Claude Opus 4.8
TL;DR
PremiumAnthropic's most capable model for complex reasoning and long-horizon agentic coding.
Available on
Not on the Go plan ($1/mo, open-source models only).
Switch with
Pick Claude Opus 4.8 from the selector.
Input
$5
per M tokens
Output
$25
per M tokens
Cache read
$0.50
per M tokens
Claude Opus 4.8 in Command Code
Claude Opus 4.8 is Anthropic's newest flagship — the most capable Claude for complex reasoning, long-horizon agentic coding, and high-autonomy work. It builds on Opus 4.7 with better long-context handling, fewer compactions, more reliable tool triggering, and adaptive thinking that reasons only when the turn needs it. Same Opus-tier pricing as 4.7, with the 1M-token context window on by default.
Opus 4.8 vs the Command Code lineup
Pricing for Opus 4.8 alongside its closest relatives. Quality numbers shown where benchmarked.
| Model | Intelligence | Speed | Input $/M | Output $/M |
|---|---|---|---|---|
| Claude Opus 4.8 | Not yet scored | — | $5.00 | $25.00 |
| Claude Opus 4.7 | 57 | ~49 tok/s | $5.00 | $25.00 |
| GPT-5.5 | 60 | ~65 tok/s | $5.00 | $30.00 |
| GPT-5.4 | 57 | ~84 tok/s | $2.50 | $15.00 |
| Claude Sonnet 4.6 | 52 | ~62 tok/s | $3.00 | $15.00 |
| Kimi K2.6 | 54 | ~40 tok/s | $0.95 | $4.00 |
What Opus 4.8 is best for
Long-horizon agentic coding, large multi-file refactors, ambiguous specs that need pushback, complex multi-step agent runs, and high-autonomy work where reasoning quality matters most.
When to switch away from Opus 4.8
Switch to Claude Sonnet 4.6
For everyday work where Sonnet is the better cost-quality trade. Most users keep Sonnet as the default and only switch up to Opus when the task calls for it.
Switch to Claude Opus 4.7
For teams that have already validated 4.7 against their codebase and want that baseline. Same Opus-tier price.
Switch to GPT-5.5
For the highest published Intelligence Index (60) or a second opinion on the OpenAI side.
Switch to Claude Haiku 4.5
For quick lookups, small edits, or high-volume mechanical work. Haiku runs ~97 tok/s.
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 $0.50 per million tokens versus $5.00 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 ($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.
| 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 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 | $100 | $150 | Open-source + premium |
| Ultra | $200 | $300 | Open-source + premium |
| Teams | $40 / seat | Pooled | Open-source + premium |
| Enterprise | Custom | Custom | Custom pool, SSO, audit logs |
Frequently asked questions
Should I use Opus 4.8 or Opus 4.7?
4.8 is the newest flagship and the most capable Claude for agents and coding, at the same Opus-tier price as 4.7. 4.7 remains a strong, stable baseline — switch with /model per task.
Why is Opus 4.8 not on the Intelligence Index?
Public aggregate benchmarks have not yet been re-run for 4.8 in the current Intelligence Index format. The model is available and routed normally.
What's new in Opus 4.8?
Compared with Opus 4.7: better long-horizon agentic coding with fewer compactions and better compaction recovery, more reliable reasoning-effort calibration, and fewer cases of skipping a required tool call. Adaptive thinking triggers reasoning only when the turn needs it.
Which Command Code model should I use?
For open models, Kimi, DeepSeek, Qwen, Mimo are all really good. For closed models,Claude Sonnet 4.6 is the recommended default. 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 Opus 4.8 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 4.8 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.