Claude Sonnet 5
TL;DR
PremiumThe recommended default in Command Code for day-to-day coding.
Available on
Not on the Go plan ($1/mo, open-source models only).
Switch with
Pick Claude Sonnet 5 from the selector.
Input
$2
per M tokens
Output
$10
per M tokens
Cache read
$0.20
per M tokens
Claude Sonnet 5 in Command Code
Claude Sonnet 5 is the next generation of Anthropic's Sonnet family and a drop-in upgrade from Sonnet 4.6 at a lower introductory price. It is the best combination of speed and intelligence in the Claude line — the day-to-day workhorse — sitting below Claude Opus 4.8 (the most capable for long-horizon agentic coding) and above Claude Haiku 4.5 (the fastest, cheapest option). In Command Code it is the recommended default, with the 1M-token context window on by default.
Sonnet 5 vs the Command Code lineup
Pricing for Sonnet 5 alongside its closest relatives. Quality numbers shown where benchmarked; Sonnet 5 is not yet scored on the public Intelligence Index aggregate at launch.
| Model | Intelligence | Speed | Input $/M | Output $/M |
|---|---|---|---|---|
| Claude Sonnet 5 | Not yet scored | — | $2.00 | $10.00 |
| Claude Sonnet 4.6 | 52 | ~62 tok/s | $3.00 | $15.00 |
| Claude Opus 4.8 | Not yet scored | — | $5.00 | $25.00 |
| Claude Haiku 4.5 | 37 | ~97 tok/s | $1.00 | $5.00 |
| GPT-5.4 | 57 | ~84 tok/s | $2.50 | $15.00 |
What Sonnet 5 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 5
Switch to Claude Opus 4.8
When the task is reasoning-heavy: ambiguous specs, large multi-file refactors, or complex multi-step agent runs. Opus 4.8 is Anthropic's most capable model for agents and coding, at roughly 2.5× the input 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 and costs half the input price.
Switch to Claude Sonnet 4.6
If you have token budgets tuned to the previous tokenizer. Sonnet 5 uses a new tokenizer that produces about 30% more tokens for the same text.
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 $0.20 per million tokens versus $2.00 for fresh input.
Second, taste-1 sits between the model and the agent loop, rewriting and reranking candidate edits to match your codebase conventions.
Plan availability
Premium model. Available on Pro ($15/mo), Max 10× ($100/mo), Max 20× ($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.
| Model | Tier | Intelligence Index | Output speed |
|---|---|---|---|
| GPT-5.5 | Premium | 60 | ~65 tok/s |
| Claude Opus 4.7 | Premium | 57 | ~49 tok/s |
| GPT-5.4 | Premium | 57 | ~84 tok/s |
| GPT-5.3 Codex | Premium | 54 | ~72 tok/s |
| Kimi K2.6 | Open-source | 54 | ~40 tok/s |
| Claude Sonnet 4.6 | Premium | 52 | ~62 tok/s |
| DeepSeek V4 Pro | Open-source | 52 | ~35 tok/s |
| GLM-5 | Open-source | 50 | ~61 tok/s |
| GPT-5.4 Mini | Premium | 49 | ~164 tok/s |
| DeepSeek V4 Flash | Open-source | 47 | ~82 tok/s |
| Claude Haiku 4.5 | Premium | 37 | ~97 tok/s |
| Kimi K2.5 | Open-source | 37 | ~35 tok/s |
| Claude Sonnet 5 | Premium | Not yet scored | — |
| Claude Opus 4.8 | Premium | Not yet scored | — |
| Claude Opus 4.6 | Premium | Not yet scored | — |
| MiniMax M2.5 | Open-source | Not 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 modelPlans and pricing
Command Code is a subscription with model usage at API rates. Each plan ships with monthly LLM credits. Credits roll over and never expire. Auto top-up keeps you running if you go over.
| Plan | Price/mo | LLM credits | Models |
|---|---|---|---|
| Go | $1 | $10 | Open-source only |
| Pro | $15 | $30 | Open-source + premium |
| Max 10× | $100 | $150 | Open-source + premium |
| Max 20× | $200 | $300 | Open-source + premium |
| Teams | $40 / seat | Pooled | Open-source + premium |
| Enterprise | Custom | Custom | Custom pool, SSO, audit logs |
Frequently asked questions
Is Sonnet 5 the right default in Command Code?
For most users, yes. It is the best balance of quality and speed in the Claude family and a drop-in upgrade from Sonnet 4.6. Switch up to Opus 4.8 when reasoning quality matters more than cost, or down to Haiku 4.5 when latency wins.
How is Sonnet 5 priced?
Introductory pricing is $2 input / $10 output per million tokens through August 31, 2026. From September 1, 2026 standard pricing of $3 / $15 applies — the same rate as Sonnet 4.6.
Why is Sonnet 5 not on the Intelligence Index?
Public aggregate benchmarks have not yet been re-run for Sonnet 5 in the current Intelligence Index format. The model is available and routed normally.
What's new in Sonnet 5?
Sonnet 5 turns on adaptive thinking by default, no longer accepts manual extended thinking or non-default sampling parameters, and uses a new tokenizer that produces about 30% more tokens for the same text. Command Code handles these automatically.
Which Command Code model should I use?
For open models, Kimi, DeepSeek, Qwen, Mimo are all really good. For closed models, Claude Sonnet 5 is the recommended default — the best combination of speed and intelligence, and a drop-in upgrade from Sonnet 4.6. Switch to Claude Opus 4.8 (the newest Anthropic flagship) for the most capable long-horizon agentic coding, 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 5 with other models in a workflow?
Yes. Switch per session using /model. Common pattern: keep Sonnet 5 as the default and switch up to Opus 4.8 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. It covers open-source models only. Pro at $15/mo unlocks premium models with $30 in LLM credits.
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.