Every cost belongs to a matter

Legal work is already organised around the matter: time is billed to one, disbursements are allocated to one, and cost that cannot be attributed to one is cost the firm absorbs. An LLM credential shared across review, summarisation and drafting produces exactly that — one monthly total with no matter attached to any part of it.

Try for free Read the docs

What a provider dashboard leaves you with

01
Document review across a large corpus is the single largest variable cost in the workflow, and it is invisible until invoiced.
02
Without per-matter attribution, agent spend cannot be passed through or recovered.
03
A run over the wrong document set is only discovered once it has finished paying for itself.

What Capsera does about it

Attribution per matter: The same mechanism that attributes spend to an end customer attributes it to a matter, so cost arrives already allocated.
A ceiling per run: A review run gets an envelope. Exceeding it stops the call rather than producing a larger invoice.
Sub-agents inherit identity: A graph composed at runtime stays attributable, because sub-agents take their parent's identity from an in-process context stack.

The number this is judged on

Spend per matter

None of this is assumed. We scanned 133 public agent repositories and found a cost defect in most of the ones making live model calls.

Read the method and limitations

import capsera
from anthropic import Anthropic
 
capsera.init(
    agent="reasoning_agent",
    run_id=ctx.run_id,
)
 
# checked before the call
capsera.budget(
    monthly=500,
    on_exceed="block",
)
 
with capsera.agent("summarizer"):
    client = Anthropic()
    resp = client.messages.create(
        model="claude-sonnet-4-6",
        max_tokens=1024,
    )
 
# no proxy, no gateway
assert resp.usage.cost < 0.02
 
if capsera.over_budget():
    raise BudgetExceeded()
 
@capsera.track()
def extract(doc):
    return chain(doc)
 
# cheaper route, same output
capsera.route(prefer="cost")

    on_exceed="block",
)
 
with capsera.agent("summarizer"):
    client = Anthropic()
    resp = client.messages.create(
        model="claude-sonnet-4-6",
        max_tokens=1024,
    )
 
# no proxy, no gateway
assert resp.usage.cost < 0.02
 
if capsera.over_budget():
    raise BudgetExceeded()
 
@capsera.track()
def extract(doc):
    return chain(doc)
 
# cheaper route, same output
capsera.route(prefer="cost")
 
spend = capsera.usage(
    group_by="agent",
    window="30d",
)
 
for a, cost in spend:
    print(a, f"${cost:.2f}")
 
# fails open, always
capsera.flush()

assert resp.usage.cost < 0.02
 
if capsera.over_budget():
    raise BudgetExceeded()
 
@capsera.track()
def extract(doc):
    return chain(doc)
 
# cheaper route, same output
capsera.route(prefer="cost")
 
spend = capsera.usage(
    group_by="agent",
    window="30d",
)
 
for a, cost in spend:
    print(a, f"${cost:.2f}")
 
# fails open, always
capsera.flush()
 
for task in queue:
    run(task)
 
log("run complete")
import capsera
from anthropic import Anthropic
 
capsera.init(
    agent="reasoning_agent",
    run_id=ctx.run_id,
)

 
spend = capsera.usage(
    group_by="agent",
    window="30d",
)
 
for a, cost in spend:
    print(a, f"${cost:.2f}")
 
# fails open, always
capsera.flush()
 
for task in queue:
    run(task)
 
log("run complete")
import capsera
from anthropic import Anthropic
 
capsera.init(
    agent="reasoning_agent",
    run_id=ctx.run_id,
)
 
# checked before the call
capsera.budget(
    monthly=500,
    on_exceed="block",
)
 
with capsera.agent("summarizer"):
    client = Anthropic()
    resp = client.messages.create(
        model="claude-sonnet-4-6",

 
for task in queue:
    run(task)
 
log("run complete")
import capsera
from anthropic import Anthropic
 
capsera.init(
    agent="reasoning_agent",
    run_id=ctx.run_id,
)
 
# checked before the call
capsera.budget(
    monthly=500,
    on_exceed="block",
)
 
with capsera.agent("summarizer"):
    client = Anthropic()
    resp = client.messages.create(
        model="claude-sonnet-4-6",
        max_tokens=1024,
    )
 
# no proxy, no gateway
assert resp.usage.cost < 0.02
 
if capsera.over_budget():
    raise BudgetExceeded()
 
@capsera.track()
def extract(doc):

)
 
# checked before the call
capsera.budget(
    monthly=500,
    on_exceed="block",
)
 
with capsera.agent("summarizer"):
    client = Anthropic()
    resp = client.messages.create(
        model="claude-sonnet-4-6",
        max_tokens=1024,
    )
 
# no proxy, no gateway
assert resp.usage.cost < 0.02
 
if capsera.over_budget():
    raise BudgetExceeded()
 
@capsera.track()
def extract(doc):
    return chain(doc)
 
# cheaper route, same output
capsera.route(prefer="cost")
 
spend = capsera.usage(
    group_by="agent",
    window="30d",
)
 
for a, cost in spend:

        model="claude-sonnet-4-6",
        max_tokens=1024,
    )
 
# no proxy, no gateway
assert resp.usage.cost < 0.02
 
if capsera.over_budget():
    raise BudgetExceeded()
 
@capsera.track()
def extract(doc):
    return chain(doc)
 
# cheaper route, same output
capsera.route(prefer="cost")
 
spend = capsera.usage(
    group_by="agent",
    window="30d",
)
 
for a, cost in spend:
    print(a, f"${cost:.2f}")
 
# fails open, always
capsera.flush()
 
for task in queue:
    run(task)
 
log("run complete")
import capsera
from anthropic import Anthropic

def extract(doc):
    return chain(doc)
 
# cheaper route, same output
capsera.route(prefer="cost")
 
spend = capsera.usage(
    group_by="agent",
    window="30d",
)
 
for a, cost in spend:
    print(a, f"${cost:.2f}")
 
# fails open, always
capsera.flush()
 
for task in queue:
    run(task)
 
log("run complete")
import capsera
from anthropic import Anthropic
 
capsera.init(
    agent="reasoning_agent",
    run_id=ctx.run_id,
)
 
# checked before the call
capsera.budget(
    monthly=500,
    on_exceed="block",
)

for a, cost in spend:
    print(a, f"${cost:.2f}")
 
# fails open, always
capsera.flush()
 
for task in queue:
    run(task)
 
log("run complete")
import capsera
from anthropic import Anthropic
 
capsera.init(
    agent="reasoning_agent",
    run_id=ctx.run_id,
)
 
# checked before the call
capsera.budget(
    monthly=500,
    on_exceed="block",
)
 
with capsera.agent("summarizer"):
    client = Anthropic()
    resp = client.messages.create(
        model="claude-sonnet-4-6",
        max_tokens=1024,
    )
 
# no proxy, no gateway
assert resp.usage.cost < 0.02

from anthropic import Anthropic
 
capsera.init(
    agent="reasoning_agent",
    run_id=ctx.run_id,
)
 
# checked before the call
capsera.budget(
    monthly=500,
    on_exceed="block",
)
 
with capsera.agent("summarizer"):
    client = Anthropic()
    resp = client.messages.create(
        model="claude-sonnet-4-6",
        max_tokens=1024,
    )
 
# no proxy, no gateway
assert resp.usage.cost < 0.02
 
if capsera.over_budget():
    raise BudgetExceeded()
 
@capsera.track()
def extract(doc):
    return chain(doc)
 
# cheaper route, same output
capsera.route(prefer="cost")
 
spend = capsera.usage(

)
 
with capsera.agent("summarizer"):
    client = Anthropic()
    resp = client.messages.create(
        model="claude-sonnet-4-6",
        max_tokens=1024,
    )
 
# no proxy, no gateway
assert resp.usage.cost < 0.02
 
if capsera.over_budget():
    raise BudgetExceeded()
 
@capsera.track()
def extract(doc):
    return chain(doc)
 
# cheaper route, same output
capsera.route(prefer="cost")
 
spend = capsera.usage(
    group_by="agent",
    window="30d",
)
 
for a, cost in spend:
    print(a, f"${cost:.2f}")
 
# fails open, always
capsera.flush()
 
for task in queue:

 
if capsera.over_budget():
    raise BudgetExceeded()
 
@capsera.track()
def extract(doc):
    return chain(doc)
 
# cheaper route, same output
capsera.route(prefer="cost")
 
spend = capsera.usage(
    group_by="agent",
    window="30d",
)
 
for a, cost in spend:
    print(a, f"${cost:.2f}")
 
# fails open, always
capsera.flush()
 
for task in queue:
    run(task)
 
log("run complete")
import capsera
from anthropic import Anthropic
 
capsera.init(
    agent="reasoning_agent",
    run_id=ctx.run_id,
)

import capsera
from anthropic import Anthropic
 
capsera.init(
    agent="reasoning_agent",
    run_id=ctx.run_id,
)
 
# checked before the call
capsera.budget(
    monthly=500,
    on_exceed="block",
)
 
with capsera.agent("summarizer"):
    client = Anthropic()
    resp = client.messages.create(
        model="claude-sonnet-4-6",
        max_tokens=1024,
    )
 
# no proxy, no gateway
assert resp.usage.cost < 0.02
 
if capsera.over_budget():
    raise BudgetExceeded()
 
@capsera.track()
def extract(doc):
    return chain(doc)
 
# cheaper route, same output
capsera.route(prefer="cost")

    on_exceed="block",
)
 
with capsera.agent("summarizer"):
    client = Anthropic()
    resp = client.messages.create(
        model="claude-sonnet-4-6",
        max_tokens=1024,
    )
 
# no proxy, no gateway
assert resp.usage.cost < 0.02
 
if capsera.over_budget():
    raise BudgetExceeded()
 
@capsera.track()
def extract(doc):
    return chain(doc)
 
# cheaper route, same output
capsera.route(prefer="cost")
 
spend = capsera.usage(
    group_by="agent",
    window="30d",
)
 
for a, cost in spend:
    print(a, f"${cost:.2f}")
 
# fails open, always
capsera.flush()

assert resp.usage.cost < 0.02
 
if capsera.over_budget():
    raise BudgetExceeded()
 
@capsera.track()
def extract(doc):
    return chain(doc)
 
# cheaper route, same output
capsera.route(prefer="cost")
 
spend = capsera.usage(
    group_by="agent",
    window="30d",
)
 
for a, cost in spend:
    print(a, f"${cost:.2f}")
 
# fails open, always
capsera.flush()
 
for task in queue:
    run(task)
 
log("run complete")
import capsera
from anthropic import Anthropic
 
capsera.init(
    agent="reasoning_agent",
    run_id=ctx.run_id,
)

 
spend = capsera.usage(
    group_by="agent",
    window="30d",
)
 
for a, cost in spend:
    print(a, f"${cost:.2f}")
 
# fails open, always
capsera.flush()
 
for task in queue:
    run(task)
 
log("run complete")
import capsera
from anthropic import Anthropic
 
capsera.init(
    agent="reasoning_agent",
    run_id=ctx.run_id,
)
 
# checked before the call
capsera.budget(
    monthly=500,
    on_exceed="block",
)
 
with capsera.agent("summarizer"):
    client = Anthropic()
    resp = client.messages.create(
        model="claude-sonnet-4-6",

 
for task in queue:
    run(task)
 
log("run complete")
import capsera
from anthropic import Anthropic
 
capsera.init(
    agent="reasoning_agent",
    run_id=ctx.run_id,
)
 
# checked before the call
capsera.budget(
    monthly=500,
    on_exceed="block",
)
 
with capsera.agent("summarizer"):
    client = Anthropic()
    resp = client.messages.create(
        model="claude-sonnet-4-6",
        max_tokens=1024,
    )
 
# no proxy, no gateway
assert resp.usage.cost < 0.02
 
if capsera.over_budget():
    raise BudgetExceeded()
 
@capsera.track()
def extract(doc):

)
 
# checked before the call
capsera.budget(
    monthly=500,
    on_exceed="block",
)
 
with capsera.agent("summarizer"):
    client = Anthropic()
    resp = client.messages.create(
        model="claude-sonnet-4-6",
        max_tokens=1024,
    )
 
# no proxy, no gateway
assert resp.usage.cost < 0.02
 
if capsera.over_budget():
    raise BudgetExceeded()
 
@capsera.track()
def extract(doc):
    return chain(doc)
 
# cheaper route, same output
capsera.route(prefer="cost")
 
spend = capsera.usage(
    group_by="agent",
    window="30d",
)
 
for a, cost in spend:

        model="claude-sonnet-4-6",
        max_tokens=1024,
    )
 
# no proxy, no gateway
assert resp.usage.cost < 0.02
 
if capsera.over_budget():
    raise BudgetExceeded()
 
@capsera.track()
def extract(doc):
    return chain(doc)
 
# cheaper route, same output
capsera.route(prefer="cost")
 
spend = capsera.usage(
    group_by="agent",
    window="30d",
)
 
for a, cost in spend:
    print(a, f"${cost:.2f}")
 
# fails open, always
capsera.flush()
 
for task in queue:
    run(task)
 
log("run complete")
import capsera
from anthropic import Anthropic

def extract(doc):
    return chain(doc)
 
# cheaper route, same output
capsera.route(prefer="cost")
 
spend = capsera.usage(
    group_by="agent",
    window="30d",
)
 
for a, cost in spend:
    print(a, f"${cost:.2f}")
 
# fails open, always
capsera.flush()
 
for task in queue:
    run(task)
 
log("run complete")
import capsera
from anthropic import Anthropic
 
capsera.init(
    agent="reasoning_agent",
    run_id=ctx.run_id,
)
 
# checked before the call
capsera.budget(
    monthly=500,
    on_exceed="block",
)

for a, cost in spend:
    print(a, f"${cost:.2f}")
 
# fails open, always
capsera.flush()
 
for task in queue:
    run(task)
 
log("run complete")
import capsera
from anthropic import Anthropic
 
capsera.init(
    agent="reasoning_agent",
    run_id=ctx.run_id,
)
 
# checked before the call
capsera.budget(
    monthly=500,
    on_exceed="block",
)
 
with capsera.agent("summarizer"):
    client = Anthropic()
    resp = client.messages.create(
        model="claude-sonnet-4-6",
        max_tokens=1024,
    )
 
# no proxy, no gateway
assert resp.usage.cost < 0.02

from anthropic import Anthropic
 
capsera.init(
    agent="reasoning_agent",
    run_id=ctx.run_id,
)
 
# checked before the call
capsera.budget(
    monthly=500,
    on_exceed="block",
)
 
with capsera.agent("summarizer"):
    client = Anthropic()
    resp = client.messages.create(
        model="claude-sonnet-4-6",
        max_tokens=1024,
    )
 
# no proxy, no gateway
assert resp.usage.cost < 0.02
 
if capsera.over_budget():
    raise BudgetExceeded()
 
@capsera.track()
def extract(doc):
    return chain(doc)
 
# cheaper route, same output
capsera.route(prefer="cost")
 
spend = capsera.usage(

)
 
with capsera.agent("summarizer"):
    client = Anthropic()
    resp = client.messages.create(
        model="claude-sonnet-4-6",
        max_tokens=1024,
    )
 
# no proxy, no gateway
assert resp.usage.cost < 0.02
 
if capsera.over_budget():
    raise BudgetExceeded()
 
@capsera.track()
def extract(doc):
    return chain(doc)
 
# cheaper route, same output
capsera.route(prefer="cost")
 
spend = capsera.usage(
    group_by="agent",
    window="30d",
)
 
for a, cost in spend:
    print(a, f"${cost:.2f}")
 
# fails open, always
capsera.flush()
 
for task in queue:

 
if capsera.over_budget():
    raise BudgetExceeded()
 
@capsera.track()
def extract(doc):
    return chain(doc)
 
# cheaper route, same output
capsera.route(prefer="cost")
 
spend = capsera.usage(
    group_by="agent",
    window="30d",
)
 
for a, cost in spend:
    print(a, f"${cost:.2f}")
 
# fails open, always
capsera.flush()
 
for task in queue:
    run(task)
 
log("run complete")
import capsera
from anthropic import Anthropic
 
capsera.init(
    agent="reasoning_agent",
    run_id=ctx.run_id,
)

import capsera
from anthropic import Anthropic
 
capsera.init(
    agent="reasoning_agent",
    run_id=ctx.run_id,
)
 
# checked before the call
capsera.budget(
    monthly=500,
    on_exceed="block",
)
 
with capsera.agent("summarizer"):
    client = Anthropic()
    resp = client.messages.create(
        model="claude-sonnet-4-6",
        max_tokens=1024,
    )
 
# no proxy, no gateway
assert resp.usage.cost < 0.02
 
if capsera.over_budget():
    raise BudgetExceeded()
 
@capsera.track()
def extract(doc):
    return chain(doc)
 
# cheaper route, same output
capsera.route(prefer="cost")

    on_exceed="block",
)
 
with capsera.agent("summarizer"):
    client = Anthropic()
    resp = client.messages.create(
        model="claude-sonnet-4-6",
        max_tokens=1024,
    )
 
# no proxy, no gateway
assert resp.usage.cost < 0.02
 
if capsera.over_budget():
    raise BudgetExceeded()
 
@capsera.track()
def extract(doc):
    return chain(doc)
 
# cheaper route, same output
capsera.route(prefer="cost")
 
spend = capsera.usage(
    group_by="agent",
    window="30d",
)
 
for a, cost in spend:
    print(a, f"${cost:.2f}")
 
# fails open, always
capsera.flush()

assert resp.usage.cost < 0.02
 
if capsera.over_budget():
    raise BudgetExceeded()
 
@capsera.track()
def extract(doc):
    return chain(doc)
 
# cheaper route, same output
capsera.route(prefer="cost")
 
spend = capsera.usage(
    group_by="agent",
    window="30d",
)
 
for a, cost in spend:
    print(a, f"${cost:.2f}")
 
# fails open, always
capsera.flush()
 
for task in queue:
    run(task)
 
log("run complete")
import capsera
from anthropic import Anthropic
 
capsera.init(
    agent="reasoning_agent",
    run_id=ctx.run_id,
)

 
spend = capsera.usage(
    group_by="agent",
    window="30d",
)
 
for a, cost in spend:
    print(a, f"${cost:.2f}")
 
# fails open, always
capsera.flush()
 
for task in queue:
    run(task)
 
log("run complete")
import capsera
from anthropic import Anthropic
 
capsera.init(
    agent="reasoning_agent",
    run_id=ctx.run_id,
)
 
# checked before the call
capsera.budget(
    monthly=500,
    on_exceed="block",
)
 
with capsera.agent("summarizer"):
    client = Anthropic()
    resp = client.messages.create(
        model="claude-sonnet-4-6",

 
for task in queue:
    run(task)
 
log("run complete")
import capsera
from anthropic import Anthropic
 
capsera.init(
    agent="reasoning_agent",
    run_id=ctx.run_id,
)
 
# checked before the call
capsera.budget(
    monthly=500,
    on_exceed="block",
)
 
with capsera.agent("summarizer"):
    client = Anthropic()
    resp = client.messages.create(
        model="claude-sonnet-4-6",
        max_tokens=1024,
    )
 
# no proxy, no gateway
assert resp.usage.cost < 0.02
 
if capsera.over_budget():
    raise BudgetExceeded()
 
@capsera.track()
def extract(doc):

)
 
# checked before the call
capsera.budget(
    monthly=500,
    on_exceed="block",
)
 
with capsera.agent("summarizer"):
    client = Anthropic()
    resp = client.messages.create(
        model="claude-sonnet-4-6",
        max_tokens=1024,
    )
 
# no proxy, no gateway
assert resp.usage.cost < 0.02
 
if capsera.over_budget():
    raise BudgetExceeded()
 
@capsera.track()
def extract(doc):
    return chain(doc)
 
# cheaper route, same output
capsera.route(prefer="cost")
 
spend = capsera.usage(
    group_by="agent",
    window="30d",
)
 
for a, cost in spend:

        model="claude-sonnet-4-6",
        max_tokens=1024,
    )
 
# no proxy, no gateway
assert resp.usage.cost < 0.02
 
if capsera.over_budget():
    raise BudgetExceeded()
 
@capsera.track()
def extract(doc):
    return chain(doc)
 
# cheaper route, same output
capsera.route(prefer="cost")
 
spend = capsera.usage(
    group_by="agent",
    window="30d",
)
 
for a, cost in spend:
    print(a, f"${cost:.2f}")
 
# fails open, always
capsera.flush()
 
for task in queue:
    run(task)
 
log("run complete")
import capsera
from anthropic import Anthropic

def extract(doc):
    return chain(doc)
 
# cheaper route, same output
capsera.route(prefer="cost")
 
spend = capsera.usage(
    group_by="agent",
    window="30d",
)
 
for a, cost in spend:
    print(a, f"${cost:.2f}")
 
# fails open, always
capsera.flush()
 
for task in queue:
    run(task)
 
log("run complete")
import capsera
from anthropic import Anthropic
 
capsera.init(
    agent="reasoning_agent",
    run_id=ctx.run_id,
)
 
# checked before the call
capsera.budget(
    monthly=500,
    on_exceed="block",
)

for a, cost in spend:
    print(a, f"${cost:.2f}")
 
# fails open, always
capsera.flush()
 
for task in queue:
    run(task)
 
log("run complete")
import capsera
from anthropic import Anthropic
 
capsera.init(
    agent="reasoning_agent",
    run_id=ctx.run_id,
)
 
# checked before the call
capsera.budget(
    monthly=500,
    on_exceed="block",
)
 
with capsera.agent("summarizer"):
    client = Anthropic()
    resp = client.messages.create(
        model="claude-sonnet-4-6",
        max_tokens=1024,
    )
 
# no proxy, no gateway
assert resp.usage.cost < 0.02

from anthropic import Anthropic
 
capsera.init(
    agent="reasoning_agent",
    run_id=ctx.run_id,
)
 
# checked before the call
capsera.budget(
    monthly=500,
    on_exceed="block",
)
 
with capsera.agent("summarizer"):
    client = Anthropic()
    resp = client.messages.create(
        model="claude-sonnet-4-6",
        max_tokens=1024,
    )
 
# no proxy, no gateway
assert resp.usage.cost < 0.02
 
if capsera.over_budget():
    raise BudgetExceeded()
 
@capsera.track()
def extract(doc):
    return chain(doc)
 
# cheaper route, same output
capsera.route(prefer="cost")
 
spend = capsera.usage(

)
 
with capsera.agent("summarizer"):
    client = Anthropic()
    resp = client.messages.create(
        model="claude-sonnet-4-6",
        max_tokens=1024,
    )
 
# no proxy, no gateway
assert resp.usage.cost < 0.02
 
if capsera.over_budget():
    raise BudgetExceeded()
 
@capsera.track()
def extract(doc):
    return chain(doc)
 
# cheaper route, same output
capsera.route(prefer="cost")
 
spend = capsera.usage(
    group_by="agent",
    window="30d",
)
 
for a, cost in spend:
    print(a, f"${cost:.2f}")
 
# fails open, always
capsera.flush()
 
for task in queue:

 
if capsera.over_budget():
    raise BudgetExceeded()
 
@capsera.track()
def extract(doc):
    return chain(doc)
 
# cheaper route, same output
capsera.route(prefer="cost")
 
spend = capsera.usage(
    group_by="agent",
    window="30d",
)
 
for a, cost in spend:
    print(a, f"${cost:.2f}")
 
# fails open, always
capsera.flush()
 
for task in queue:
    run(task)
 
log("run complete")
import capsera
from anthropic import Anthropic
 
capsera.init(
    agent="reasoning_agent",
    run_id=ctx.run_id,
)

Every call, on a matter.

Stop runaway agents before they become runaway invoices.

Try for free