Skip to content
Back to Models
Text model

Claude Haiku 4.5 API pricing

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

Model IDanthropic/claude-haiku-4.5
ChatStreamingTool callingVision

Call summary

Input
$1.00$0.30/ 1M tokens
Cache write $0.60
Cache read $0.12
Output
$9.00$3.00/ 1M tokens
Context Window
200K
API Endpoints
2

Claude Haiku 4.5 API endpoints

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

POST/v1/chat/completionsOpenAI-compatible · Works for every model
POST/v1/messagesAnthropic-native · Native for Claude Code

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

184.18

tokens/s
Avg. time to first token

3.79 s

Avg. latency

6.83 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 24, 2026, 8:12 PM 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.

16 channel versions

Claude Haiku 4.5 compared with other models

Spec and price matchups against peer models.

Claude Haiku 4.5 at a glance

Claude Haiku 4.5 (model ID anthropic/claude-haiku-4.5) is a Claude-series text model on Router One. Posted rate: $0.30 in / $3.00 out per 1M tokens (was $1.00 in / $9.00 out). Router One subscriptions include Claude Haiku 4.5 in the Standard models allowance: Pro 5,000, Max 8,000, Ultra 25,000 requests per 30-day cycle. Usage beyond the allowance bills the wallet at posted rates. Context window: 200K tokens. Accepts text, image; returns text. Endpoints: POST /v1/chat/completions (OpenAI-compatible), POST /v1/messages (Anthropic-native, the Claude Code path).

Claude Haiku 4.5 FAQ

How much does Claude Haiku 4.5 cost on Router One?

Claude Haiku 4.5 is billed per token on Router One: $0.30 in / $3.00 out per 1M tokens, pay as you go.

Is Claude Haiku 4.5 included in Router One subscriptions?

Router One subscriptions include Claude Haiku 4.5 in the Standard models allowance: Pro 5,000, Max 8,000, Ultra 25,000 requests per 30-day cycle. Usage beyond the allowance bills the wallet at posted rates.

Which endpoints serve Claude Haiku 4.5?

Claude Haiku 4.5 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 Haiku 4.5's context window?

Claude Haiku 4.5 accepts up to 200K tokens of context per request on Router One.

Start using Claude Haiku 4.5

Create an API key and call Claude Haiku 4.5 at $0.30 in / $3.00 out per 1M tokens on Router One — pay as you go, with per-request cost and latency visibility.