theserverless.dev InferenceList

Models / Anthropic

Anthropic: Claude Haiku 4.5

anthropic/claude-haiku-4.5

text imageContext 200K

Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4’s performance...

Price

Input$1

per 1M tokens

Output$5

per 1M tokens

Compare this model

Providers

Each row is one seller. Prices are the published rate from that source. A dash means that source did not publish the amount. Sorted by a 3:1 blend of input and output.

ProviderTagQuant InputOutput ContextUptimeStatusSource
Amazon Bedrock amazon-bedrock/global — $1/1M $5/1M 200K 100% Live openrouter-endpoints
Anthropic anthropic — $1/1M $5/1M 200K 100% Live openrouter-endpoints
Azure azure/global — $1/1M $5/1M 200K 100% Live openrouter-endpoints
Google google-vertex/global — $1/1M $5/1M 200K 100% Live openrouter-endpoints
Phala — — $1/1M $5/1M 200K — Listed phala
Amazon Bedrock amazon-bedrock/eu-west-1 — $1.1/1M $5.5/1M 200K 100% Live openrouter-endpoints
Amazon Bedrock amazon-bedrock/us — $1.1/1M $5.5/1M 200K 100% Live openrouter-endpoints
Google google-vertex/europe — $1.1/1M $5.5/1M 200K 100% Live openrouter-endpoints
Google google-vertex/us-east5 — $1.1/1M $5.5/1M 200K — Live openrouter-endpoints

Monthly bill

Token models use the token counts. Image, video, and audio models use units times the flat rate.

$6.00 at list price for this workload

Cache

Cache read$0.1

per 1M tokens

Cache write$1.25

per 1M tokens

1-hour cache write$2

per 1M tokens

Tiers

Web search
$0.01 per request
Every rate
UnitInputOutputFlatConfidence
token $1/1M $5/1M Not published— official

Price history

Anthropic: Claude Haiku 4.5
5.5 0 2026-09-15: $12026-09-16: $12026-09-17: $12026-09-18: $12026-09-19: $12026-09-20: $12026-09-21: $12026-09-22: $12026-09-23: $12026-09-24: $12026-09-25: $12026-09-26: $12026-09-27: $12026-09-28: $12026-09-29: $12026-09-30: $12026-10-01: $12026-10-02: $12026-10-03: $12026-10-04: $12026-10-05: $12026-10-06: $12026-10-07: $12026-10-08: $12026-10-09: $12026-10-10: $12026-10-11: $12026-10-12: $12026-10-13: $12026-10-14: $12026-10-15: $12026-10-16: $12026-10-17: $12026-10-18: $12026-10-19: $12026-10-20: $12026-10-21: $12026-10-22: $12026-10-23: $12026-10-24: $12026-10-25: $12026-10-26: $12026-10-27: $12026-10-28: $12026-10-29: $12026-10-30: $1 2026-09-15 2026-10-30

input or flat output

Daily snapshots
UTC dateUnitInputOutputFlat
2026-09-15 token $1 $5 Not published—
2026-09-16 token $1 $5 Not published—
2026-09-17 token $1 $5 Not published—
2026-09-18 token $1 $5 Not published—
2026-09-19 token $1 $5 Not published—
2026-09-20 token $1 $5 Not published—
2026-09-21 token $1 $5 Not published—
2026-09-22 token $1 $5 Not published—
2026-09-23 token $1 $5 Not published—
2026-09-24 token $1 $5 Not published—
2026-09-25 token $1 $5 Not published—
2026-09-26 token $1 $5 Not published—
2026-09-27 token $1 $5 Not published—
2026-09-28 token $1 $5 Not published—
2026-09-29 token $1 $5 Not published—
2026-09-30 token $1 $5 Not published—
2026-10-01 token $1 $5 Not published—
2026-10-02 token $1 $5 Not published—
2026-10-03 token $1 $5 Not published—
2026-10-04 token $1 $5 Not published—
2026-10-05 token $1 $5 Not published—
2026-10-06 token $1 $5 Not published—
2026-10-07 token $1 $5 Not published—
2026-10-08 token $1 $5 Not published—
2026-10-09 token $1 $5 Not published—
2026-10-10 token $1 $5 Not published—
2026-10-11 token $1 $5 Not published—
2026-10-12 token $1 $5 Not published—
2026-10-13 token $1 $5 Not published—
2026-10-14 token $1 $5 Not published—
2026-10-15 token $1 $5 Not published—
2026-10-16 token $1 $5 Not published—
2026-10-17 token $1 $5 Not published—
2026-10-18 token $1 $5 Not published—
2026-10-19 token $1 $5 Not published—
2026-10-20 token $1 $5 Not published—
2026-10-21 token $1 $5 Not published—
2026-10-22 token $1 $5 Not published—
2026-10-23 token $1 $5 Not published—
2026-10-24 token $1 $5 Not published—
2026-10-25 token $1 $5 Not published—
2026-10-26 token $1 $5 Not published—
2026-10-27 token $1 $5 Not published—
2026-10-28 token $1 $5 Not published—
2026-10-29 token $1 $5 Not published—
2026-10-30 token $1 $5 Not published—

Alternatives

Parameters (12)
include_reasoningmax_completion_tokensmax_tokensreasoningresponse_formatstopstructured_outputstemperaturetool_choicetoolstop_ktop_p
Call this model

OpenRouter id anthropic/claude-haiku-4.5. InferenceList does not send the request.

curl
curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"anthropic/claude-haiku-4.5","messages":[{"role":"user","content":"Hello"}]}'

JavaScript
await fetch("https://openrouter.ai/api/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: "Bearer " + process.env.OPENROUTER_API_KEY,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "anthropic/claude-haiku-4.5",
    messages: [{ role: "user", content: "Hello" }],
  }),
});

Python
import os, json, urllib.request
req = urllib.request.Request(
    "https://openrouter.ai/api/v1/chat/completions",
    data=json.dumps({"model": "anthropic/claude-haiku-4.5", "messages": [{"role": "user", "content": "Hello"}]}).encode(),
    headers={"Authorization": "Bearer " + os.environ["OPENROUTER_API_KEY"], "Content-Type": "application/json"},
)
print(urllib.request.urlopen(req).read().decode())

JSON · History JSON