Unbiased: Pareto
unbiased/pareto
Pareto is Unbiased's blended AI service: multiple underlying language models contribute to a request and the service returns one synthesized answer through a single model alias. It is a hosted composite service, not an identified standalone weight checkpoint. The published model card supports text and image inputs; the API returns text and tool calls through OpenAI Chat Completions or Anthropic Messages, including streaming. It can be used for conversational assistance and tool-based workflows. The rolling API identifier remains pareto; a dated model-card edition does not establish a version-pinned endpoint. The configured context window is 1,048,576 tokens and the maximum output is 131,072 tokens, using exact limits confirmed by the user on October 2, 2026; these limits are not stated in the retrieved public specification. Serving quantization remains unspecified.
Model specifications
- Input
- text, image
- Output
- text
- Context
- 1,048,576 tokens
- Max output
- 131,072 tokens
- Input price
- $2.5 / 1M tokens
- Output price
- $7.5 / 1M tokens
- Released
- 2026-10-02
Capabilities
- Streaming
- Function calling
- Vision
- JSON mode
Provider pricing, discounts and data privacy
Compare effective provider prices, published discounts, regions, retention policies, training use, compliance, and privacy links by service tier.
Standard service tier
1 available provider · tier input average $2.5 / 1M tokens · tier output average $7.5 / 1M tokens
UnBiased
Tier: Standard · Region: US
Pricing
- Input
- $2.5 / 1M tokens
- Output
- $7.5 / 1M tokens
- Cache read
- $0.25 / 1M tokens
No provider discount is currently published.
Data privacy and compliance
- Region
- US
- Zero data retention
- No
- Used for training
- No
- Data collection
- Moderated
- No
- GDPR compliant
- No
- HIPAA compliant
- No
- SOC 2 certified
- No
- BYOK supported
- No
Frequently asked questions
- What is Unbiased: Pareto?
- Pareto is Unbiased's blended AI service: multiple underlying language models contribute to a request and the service returns one synthesized answer through a single model alias. It is a hosted composite service, not an identified standalone weight checkpoint. The published model card supports text and image inputs; the API returns text and tool calls through OpenAI Chat Completions or Anthropic Messages, including streaming. It can be used for conversational assistance and tool-based workflows. The rolling API identifier remains pareto; a dated model-card edition does not establish a version-pinned endpoint. The configured context window is 1,048,576 tokens and the maximum output is 131,072 tokens, using exact limits confirmed by the user on October 2, 2026; these limits are not stated in the retrieved public specification. Serving quantization remains unspecified.
- How much does Unbiased: Pareto cost?
- Input costs start at $2.5 / 1M tokens and output costs start at $7.5 / 1M tokens. Provider-level prices vary by service tier.
- What is the context length of Unbiased: Pareto?
- Unbiased: Pareto supports a 1,048,576 token context window and up to 131,072 output tokens.
- What capabilities does Unbiased: Pareto support?
- Unbiased: Pareto supports Streaming, Function calling, Vision, JSON mode.
- Which providers offer Unbiased: Pareto?
- Unbiased: Pareto is available from UnBiased.
- How do providers handle data privacy for Unbiased: Pareto?
- 1 of 1 providers report that customer data is not used for training, and 0 offer zero-data-retention routing. Retention, compliance, and privacy-policy links are listed per provider.