Pricing, context window, capabilities, and release date — pulled from each provider's public docs. Both are available via the same AIgateway OpenAI-compatible endpoint; flip the model string to switch.
Both models stream in parallel through your own AIgateway key. Tokens, latency, and cost update as they arrive.
| Claude Haiku 5.5 anthropic/claude-haiku-5.5 | Pareto unbiased/pareto | |
|---|---|---|
| Provider | Anthropic | Unbiased |
| Family | Claude 4 | |
| Modality | text | text |
| Context window | 1,000,000 tok | 262,144 tok |
| Max output | 128,000 tok | 32,768 tok |
| Released | 2026-10-12 | 2026-09-17 |
| Input price | $0.100 /1M | $2.50 /1M |
| Output price | $0.500 /1M | $7.50 /1M |
| Cache read | — | — |
| Tools | yes | — |
| Streaming | yes | yes |
| Vision | yes | — |
| JSON mode | yes | — |
| Reasoning | — | — |
| Prompt caching | — | — |
Claude Haiku 5.5 is a fast, cost-efficient model for high-volume, latency-sensitive tasks such as classification, extraction, routing, and subagent work.
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.
# pip install aigateway-py openai
# aigateway-py: sub-accounts, evals, replays, jobs, webhook verify.
# openai SDK: chat/embeddings/images/audio — drop-in compat per our SDK's own guidance.
from openai import OpenAI
client = OpenAI(
base_url="https://api.aigateway.sh/v1",
api_key="sk-aig-...",
)
# Try Claude Haiku 5.5
client.chat.completions.create(
model="anthropic/claude-haiku-5.5",
messages=[{"role":"user","content":"hello"}],
)
# Try Pareto — same client, same key
client.chat.completions.create(
model="unbiased/pareto",
messages=[{"role":"user","content":"hello"}],
)