DeepSeek V4 Pro
TL;DR
Open-sourceOpen-source hybrid-attention long-context reasoning.
Available on
Routed across multiple upstream providers; mean per-provider price.
Switch with
Pick DeepSeek V4 Pro from the selector.
Intelligence Index
V4 Pro vs siblings
DeepSeek V4 Pro
GLM-5
DeepSeek V4 Flash
Speed
~35
tokens / sec
Input
$1.74
per M tokens
Output
$3.48
per M tokens
DeepSeek V4 Pro in Command Code
DeepSeek V4 Pro uses hybrid attention for efficient long-context reasoning. In Command Code it matches Claude Sonnet 4.6 on Intelligence (52) at roughly half the input price — the open-source pick for repo-wide and multi-file work.
V4 Pro vs the Command Code lineup
Quality, speed, and pricing for V4 Pro alongside open-source peers and the premium reference.
| Model | Intelligence | Speed | Input $/M | Output $/M |
|---|---|---|---|---|
| DeepSeek V4 Pro | 52 | ~35 tok/s | $1.74 | $3.48 |
| DeepSeek V4 Flash | 47 | ~82 tok/s | $0.14 | $0.28 |
| Kimi K2.6 | 54 | ~40 tok/s | $0.95 | $4.00 |
| GLM-5 | 50 | ~61 tok/s | $1.00 | $3.20 |
| Claude Sonnet 4.6 | 52 | ~62 tok/s | $3.00 | $15.00 |
| GPT-5.3 Codex | 54 | ~72 tok/s | $2.00 | $8.00 |
What V4 Pro is best for
Repo-wide audits, multi-file refactors, and tasks where hybrid attention and long context pay off — at open-source prices.
When to switch away from V4 Pro
Switch to DeepSeek V4 Flash
For high-volume work where per-task cost dominates. Flash is much cheaper ($0.14/M input) and faster (~82 vs ~35 tok/s).
Switch to Kimi K2.6
For the top open-weights Intelligence Index (54).
Switch to Claude Sonnet 4.6
For the recommended Command Code default with strong prompt caching.
In Command Code: caching and taste-1
Open-source models are routed across multiple upstream providers for high availability. The price you see is the mean per-provider rate; the Usage page reflects what was actually charged.
Where supported by the upstream, prompt caching is on by default — cache reads are billed at $0.14 per million tokens versus $1.74 for fresh input.
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
Open-source model. Available on every plan, including Go ($1/mo). Routed across multiple upstream providers; listed price is the mean per-provider rate.
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 4.6 | 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 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.
| Plan | Price/mo | LLM credits | taste-1 usage | Models |
|---|---|---|---|---|
| Go | $1 | $10 | $100 | Open-source only |
| Pro | $15 | $30 | $500 | Open-source + premium |
| Max | $100 | $150 | $5,000 | Open-source + premium |
| Ultra | $200 | $300 | $10,000 | Open-source + premium |
| Teams | $40 / seat | Pooled | $1,000 | Open-source + premium |
| Enterprise | Custom | Custom | Custom | Custom pool, SSO, audit logs |
Frequently asked questions
V4 Pro or V4 Flash?
Pro for harder reasoning and long context (Intelligence 52 vs 47). Flash for fast, cost-efficient work at scale (~82 vs ~35 tok/s).
V4 Pro or Claude Sonnet 4.6?
Both score 52. V4 Pro costs about half on input ($1.74 vs $3.00). Sonnet runs faster and has stronger prompt caching.
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 DeepSeek V4 Pro 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.