Pricing
Usage based pricing or monthly plans to power your agents efficiently.
Model Prices
With runtime context compression, you'll use less tokens and save 50-80% per task vs. other inference providers.
| Model | Input | Output | Cached | Context window |
|---|---|---|---|---|
| GLM-5.3 Marathon Frontier coding and agentic work | $1.40 /1M | $4.40 /1M | $0.26 /1M | 5M |
| DeepSeek V4.1 Flash Marathon Multimodal & high-throughput | $0.30 /1M | $1.40 /1M | $0.007 /1M | 5M |
| Nemotron 3 Ultra | Available for dedicated deploymentContact us | |||
| Kimi K3 | Available for dedicated deploymentContact us | |||
Prices in USD per 1M tokens. With efficient caching, we see upwards of a 95% cache hit rate on agentic coding workloads, so most input tokens bill at the cached rate.
Pay 3.2× less than Opus 5.5,
and 2.9× less than standard GLM-5.3.
Standard inference vs. Subconscious with runtime context compression.
Less Tokens
More Tokens
ShortShort
MedMedium
LongLong
XLExtra long
MaxMax
50K
300K
750K
1.5M
5M
Opus 5.5
$89.11
GLM-5.3
$80.69
GLM-5.3 Marathon
$27.56
Effective context
750K tokens
Tokens billed
281.6M → 96.2M
Cost savings vs Opus
3.2× less
Cost savings vs standard GLM
2.9× less
Team Token Plans
Large monthly token budgets for you and your team, with 5x the usage. A $1,000 plan gets over $5,000 of inference a month at usage-based rates. Go past a day's usage and you move back to usage-based pricing.
Base
For teams putting agents into production
$1,000/ month
5x usage, every day
- Usage value
- $5,000+ / month
- Concurrent requests
- 100
- Rate limits
- Standard
- Every model on the API
- Works with Claude Code, Codex, OpenCode, or any OpenAI-compatible harness
Cancel any time
TeamMost popular
For engineering teams running agents all day
$5,000/ month
5x usage, every day
- Usage value
- $25,000+ / month
- Concurrent requests
- 500
- Rate limits
- Increased
- Everything in Base, at 5x the scale
- Increased rate limits
Cancel any time
Heavy
For organizations running agents at scale
$10,000/ month
5x usage, every day
- Usage value
- $50,000+ / month
- Concurrent requests
- 1,000
- Rate limits
- Increased
- Everything in Team, at 2x the scale
- Per-member API keys and a shared usage dashboard
- Direct line to our engineering team
Cancel any time
Custom
Larger budgets, dedicated capacity, or custom terms.
- One budget shared across your team and every model
- Usage resets daily at midnight UTC
- Past the day's usage, requests move to usage-based pricing
- Switch tiers or cancel at any time
Usage value is what the plan's daily usage would cost at our usage-based rates over a 30 day month, assuming a token mix of 98.2% cached, 1.6% input, and 0.2% output, typical of long-horizon agent tasks. Concurrent requests is how many calls can be in flight at once across your team; each agent holds one while it waits on the model.
5x the usage for the same budget
What a month of Team plan usage costs without the plan.
Subconscious Team plan
$5,000Flat monthly fee, shared across your team
Subconscious, pay per token
$25,787Billed per request
GLM-5.3 on other platforms
$51,574Identical list price, but without context compression
Claude Opus 5.5
$56,952Frontier list price
Assumes agentic coding traffic: 98.2% cached input, 1.6% uncached input, 0.2% output. Rows without context compression carry 2x the tokens for the same work, because the harness re-sends a conversation that grows with every step. Our GLM-5.3 rate is the same list price Z.ai publishes, so that row is the cost of compression alone, not a cheaper model.
Deploy in your cloud
Past a certain scale it is cheaper to own the serving. We install our inference system inside your VPC, on your GPUs, and charge a monthly fee per node instead of per token.
Half the GPUs, faster throughput, better capability, better economics
Our serving infrastructure runs more concurrent agents on the same hardware, so a node does the work that used to take two. You keep the savings, we charge a fraction of it, with hands-on setup by our team of world-class AI researchers.
On long tasks vs. standard inference providers:
- Concurrent workloads
2.3×
- Faster task completion
2x
- Higher accuracy
1-10%
- Effective context
5M+
We install in your cloud
Already running GPUs? We deploy our inference system directly onto the fleet you have today, and your team is serving open models in your own cloud within a week.
We get you the hardware first
No spare GPUs? We connect you to our compute partners or work with your cloud provider of choice, secure the lowest cost per GPU we can, then install and run the system for you.
Estimate your savings
GPU price, per hour
Deployment size, GPUs
Standard inference infrastructure
$186,880/mo
With Subconscious
$116,800/mo
50% the GPUs + our per GPU pricing*
You save
$70,080/mo
38% lower per month
* An estimate of our cost per node using our inference system, which covers everything we provide: our inference system, a routing gateway and supporting infrastructure, a frontend for API key management and usage monitoring, and dedicated setup and support from our team of world-class AI researchers.