Models

Claude Sonnet 4.6

TL;DR

Premium

The recommended default in Command Code for day-to-day coding.

Available on

ProMaxUltraTeamsEnterprise

Not on the Go plan ($1/mo, open-source models only).

Switch with

/model

Pick Claude Sonnet 4.6 from the selector.

Intelligence Index

Sonnet 4.6 vs the Claude 4 family

52

Opus 4.7

57

Sonnet 4.6

52

Haiku 4.5

37

Speed

~62

tokens / sec

Input

$3

per M tokens

Output

$15

per M tokens

Claude Sonnet 4.6 in Command Code

Claude Sonnet 4.6 is the mid-tier model in Anthropic's Claude 4 family. It sits between Claude Opus 4.7 (the most intelligent Claude for agents and coding) and Claude Haiku 4.5 (the fastest, cheapest option), and is positioned as the day-to-day workhorse. In Command Code it is the recommended default — strong enough for most tasks without paying Opus prices on every step.

Sonnet 4.6 vs the Command Code lineup

Quality (Intelligence Index), output speed, and per-million-token pricing for Sonnet 4.6 alongside the most relevant alternatives.

ModelIntelligenceSpeedInput $/MOutput $/M
Claude Sonnet 4.652~62 tok/s$3.00$15.00
Claude Opus 4.757~49 tok/s$5.00$25.00
Claude Haiku 4.537~97 tok/s$1.00$5.00
GPT-5.457~84 tok/s$2.50$15.00
GPT-5.3 Codex54~72 tok/s$2.00$8.00
DeepSeek V4 Pro52~35 tok/s$1.74$3.48
Kimi K2.654~40 tok/s$0.95$4.00

What Sonnet 4.6 is best for

Feature work, bug fixes, medium refactors, test writing, and code review — the everyday coding tasks that make up most Command Code sessions.

When to switch away from Sonnet 4.6

Switch to Claude Opus 4.7

When the task is reasoning-heavy: ambiguous specs, large multi-file refactors, or complex multi-step agent runs. Opus 4.7 scores 57 versus Sonnet's 52, at roughly 1.7× the price.

Switch to Claude Haiku 4.5

For quick lookups, small edits, or high-volume mechanical work where latency dominates value. Haiku runs at ~97 tok/s vs Sonnet at ~62, and costs a third of the input price.

Switch to GPT-5.4

When you want a second opinion or prefer the OpenAI side. GPT-5.4 ties Opus at 57 and runs faster than Sonnet at ~84 tok/s, with a slightly lower input price.

Switch to DeepSeek V4 Pro

For cost-sensitive work that still needs strong reasoning. V4 Pro matches Sonnet at 52 and costs about half on input ($1.74 vs $3.00). Available on every plan including Go.

In Command Code: caching and taste-1

Two things change the experience of using this model inside Command Code versus calling it directly through the upstream API.

First, prompt caching is on by default. In an agent loop the same context is read across many steps; cache reads are billed at $0.30 per million tokens versus $3.00 for fresh input.

Second, taste-1 sits between the model and the agent loop, rewriting and reranking candidate edits to match your codebase conventions. Each plan ships with a taste-1 usage allowance that scales by tier (Go $100 → Ultra $10,000).

Plan availability

Premium model. Available on Pro ($15/mo), Max ($100/mo), Ultra ($200/mo), Teams ($40/mo per seat), and Enterprise. Not on the Go plan.

All Command Code models, ranked by quality and speed

Quality is the Intelligence Index — an aggregate score across reasoning, math, coding, and knowledge evaluations. Speed is reported output tokens per second. Models without a published score are noted.

ModelTierIntelligence IndexOutput speed
GPT-5.5Premium60~65 tok/s
Claude Opus 4.7Premium57~49 tok/s
GPT-5.4Premium57~84 tok/s
GPT-5.3 CodexPremium54~72 tok/s
Kimi K2.6Open-source54~40 tok/s
Claude Sonnet 4.6Premium52~62 tok/s
DeepSeek V4 ProOpen-source52~35 tok/s
GLM-5Open-source50~61 tok/s
GPT-5.4 MiniPremium49~164 tok/s
DeepSeek V4 FlashOpen-source47~82 tok/s
Claude Haiku 4.5Premium37~97 tok/s
Kimi K2.5Open-source37~35 tok/s
Claude Opus 4.6PremiumNot yet scored
MiniMax M2.5Open-sourceNot yet scored

Switching models with /model

In an interactive Command Code session, run /model to open the model selector. Pick the model you want and it applies to this session and to future sessions until you change it again. Premium models require Pro or higher; open-source models are available on every plan, including Go.

cmd               # start an interactive session
/model            # open the selector and pick a model

Plans and pricing

Command Code is a subscription with model usage at API rates. Each plan ships with monthly LLM credits and a separate taste-1 usage allowance that scales by tier. Credits roll over and never expire. Auto top-up keeps you running if you go over.

PlanPrice/moLLM creditstaste-1 usageModels
Go$1$10$100Open-source only
Pro$15$30$500Open-source + premium
Max$100$150$5,000Open-source + premium
Ultra$200$300$10,000Open-source + premium
Teams$40 / seatPooled$1,000Open-source + premium
EnterpriseCustomCustomCustomCustom pool, SSO, audit logs

Frequently asked questions

Is Sonnet 4.6 the right default in Command Code?

For most users, yes. It is the strongest balance of quality and speed in the Claude family. Switch up to Opus 4.7 when reasoning quality matters more than cost, or down to Haiku 4.5 when latency wins.

How does Sonnet 4.6 compare to Claude Opus 4.7?

Opus 4.7 scores 57 versus Sonnet 4.6 at 52, at roughly 1.7× the price ($5 vs $3 input, $25 vs $15 output). Sonnet runs faster (~62 vs ~49 tok/s). For most everyday work, Sonnet is the better cost-quality trade.

How does Sonnet 4.6 compare to GPT-5.4?

GPT-5.4 scores higher (57 vs 52) and runs faster (~84 vs ~62 tok/s) at a slightly lower input price ($2.50 vs $3.00). Sonnet 4.6 has stronger prompt caching that Command Code activates automatically.

Which Command Code model should I use?

Claude Sonnet 4.6 is the recommended default. Switch to GPT-5.5 (Intelligence Index 60) for the absolute hardest reasoning, or Claude Opus 4.7 / GPT-5.4 (both 57) for top-tier work at lower cost. For fast lookups, Claude Haiku 4.5 or GPT-5.4 Mini. For open-source, Kimi K2.6 leads the open-weights tier (Intelligence Index 54).

Can I mix Claude Sonnet 4.6 with other models in a workflow?

Yes. Switch per session using /model. Common pattern: keep Sonnet 4.6 as the default and switch up to Opus 4.7 or down to Haiku 4.5 as the task calls for it.

Are open-source model prices fixed?

Open-source models are routed across multiple upstream providers for high availability. The price listed for each is the mean per-provider rate. Actual cost on a given request may vary slightly. The Usage page reflects the price charged.

Is Command Code free to try?

The Go plan starts at $1/mo with $10 in LLM credits and $100 of taste-1 usage. It covers open-source models only. Pro at $15/mo unlocks premium models with $30 in LLM credits and $500 of taste-1 usage.

Does Command Code train on my code?

No. Command Code does not train on your code or store your code snippets. taste-1 data is stored locally in your project directory.

Where can I track my usage?

The Usage page in Studio shows per-request cost, token counts, and which model ran. Settings > Billing lets you change plans, buy credits, or enable auto top-up.

Does Command Code replace my editor?

No. Command Code is editor-agnostic — it runs as a CLI and works alongside any editor (Cursor, VS Code, Zed, JetBrains, Neovim, etc.).

Ship code that matches your taste

Command Code is the AI coding agent that continuously learns your taste. Start for $1.