Claude API Gateway: Models, Pricing & Code

Use one Anthropic Messages-compatible integration for all eight Claude models available through APIXO. Configure the APIXO base URL and API key once, then switch models by changing only the model value.

This page includes the complete APIXO Claude model and pricing snapshot verified on August 3, 2026. Model availability and pricing can change, so check the APIXO Claude model page before making billing-sensitive decisions.

Choose your integration path: Use the Quickstart to integrate manually, or let an AI implement it by copying this page or using APIXO MCP.

Compare Claude models and pricing

Choose the model that fits the workload, then use its exact model ID in any example on this page.

Model	Model ID	Recommended for	Input	Output	Cache write	Cache read	Savings
Claude Opus 4.8	`claude-opus-4-8`	Latest Opus model for the most demanding reasoning, coding, and agentic work	$3	$15	$3.75	$0.3	40%
Claude Opus 4.7	`claude-opus-4-7`	High-capability Opus workloads that already target the 4.7 model	$3	$15	$3.75	$0.3	40%
Claude Opus 4.6	`claude-opus-4-6`	Existing complex reasoning and coding integrations on Opus 4.6	$3	$15	$3.75	$0.3	40%
Claude Opus 4.5 20251101	`claude-opus-4-5-20251101`	Version-pinned Opus 4.5 integrations	$3	$15	$3.75	$0.3	40%
Claude Sonnet 4.6	`claude-sonnet-4-6`	Balanced capability and cost for everyday professional and coding work	$1.8	$9	$2.25	$0.18	40%
Claude Sonnet 4.5	`claude-sonnet-4-5`	Existing Sonnet 4.5 integrations that do not need a dated model ID	$1.8	$9	$2.25	$0.18	40%
Claude Sonnet 4.5 20250929	`claude-sonnet-4-5-20250929`	Version-pinned Sonnet 4.5 integrations	$1.8	$9	$2.25	$0.18	40%
Claude Haiku 4.5 20251001	`claude-haiku-4-5-20251001`	Cost-sensitive, low-latency, and higher-volume Claude workloads	$0.6	$3	$0.75	$0.06	40%

Prices are in USD per 1 million tokens. Prices verified: 2026-08-03. See the APIXO Claude model page for the current rate card.

Start with Claude Opus 4.8 when capability matters most, Claude Sonnet 4.6 for a balanced default, or Claude Haiku 4.5 for lower-cost, higher-volume work. Keep an older or dated ID when your application intentionally pins that model.

What to change

Setting	APIXO value
SDK Base URL	`https://llm.apixo.ai`
Raw HTTP path	`POST /v1/messages`
Request URL	`https://llm.apixo.ai/v1/messages`
API key	`APIXO_API_KEY` from APIXO API Keys
API key header	`x-api-key`
API key value	`$APIXO_API_KEY`
Required version header	`anthropic-version: 2023-06-01`
Model location	Request body `model`

2023-06-01 is the current Anthropic Messages API protocol version, not a Claude model release date. Keep this required header in raw HTTP requests. The Anthropic SDK adds it automatically.

Quickstart

export APIXO_API_KEY="your_apixo_api_key"

cURL
JavaScript
Python

curl -X POST "https://llm.apixo.ai/v1/messages" \
  -H "x-api-key: $APIXO_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-opus-4-8",
    "max_tokens": 256,
    "messages": [
      {"role": "user", "content": "Say hello in one sentence."}
    ]
  }'

import Anthropic from "@anthropic-ai/sdk";

const client = new Anthropic({
  apiKey: process.env.APIXO_API_KEY,
  baseURL: "https://llm.apixo.ai"
});

const message = await client.messages.create({
  model: "claude-opus-4-8",
  max_tokens: 256,
  messages: [{ role: "user", content: "Say hello in one sentence." }]
});

console.log(message.content);

import os
from anthropic import Anthropic

client = Anthropic(
    api_key=os.environ["APIXO_API_KEY"],
    base_url="https://llm.apixo.ai",
)

message = client.messages.create(
    model="claude-opus-4-8",
    max_tokens=256,
    messages=[{"role": "user", "content": "Say hello in one sentence."}],
)

print(message.content)

The examples use claude-opus-4-8. To use any other model in the comparison table, change only the model value.

Let an AI implement it

Copy this page to an AI

Use the Copy page button in the page menu, paste the copied documentation into your AI coding tool, and add this prompt:

Integrate the APIXO Anthropic-compatible Messages API into my existing project
using the documentation below.

Requirements:
- Use model claude-opus-4-8 unless my project already specifies another supported model.
- Read APIXO_API_KEY from an environment variable and keep it server-side.
- Preserve my current language, framework, and project structure.
- Add the smallest working integration and one minimal verification request.
- Do not invent endpoints, model IDs, or request fields that are not documented.

Replace claude-opus-4-8 in the prompt with any model ID from the comparison table.

Use APIXO MCP

APIXO MCP reads APIXO’s published machine-readable model catalog and schemas. The claude schema includes the gateway endpoint, required headers, supported model IDs, model guidance, and the pricing snapshot shown above. After installing APIXO MCP, ask your AI:

Use the APIXO MCP tools to find the claude model schema. Compare the supported
Claude models and prices, choose the best model for my stated workload, then
integrate the APIXO Anthropic-compatible Messages API into this project. Keep
the API key server-side and add a minimal verification request.

APIXO MCP helps your AI write the integration; it does not replace the API connection used by your application.

Streaming

curl -N -X POST "https://llm.apixo.ai/v1/messages" \
  -H "x-api-key: $APIXO_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-opus-4-8",
    "stream": true,
    "max_tokens": 256,
    "messages": [
      {"role": "user", "content": "Write a short release note."}
    ]
  }'

Supported Claude models

Use one of these exact IDs in the request body model field.

claude-opus-4-8
claude-opus-4-7
claude-opus-4-6
claude-opus-4-5-20251101
claude-sonnet-4-6
claude-sonnet-4-5
claude-sonnet-4-5-20250929
claude-haiku-4-5-20251001

To switch models, keep the same endpoint, API key, headers, and request format, then change only model.

Troubleshooting

401: missing or invalid API key
400: invalid Messages API request body, unsupported model ID, missing max_tokens, or missing anthropic-version
429: rate limit or temporary capacity limit
502 / 504: upstream provider error or timeout

Retry 429, 502, and 504 with backoff. Fix 400 and 401 before retrying.

Open a model on APIXO

These links open the selected model on APIXO’s Claude gateway page, where you can review its current pricing and copy model-specific code examples.

​Compare Claude models and pricing

​What to change

​Quickstart

​Let an AI implement it

​Copy this page to an AI

​Use APIXO MCP

​Streaming

​Supported Claude models

​Troubleshooting

​Related links

​Open a model on APIXO

Compare Claude models and pricing

What to change

Quickstart

Let an AI implement it

Copy this page to an AI

Use APIXO MCP

Streaming

Supported Claude models

Troubleshooting

Related links

Open a model on APIXO