Nemotron 3.5 Super VL
nvidia/nemotron-3.5-super-vl
open vision-language model for coding and documents.
cmd --model nvidia/nemotron-3.5-super-vl
Intelligence index
not yet scored
Coding index
not yet scored
Input
$0.20 /M
Output
$0.50 /M
Cache read
$0.04 /M
Agent-loop cost
$0.09 /M in
Context window
262K tokens
Released
October 14, 2026
Modalities
→
vs. the lineup
Nemotron 3.5 Super VL beside its stablemates and nearest rivals. The ◆ marks the best value in each column across every row shown.
pin a rival:
| Model | Intelligence | Coding | Input $/M | Output $/M | Blended $/M | Context |
|---|---|---|---|---|---|---|
| Claude Haiku 5.5 | 43.4◆ | —◆ | $0.10◆ | $0.50◆ | $0.20◆ | 1M◆ |
| Nemotron 3 Ultra | 22.9◆ | 49.3◆ | $0.60◆ | $2.40◆ | $1.05◆ | 1M◆ |
| Claude Haiku 4.5 | 15.4◆ | —◆ | $1◆ | $5◆ | $2◆ | 200K◆ |
| Nemotron 3.5 Super VL ◆ | —◆ | —◆ | $0.20◆ | $0.50◆ | $0.28◆ | 262K◆ |
| DeepSeek V4 Pro (latest)pinned | 36◆ | 68.8◆ | $0.66◆ | $1.98◆ | $0.99◆ | 1M◆ |
| DeepSeek V4 Flash (latest)pinned | 34◆ | 69.1◆ | $0.15◆ | $0.60◆ | $0.26◆ | 1M◆ |
usage calculator
How far a month of credits goes on Nemotron 3.5 Super VL.
Input tokensfresh prompt
800Output tokensmodel reply
180Cache read tokensre-read context
50Kcost / request $0.0023 · in $0.20 · out $0.50 · cache $0.04 per M
fresh input 7%output 4%cache reads 89%
Requests / 30 days
2.7K
$6 credits ÷ $0.0023 per request
~533 quick fixes~107 bug fixes~18 feature PRs
what real work costs
Real coding tasks priced end to end on Nemotron 3.5 Super VL, from a quick lookup to a full-repo agent run.
One agent task
$0.02
180K in at 75% cache hit, 12K out
What you pay
$0.11 /M
all-in across every token that task touched
Sticker input
$0.20 /M
cache reads bill at $0.04 /M instead
| Task | Tokens in · out | Nemotron 3.5 Super VL | Claude Haiku 5.5 | Claude Haiku 4.5 |
|---|---|---|---|---|
| Quick lookup / one-liner | 8K · 1K | $0.0009 | $0.0007 | $0.0065 |
| Review a 500-line PR | 60K · 4K | $0.0073 | $0.0042 | $0.04 |
| Fix a bug (agent loop) | 180K · 12K | $0.02 | $0.01 | $0.12 |
| Refactor a module | 320K · 20K | $0.04 | $0.02 | $0.21 |
| Full-repo agent run | 900K · 45K | $0.09 | $0.05 | $0.49 |
frequently asked
How much does Nemotron 3.5 Super VL cost?
$0.20/M input and $0.50/M output, cache reads $0.04/M. In an agent loop most input is cache-read, so the effective input rate is about $0.09/M.Which plan do I need?
Available on Go and above.
How do I switch to it?
Run
cmd --model nvidia/nemotron-3.5-super-vl, or type /model in a session and pick it. You can switch mid-session without losing context.Ship code that matches your taste
Command Code is the AI coding agent that continuously learns your taste. Start for $1.
Benchmarks from Artificial Analysis (v4.3)commandcode.ai/models/nemotron-3-5-super-vl