theserverless.dev InferenceList

Models / Anthropic

Anthropic: Claude Opus 4.8

anthropic/claude-opus-4.8

text imageContext 1M

Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token...

Price

Input$5

per 1M tokens

Output$25

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 — $5/1M $25/1M 1M 100% Live openrouter-endpoints
Anthropic anthropic — $5/1M $25/1M 1M 100% Live openrouter-endpoints
AtlasCloud — fp8 $5/1M $25/1M 1M — Listed atlascloud
Azure azure/global — $5/1M $25/1M 1M — Live openrouter-endpoints
Claude Platform on AWS claude-on-aws — $5/1M $25/1M 1M 100% Live openrouter-endpoints
Google google-vertex/global — $5/1M $25/1M 1M 100% Live openrouter-endpoints
Phala — — $5/1M $25/1M 1M — Listed phala
Amazon Bedrock amazon-bedrock/eu-west-1 — $5.5/1M $27.5/1M 1M — Live openrouter-endpoints
Amazon Bedrock amazon-bedrock/us — $5.5/1M $27.5/1M 1M 100% Live openrouter-endpoints
Azure azure/us — $5.5/1M $27.5/1M 1M — Live openrouter-endpoints
Google google-vertex/europe — $5.5/1M $27.5/1M 1M — Live openrouter-endpoints
Google google-vertex/us — $5.5/1M $27.5/1M 1M — Live openrouter-endpoints
Anthropic anthropic/fast — $10/1M $50/1M 1M 100% Live openrouter-endpoints

Monthly bill

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

$30.00 at list price for this workload

Cache

Cache read$0.5

per 1M tokens

Cache write$6.25

per 1M tokens

1-hour cache write$10

per 1M tokens

Tiers

Web search
$0.01 per request
Every rate
UnitInputOutputFlatConfidence
token $5/1M $25/1M Not published— official

Price history

Anthropic: Claude Opus 4.8
30 0 2026-09-15: $52026-09-16: $52026-09-17: $52026-09-18: $52026-09-19: $52026-09-20: $52026-09-21: $52026-09-22: $52026-09-23: $52026-09-24: $52026-09-25: $52026-09-26: $52026-09-27: $52026-09-28: $52026-09-29: $52026-09-30: $52026-10-01: $52026-10-02: $52026-10-03: $52026-10-04: $52026-10-05: $52026-10-06: $52026-10-07: $52026-10-08: $52026-10-09: $52026-10-10: $52026-10-11: $52026-10-12: $52026-10-13: $52026-10-14: $52026-10-15: $52026-10-16: $52026-10-17: $52026-10-18: $52026-10-19: $52026-10-20: $52026-10-21: $52026-10-22: $52026-10-23: $52026-10-24: $52026-10-25: $52026-10-26: $52026-10-27: $52026-10-28: $52026-10-29: $52026-10-30: $5 2026-09-15 2026-10-30

input or flat output

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

Alternatives

Parameters (11)
include_reasoningmax_completion_tokensmax_tokensreasoningreasoning_effortresponse_formatstopstructured_outputstool_choicetoolsverbosity
Call this model

OpenRouter id anthropic/claude-opus-4.8. 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-opus-4.8","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-opus-4.8",
    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-opus-4.8", "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