A
Claude 4.8 Opus
Claude 4.8 Opus, a language model from Anthropic.
modelOverride: { model: "claude-4-8-opus" }
Anthropic·Released May 2026Pricing
- Input
- $5.00 / 1M
- Output
- $25.00 / 1M
- Cached input
- $0.50 / 1M
- Cached input
- $6.25 / 1M
- Cached input
- $10.00 / 1M
Specifications
- Context window
- 1,000,000 tokens
- Max output
- 128,000 tokens
- Released
- May 2026
- Model string
- claude-opus-4-8
- Capabilities
- VisionLarge contextReasoningToolsMCP
Parameters
Model options, passed in
modelOverride.config.| Parameter | Type | Default | Range / options |
|---|---|---|---|
reasoningWhen enabled, the model will explain its thought process step-by-step before providing a final answer. This can help users understand how the model arrived at its conclusions, but may result in longer responses. Opus 4.7 uses adaptive thinking mode. The model dynamically decides when and how much to think. | Select | false | falsetrue |
effortControls how much the model thinks vs. how quickly it responds. Higher effort produces better quality but uses more tokens and is slower. Recommended: High or Extra High for coding and agentic work; Medium for general use; Low for short, latency-sensitive tasks. Only applies when Reasoning is enabled. | Select | medium | lowmediumhighxhighmax |
tools | Tools | — | — |
mcpServers | MCP servers | — | — |
Use this model
await mindstudio.generateText({ message: "...", modelOverride: { model: "claude-4-8-opus", config: { reasoning: "false", effort: "medium", }, }, });