Providers & pricing
| Provider | Input | Output | Free tier |
|---|---|---|---|
 Anthropic Default | 75.7 RODI/M~0.100 USD/M | 378.4 RODI/M | — |
 AWS | 75.7 RODI/M~0.100 USD/M | 378.4 RODI/M | — |
Pricing
| Rate | RODI | USD (ref.) | Unit |
|---|---|---|---|
| In | 75.7 | ~ 0.100 | USD/M · RODI/M |
| Out | 378.4 | ~ 0.500 | USD/M · RODI/M |
| Cached | 7.6 | ~ 0.0100 | USD/M · RODI/M |
RODI prices include RodiumAi markup and upstream fees. USD figures are wholesale reference rates.
Capabilities
About this model
Claude Haiku 5.5 is Anthropic's fastest and most efficient model, built for high-volume, latency-sensitive work such as classification, extraction, routing, summarization, subagents, and browser use. It is the most capable Haiku yet, with stronger coding and agent performance than Haiku 4.5, and the first Haiku with effort controls (low to max, default medium) and adaptive thinking. It supports text, image, and document inputs with text output, a 1M-token context window, and up to 128K output tokens.
API usage
Native Anthropic Messages API: use client.messages() or the anthropic package.
RodiumAi SDK
Use messages() for Anthropic-native payloads; OpenAI chat mode remains available below.
…Compatible SDKs (OpenAI / Anthropic packages)
…Anthropic POST /v1/messages: anthropic package + base_url https://api.rodiumai.io.
…