Providers & pricing
| Provider | Input | Output | Free tier |
|---|---|---|---|
 Anthropic Default | 3767.7 RODI/M~5.00 USD/M | 18838.4 RODI/M | — |
 AWS | 3767.7 RODI/M~5.00 USD/M | 18838.4 RODI/M | — |
Pricing
| Rate | RODI | USD (ref.) | Unit |
|---|---|---|---|
| In | 3767.7 | ~ 5.00 | USD/M · RODI/M |
| Out | 18838.4 | ~ 25.00 | USD/M · RODI/M |
| Cached | 376.8 | ~ 0.500 | USD/M · RODI/M |
RODI prices include RodiumAi markup and upstream fees. USD figures are wholesale reference rates.
Capabilities
Streaming
Tool calling
Vision
JSON mode
Reasoning
About this model
Most capable generally available model for complex reasoning and agentic coding. Features a new tokenizer (compared to previous models) that may use up to 35% more tokens for the same fixed text. Includes a step-change improvement in agentic coding over Opus 4.6. Supports up to 300k output tokens via Message Batches API with the output-300k-2026-03-24 beta header.
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.
…