tokenstat
tokenstat

Anthropic: Claude 4.6 Opus Thinking

anthropic/claude-opus-4-6 · rates as of · Benchmarks · AI plans · Calculator

High-end Claude for difficult coding, planning, and slower expert reasoning

Cheapest input
$2.50
$/MTok · OpenRouter
Cheapest output
$12.50
$/MTok
Context
1M
tokens
Sources
4
56 listings

Sources

Same model, different sources. Our first-party rate is listed first, then router and aggregator rows stay separate so you can see the spread instead of a single blended number.

SourceProviderInputOutputCache readContext
tokenstatanthropic/claude-opus-4.6Anthropic$5$25$0.51M
OpenRoutercheapestanthropic/claude-opus-4.6:batchOpenRouter$2.50$12.50$0.251M
LiteLLManthropic/claude-opus-4.6:batchN/A$2.50$12.50$0.25N/A
models.devstealth/claude-opus-4.6Kilo Gateway$4$20$0.41M
models.devanthropic/claude-opus-4.6Poe$4.30$21$0.43983K
models.devanthropic/claude-opus-4.6:thinkingNanoGPT$5$25$0.51M
models.devdatabricks-claude-opus-4-6Databricks$5$25$0.51M
models.devclaude-opus-4-6Abacus$5$25$01M
models.devclaude-opus-4-6AIHubMix$5$25$0.51M
models.devclaude-opus-4-6Anthropic$5$25$0.51M
models.devclaude-opus-4-6Auriko$5$25$0.51M
models.devclaude-opus-4-6Azure$5$25$0.51M
models.devclaude-opus-4-6Azure$5$25$0.51M
models.devanthropic/claude-opus-4.6Cloudflare$5$25$0.51M
models.devanthropic/claude-opus-4-6Eden AI$5$25$0.51M
models.devclaude-opus-4-6FreeModel$5$25$0.51M
models.devclaude-opus-4-6FrogBot$5$25$0.5200K
models.devanthropic/claude-opus-4.6GMI Cloud$5$25$0.5410K
models.devanthropic/claude-opus-4-6Impossibl$5$25$0.51M
models.devclaude-opus-4-6Jiekou.AI$5$25$01M
models.devanthropic/claude-opus-4.6Kilo Gateway$5$25$0.51M
models.devvertex-anthropic/claude-opus-4-6LLM Gateway$5$25$0.51M
models.devclaude-opus-4-6DevPass (LLM Gateway)$5$25$0.51M
models.devanthropic/claude-opus-4-6Merge Gateway$5$25$0.51M
models.devanthropic/claude-opus-4.6NanoGPT$5$25$0.51M
models.devanthropic/claude-opus-4-6NEAR AI Cloud$5$25$0.5200K
models.devclaude-opus-4-6Neon$5$25$0.51M
models.devanthropic/claude-opus-4.6Ofox$5$25$0.51M
models.devclaude-opus-4-6OpenCode Zen$5$25$0.51M
OpenRouteranthropic/claude-opus-4.6OpenRouter$5$25$0.51M
models.devanthropic/claude-opus-4-6Opper$5$25$0.51M
models.devanthropic/claude-opus-4.6OrcaRouter$5$25$0.51M
models.devanthropic/claude-opus-4-6Perplexity$5$25$0.5200K
models.devclaude-opus-4-6Pioneer$5$25$0.51M
models.devclaude-opus-4-6Requesty$5$25$0.51M
models.devanthropic/claude-opus-4.6Vercel AI Gateway$5$25$0.51M
models.devanthropic/claude-opus-4.6ZenMux$5$25$0.51M
models.devclaude-opus-4-6-thinkAIHubMix$5$25$0.51M
models.devanthropic-claude-opus-4.6DigitalOcean$5$25$0.5200K
models.devclaude-opus-4-6@defaultVertex (Anthropic)$5$25$0.51M
models.devclaude-opus-4-6@defaultGoogle Vertex AI$5$25$0.51M
models.devanthropic/claude-opus-4.6:thinking:lowNanoGPT$5$25$0.51M
models.devanthropic/claude-opus-4.6:thinking:maxNanoGPT$5$25$0.51M
models.devanthropic/claude-opus-4.6:thinking:mediumNanoGPT$5$25$0.51M
models.devanthropic--claude-4.6-opusSAP AI Core$5$25$0.51M
LiteLLMclaude-opus-4-6N/A$5$25$0.5N/A
LiteLLMclaude-opus-4-6@defaultN/A$5$25$0.5N/A
LiteLLMazure_ai/claude-opus-4-6N/A$5$25$0.5N/A
LiteLLMclaude-opus-4-6-20260205N/A$5$25$0.5N/A
LiteLLMperplexity/anthropic/claude-opus-4-6N/A$5$25$0.5N/A
LiteLLMvercel_ai_gateway/anthropic/claude-opus-4.6N/A$5$25$0.5N/A
LiteLLMvertex_ai/claude-opus-4-6N/A$5$25$0.5N/A
LiteLLMvertex_ai/claude-opus-4-6@defaultN/A$5$25$0.5N/A
LiteLLMdatabricks-claude-opus-4-6N/A$5$25$0.5N/A
LiteLLMdatabricks/databricks-claude-opus-4-6N/A$5$25$0.5N/A
models.devclaude-opus-4-6Venice AI$6$30$0.61M

Capabilities

  • Reasoning
  • Tool calling
  • Structured output
  • Attachments
  • In: text
  • In: image
  • In: pdf
  • In: file
  • Out: text
Knowledge cutoff: 2025-05-31Released: 2026-02-05Family: claude-opus

Scores

Sparse coverage on purpose. Missing a score means we have not linked one yet, not that the model is unranked. Hover or tap the i next to any score for its source. Full boards on /benchmarks.

Arena rows are community-vote Elo from Arena AI, Artificial Analysis indices arrive via OpenRouter, and launch-eval figures are collected from vendor announcements, analyst writeups, and community benchmarks. Full boards and credits on /benchmarks.

Run this model in a real workspace

Launch agents from the project they work in, use remote management to reach another machine, and see this model's sessions and token usage in your own history. Free to use, runs on your device.

CLI for macOS, Linux, and Windows

Data and list-price estimates may contain mistakes. Not investment advice.