Skip to content
Router One
Sign up
Back to Models
Long context

Claude Sonnet 4.6 (thinking) API pricing

Anthropic's Claude series — long context, dependable tool calling, and the native models behind Claude Code.

Model IDanthropic/claude-sonnet-4.6-thinking
ChatStreamingTool callingVision
Get API KeyRun your first request

Call summary

Input
$3.00$0.90/ 1M tokens
Cache write $1.875
Cache read $0.15
Output
$15.00$4.50/ 1M tokens
Context Window
1.05M
API Endpoints
2

Claude Sonnet 4.6 (thinking) API endpoints

One API key — call this model through any of the 2 endpoints below.

POST/v1/chat/completionsOpenAI-compatible · Works for every model
Chat Completions reference
POST/v1/messagesAnthropic-native · Native for Claude Code
Messages API reference

Production reliability

Privacy-safe aggregates from real Router One model calls, so you can assess stability and response latency before integrating.

Successful response share

99.88%

Success 2xx

99.88%

Rate limit 429

0.00%

Server 5xx

0.12%

TPS

—

tokens/s
Avg. time to first token

—

Avg. latency

6.42 s

Includes production requests ending in 2xx, 429, or 5xx. Average latency uses successful requests; time to first token and TPS require complete observations from successful streams. Public thresholds are 100 requests and 5 independent principals.

Updated Oct 25, 2026, 8:12 AM UTC

More Claude models on Router One

29 other Claude models on the same gateway and API key — each page lists endpoints, posted price, and context window.

Claude Fable 5$8.00 in / $40.00 out per 1M1.05M contextClaude Fable 5.1$6.00 in / $30.00 out per 1M1.05M contextClaude Haiku 4.5$0.30 in / $3.00 out per 1M200K contextClaude Haiku 5.5$0.06 in / $0.30 out per 1M1.05M contextClaude Opus 4.6$2.25 in / $11.25 out per 1M1.05M contextClaude Opus 4.6 (thinking)$2.25 in / $11.25 out per 1M1.05M contextClaude Opus 4.7 (thinking)$2.25 in / $11.25 out per 1M1.05M contextClaude Opus 4.8$2.25 in / $11.25 out per 1M1.05M contextClaude Opus 5$2.25 in / $11.25 out per 1M1.05M contextClaude Opus 5.5$2.40 in / $12.00 out per 1M1.05M contextClaude Sonnet 4.6$0.90 in / $4.50 out per 1M1.05M contextClaude Sonnet 5$0.90 in / $4.50 out per 1M1.05M contextClaude Sonnet 5.5$1.20 in / $6.00 out per 1M1.05M context
16 channel versions
Claude Haiku 4.5 · AWS$1.00 in / $5.00 out per 1M200K contextClaude Opus 4.5 · AWS$5.00 in / $25.00 out per 1M200K contextClaude Opus 4.6 · AWS$5.00 in / $25.00 out per 1M1M contextClaude Opus 4.7 · AWS$5.00 in / $25.00 out per 1M1M contextClaude Opus 4.8 · AWS$5.00 in / $25.00 out per 1M1M contextClaude Opus 5 · AWS$5.00 in / $25.00 out per 1M1M contextClaude Sonnet 4.5 · AWS$3.00 in / $15.00 out per 1M200K contextClaude Sonnet 4.6 · AWS$3.00 in / $15.00 out per 1M1M contextClaude Sonnet 5 · AWS$2.00 in / $10.00 out per 1M1M contextClaude Opus 4.6 · Vertex$5.00 in / $25.00 out per 1M1M contextClaude Opus 4.7 · Vertex$5.00 in / $25.00 out per 1M1M contextClaude Opus 4.8 · Vertex$5.00 in / $25.00 out per 1M1M contextClaude Opus 5 · Vertex$5.00 in / $25.00 out per 1M1M contextClaude Sonnet 4.5 · Vertex$3.00 in / $15.00 out per 1M200K contextClaude Sonnet 4.6 · Vertex$3.00 in / $15.00 out per 1M1M contextClaude Sonnet 5 · Vertex$2.00 in / $10.00 out per 1M1M context

Claude Sonnet 4.6 (thinking) at a glance

Claude Sonnet 4.6 (thinking) (model ID anthropic/claude-sonnet-4.6-thinking) is a Claude-series text model on Router One. anthropic/claude-sonnet-4.6-thinking thinks by default: a request that omits the thinking field is sent with adaptive thinking, and a request that already carries a thinking value (disabled included) is not given a second one — the API compatibility facts state the per-generation rules. Posted rate: $0.90 in / $4.50 out per 1M tokens (was $3.00 in / $15.00 out). Router One subscriptions include Claude Sonnet 4.6 (thinking) in the Mid-tier models allowance: Pro 1,200, Max 4,500, Ultra 15,000 requests per 30-day cycle. Usage beyond the allowance bills the wallet at posted rates. Within a plan allowance, a request above 256,000 / 512,000 input tokens counts as 2 / 4 requests. Context window: 1.05M tokens. Accepts text, image; returns text. Endpoints: POST /v1/chat/completions (OpenAI-compatible), POST /v1/messages (Anthropic-native, the Claude Code path).

Claude Sonnet 4.6 (thinking) FAQ

How much does Claude Sonnet 4.6 (thinking) cost on Router One?

Claude Sonnet 4.6 (thinking) is billed per token on Router One: $0.90 in / $4.50 out per 1M tokens, pay as you go.

Is Claude Sonnet 4.6 (thinking) included in Router One subscriptions?

Router One subscriptions include Claude Sonnet 4.6 (thinking) in the Mid-tier models allowance: Pro 1,200, Max 4,500, Ultra 15,000 requests per 30-day cycle. Usage beyond the allowance bills the wallet at posted rates. Within a plan allowance, a request above 256,000 / 512,000 input tokens counts as 2 / 4 requests.

Which endpoints serve Claude Sonnet 4.6 (thinking)?

Claude Sonnet 4.6 (thinking) is served on 2 endpoints — POST /v1/chat/completions (OpenAI-compatible), POST /v1/messages (Anthropic-native, the Claude Code path). The same Router One API key works on each.

What is Claude Sonnet 4.6 (thinking)'s context window?

Claude Sonnet 4.6 (thinking) accepts up to 1.05M tokens of context per request on Router One.

Start using Claude Sonnet 4.6 (thinking)

Create an API key and call Claude Sonnet 4.6 (thinking) at $0.90 in / $4.50 out per 1M tokens on Router One — pay as you go, with per-request cost and latency visibility.

Get API KeyPlans & pay-as-you-go pricingCompare models side by sideQuickstart guideClaude API access