use
Pareto pricing
USD, as listed on Oct 15, 2026. Most bills are input heavy, so the cached input rate matters as much as the headline price.
| Input | $3.44 / 1M tokens | |
|---|---|---|
| Output | $10.32 / 1M tokens | |
| Cached input (read) | $0.3439 / 1M tokens | 90% off input |
Pareto providers
2 providers serve it, including Cloudflare AI Gateway and AI/ML API. The lowest input price is $2.50 per million tokens at Cloudflare AI Gateway. Each host sets its own price and limits, so the cheapest one is not always the one with the longest context.
| Provider | Input /M | Output /M | Cache read /M | Context | Max output |
|---|---|---|---|---|---|
| Cloudflare AI Gateway | $2.50 | $7.50 | $0.25 | 262K | 131K |
| AI/ML API | $3.44 | $10.32 | $0.3439 | 262K | 131K |
What Pareto costs per month
Pick a workload close to yours or type your own volumes.
Supported request parameters
What you can set when you call Pareto through an OpenAI compatible API.
- Tools
tools - Temperature
temperature
Alternatives to Pareto
Models that take the same inputs and call tools, closest in price, cheaper ones first.
- 262K context
Reads text and images. Tool calling, structured output, reasoning. Served by 22 providers.
by thinkingmachinesJul 15, 2026$3.74/M input tokens$9.36/M output tokens22 providers
- Index 42.1
Reads text, images and files. Tool calling, structured output, reasoning. Served by 39 providers.
by openaiJul 9, 20261.05M context$2/M input tokens$12/M output tokens39 providers
- Index 29.7
Reads text, images, audio and video. Tool calling, structured output, reasoning. Served by 5 providers.
by googleFeb 19, 20261.05M context$2/M input tokens$12/M output tokens5 providers
- Index 51.8
Reads text, images and files. Tool calling, structured output, reasoning. Served by 28 providers.
by openaiSep 29, 20261.05M context$2/M input tokens$10/M output tokens28 providers
- Index 56
Reads text, images and files. Tool calling, structured output, reasoning. Served by 27 providers.
by anthropicSep 26, 20261M context$2/M input tokens$10/M output tokens27 providers
- 1.05M context
Reads text, images and files. Tool calling, structured output, reasoning. Served by 29 providers.
by openaiSep 22, 2026$2/M input tokens$10/M output tokens29 providers
More from Unbiased
- 1.05M context
Reads text and images. Tool calling. Served by 2 providers.
by unbiasedOct 1, 2026$0.80/M input tokens$3.20/M output tokens2 providers
- 262K context
Reads text and images. Tool calling. Served by 2 providers.
by unbiasedSep 18, 2026$2.50/M input tokens$7.50/M output tokens2 providers
Pareto questions
How much does the Pareto API cost?
$3.44 per million input tokens and $10.32 per million output tokens, with cached input at $0.3439. The estimator on this page turns that into a monthly bill for your own workload.
What is the context window of Pareto?
262,144 tokens of input, and it can write up to 131,072 tokens in one reply. As a rough guide, a million tokens is around 750,000 English words.
Which providers serve Pareto?
2 providers serve it, including Cloudflare AI Gateway and AI/ML API. The lowest input price is $2.50 per million tokens at Cloudflare AI Gateway. Prices differ by host, so the Providers table on this page lists each one with its input and output price.
Does Pareto support tool calling?
Yes. It accepts tool definitions, which is what an agent needs to call your APIs.
Is Pareto open source?
No. Unbiased serves it through an API only, so you cannot download the weights or host it yourself.
When was Pareto released?
Sep 17, 2026.
Catalog data from models.dev (MIT licensed), refreshed daily, last on Oct 15, 2026. The summary is written from these facts.