tokenstat
tokenstat

Anthropic: Claude Sonnet 4

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

Balanced Claude model for coding, analysis, agent workflows, and cost control

Cheapest input
$2.60
$/MTok · models.dev
Cheapest output
$13
$/MTok
Context
1M
tokens
Sources
3
46 listings

Price changes

Cheapest list input/output only. Rates move rarely, so this is an event log. Down means cheaper. Showing the 8 latest changes.

Input $/MTok over sampled dates
Output $/MTok
  • ↓ lowerOutput $15 → $13
  • ↓ lowerInput $3 → $2.60

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
models.devcheapestanthropic/claude-sonnet-4Poe$2.60$13$0.26983K
models.devclaude-sonnet-4-20250514Jiekou.AI$2.70$13.50$0200K
models.devclaude-sonnet-4Cortecs$2.90$14.49$0.29200K
LiteLLMdatabricks-claude-sonnet-4N/A$3$15$0.3N/A
LiteLLMdatabricks/databricks-claude-sonnet-4N/A$3$15$0.3N/A
models.devanthropic/claude-sonnet-4FastRouter$3$15$0.3200K
models.devanthropic/claude-sonnet-4Kilo Gateway$3$15$0.3200K
models.devanthropic/claude-sonnet-4NanoGPT$3$15$0.3200K
OpenRouteranthropic/claude-sonnet-4OpenRouter$3$15$0.31M
models.devanthropic/claude-sonnet-4Vercel AI Gateway$3$15$0.31M
models.devanthropic/claude-sonnet-4ZenMux$3$15$0.31M
models.devdatabricks-claude-sonnet-4Databricks$3$15$0.3200K
models.devclaude-sonnet-4-20250514Abacus$3$15$0200K
models.devclaude-sonnet-4@20250514Vertex (Anthropic)$3$15$0.3200K
models.devclaude-sonnet-4@20250514Google Vertex AI$3$15$0.3200K
models.devapac.anthropic.claude-sonnet-4-20250514-v1:0Amazon Bedrock$3$15$0.3200K
models.deveu.anthropic.claude-sonnet-4-20250514-v1:0Amazon Bedrock$3$15$0.3200K
models.devglobal.anthropic.claude-sonnet-4-20250514-v1:0Amazon Bedrock$3$15$0.3200K
models.devus.anthropic.claude-sonnet-4-20250514-v1:0Amazon Bedrock$3$15$0.3200K
models.devclaude-sonnet-4Helicone$3$15$0.3200K
models.devclaude-sonnet-4OpenCode Zen$3$15$0.31M
models.devanthropic-claude-sonnet-4DigitalOcean$3$15$0.31M
models.devanthropic/claude-sonnet-4-20250514Merge Gateway$3$15$0.3200K
models.devanthropic/claude-sonnet-4:thinkingNanoGPT$3$15$0.31M
models.devanthropic--claude-4-sonnetSAP AI Core$3$15$0.3200K
LiteLLManthropic/claude-sonnet-4N/A$3$15$0.3N/A
LiteLLMclaude-sonnet-4-20250514N/A$3$15$0.3N/A
LiteLLMclaude-sonnet-4@20250514N/A$3$15$0.3N/A
LiteLLMapac.anthropic.claude-sonnet-4-20250514-v1:0N/A$3$15$0.3N/A
LiteLLMeu.anthropic.claude-sonnet-4-20250514-v1:0N/A$3$15$0.3N/A
LiteLLMglobal.anthropic.claude-sonnet-4-20250514-v1:0N/A$3$15$0.3N/A
LiteLLMus.anthropic.claude-sonnet-4-20250514-v1:0N/A$3$15$0.3N/A
LiteLLMclaude-sonnet-4N/A$3$15$0.3N/A
LiteLLManthropic.claude-sonnet-4-20250514-v1:0N/A$3$15$0.3N/A
LiteLLMclaude-4-sonnet-20250514N/A$3$15$0.3N/A
LiteLLMclaude-sonnet-4-20250514-v1:0N/A$3$15$0.3N/A
LiteLLMgmi/anthropic/claude-sonnet-4N/A$3$15$0.3N/A
LiteLLMreplicate/anthropic/claude-4-sonnetN/A$3$15$0.3N/A
LiteLLMsnowflake/claude-4-sonnetN/A$3$15$0.3N/A
LiteLLMvercel_ai_gateway/anthropic/claude-4-sonnetN/A$3$15$0.3N/A
LiteLLMvercel_ai_gateway/anthropic/claude-sonnet-4N/A$3$15$0.3N/A
LiteLLMvertex_ai/claude-sonnet-4N/A$3$15$0.3N/A
LiteLLMvertex_ai/claude-sonnet-4@20250514N/A$3$15$0.3N/A
LiteLLManthropic/claude-4-sonnetN/A$3.30$16.50$0.33N/A
LiteLLMclaude-4-sonnetN/A$3.30$16.50$0.33N/A
LiteLLMdeepinfra/anthropic/claude-4-sonnetN/A$3.30$16.50$0.33N/A

Capabilities

  • Reasoning
  • Tool calling
  • Structured output
  • Attachments
  • In: text
  • In: image
  • In: pdf
  • In: file
  • Out: text
Knowledge cutoff: 2025-03-31Released: 2025-09-29Family: claude-sonnet

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.