Anthropic · checked October 13, 2026

How do I run Claude Sonnet 5.5 in Claude Code, OpenCode or Codex?

Q: How do I run Claude Sonnet 5.5 in Claude Code, OpenCode or Codex?

Claude Sonnet 5.5 runs on Standard Compute through https://api.stdcmpt.com/v1 with the model ID anthropic/claude-sonnet-5.5. The same key works in Claude Code, OpenCode and Codex.

Claude Sonnet 5.5 runs on Standard Compute through https://api.stdcmpt.com/v1 with the model ID anthropic/claude-sonnet-5.5. The same key works in Claude Code, OpenCode and Codex.

Model	Anthropic's mid-tier Claude 5.5 model, described by Anthropic as the best combination of speed and intelligence. It has a 1M-token context window, 128K max output and adaptive thinking.
Model ID	`anthropic/claude-sonnet-5.5` Short form `claude-sonnet-5.5` also works
Base URL	`https://api.stdcmpt.com/v1` Claude Code uses `https://api.stdcmpt.com`
Context	1M tokens; about 850K input and 50K output per request
Input	Text, images and files
Reasoning	low, medium, high, xhigh or max, set per model on the Models page

Copy a working config

Pick your agent and paste the config. In Claude Code, use the full ID: Claude Code's own sonnet shortcut means smart routing on Standard Compute.

terminal/v1/messages

# Install the Standard Compute launcher once
curl -fsSL https://standardcompute.com/cli/install.sh | sh

# Start Claude Code on your key, pinned to anthropic/claude-sonnet-5.5
standardcompute launch claude -- --model anthropic/claude-sonnet-5.5

# Or configure it yourself. No /v1 here: Claude Code adds /v1/messages.
export ANTHROPIC_BASE_URL=https://api.stdcmpt.com
export ANTHROPIC_AUTH_TOKEN=YOUR_API_KEY
export ANTHROPIC_MODEL=anthropic/claude-sonnet-5.5
claude

{
  "$schema": "https://opencode.ai/config.json",
  "model": "standardcompute/anthropic/claude-sonnet-5.5",
  "provider": {
    "standardcompute": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "Standard Compute",
      "options": {
        "baseURL": "https://api.stdcmpt.com/v1",
        "apiKey": "{env:STANDARDCOMPUTE_API_KEY}"
      },
      "models": {
        "anthropic/claude-sonnet-5.5": { "name": "Claude Sonnet 5.5" },
        "standardcompute": { "name": "Smart routing" }
      }
    }
  }
}

# Install Codex and the Standard Compute launcher once
npm install -g @openai/codex
curl -fsSL https://standardcompute.com/cli/install.sh | sh

# Start Codex pinned to anthropic/claude-sonnet-5.5
standardcompute launch codex -- --model anthropic/claude-sonnet-5.5

Replace YOUR_API_KEY with a key from the dashboard; OpenCode reads it from STANDARDCOMPUTE_API_KEY. Full setup: Claude Code, OpenCode, Codex CLI.

What it costs

Per 1M tokens	Sonnet 5.5	Sonnet 5
Input	$2.00	$2.00
Cache hit	$0.10	$0.20
5-minute cache write	$2.50	$2.50
Output	$10.00	$10.00

Anthropic standard API rates. Same headline price as Sonnet 5; the cache-hit rate is half. Source: Anthropic API pricing, checked October 13, 2026.

A 90K-token Claude Code turn on Sonnet 5.5

11,700 fresh input × $2.00/M$0.0234

78,300 cache hits × $0.10/M$0.0078

700 output × $10.00/M$0.0070

One turn$0.0382

Averages from coding-agent traffic on our gateway, Sep 13 to Oct 12, 2026: 87% of prompt tokens are cache hits and a turn returns about 700 tokens. Vendor list prices.

Agents mostly re-read a cached prompt, so the halved cache rate is where Sonnet 5.5 saves against Sonnet 5. The $19 Starter plan's $20 budget covers roughly 520 turns like this one.

What works differently here

Typing /model sonnet in Claude Code does not select Sonnet 5.5. Claude Code's short names (sonnet, opus, haiku) are treated as smart routing so old setups keep working. Use anthropic/claude-sonnet-5.5 to pin it.
Adding Sonnet 5.5 to the catalog did not change anyone's saved selection. If your Models page holds Sonnet 5, routed requests keep going to Sonnet 5 until you swap it.
The Messages endpoint ignores Claude Code's thinking setting and returns no thinking blocks; set the reasoning level under Customize on the Models page. A plan here is not a Claude Pro or Max subscription.

Other ways to run Claude Sonnet 5.5

Anthropic API $2 / $10 per 1M	First-party, pay per token. Batch requests are 50% off and prompt caching is yours to set up.
Claude Pro / Max Subscription	Claude Code's native login. Usage runs in session and weekly limits rather than a token bill.
Bedrock / Vertex / Foundry Pay per token	Cloud billing for procurement teams. On Bedrock the ID is anthropic.claude-sonnet-5-5.
Standard Compute Monthly plan	One key for Claude Code, Codex and OpenCode, drawing on a monthly compute budget.

FAQ

Why does /model sonnet not give me Sonnet 5.5?

On the Messages API, the names sonnet, opus and haiku (and older dated Claude IDs) mean smart routing, so existing Claude Code installs keep working. Pin Sonnet 5.5 with its full ID.

Sonnet 5 or Sonnet 5.5?

On Anthropic's list prices Sonnet 5.5 is never more expensive: the same $2 / $10 per million tokens, with cache hits at $0.10 instead of $0.20. For a cache-heavy coding agent that makes Sonnet 5.5 the more efficient default.

Sonnet 5.5 or Opus 5.5 for Claude Code?

Sonnet 5.5 for most sessions: Opus 5.5 costs twice as much per token ($4 / $20). Select both on the Models page and keep the model on standardcompute if you want hard requests to reach Opus automatically.

Plans from $19/mo

One key for Claude Sonnet 5.5 and the rest of the catalog, with a monthly compute budget you can watch in the dashboard and no overage charges.

Get your API key

Sources: Anthropic API pricing · Anthropic models overview
Related: Claude Sonnet 5 setup · Cheapest way to run Claude Code · All model IDs