AI Calculator Pro
Agentic setups

Which model for each step of your agent

Everyone publishes “the best model for coding”. Almost nobody publishes the thing people actually build: a workflow with several steps, a different model on each, and what one run costs. A planner called once and an implementer called twelve times have almost nothing in common — but most agents run both on whatever model the team picked first.

Below are four setups with the model each step should use, and the same workflow priced with one frontier model doing everything. Every figure is computed from today’s prices at the cheapest major provider — nothing here is hand-written.

Coding agent

Plan once with a frontier model, implement and review with cheaper ones.

The shape almost every coding agent converges on. Planning is one expensive call where being wrong is costly, so it gets a frontier model. Implementation is dozens of calls where a good mid-tier coding model is indistinguishable in the diff, and the final summary is nearly free. Running all four steps on the planner's model is the version most people ship by accident.

$0.0984
per run, right model per step
$1.60
per run, all on Claude Opus 5
94%
$196.89 vs $3,210.00 per month at 2,000 runs
StepNeedsModelArenaCalls$ / run
Plan the change
Read the task and the relevant code, decide the approach and the files to touch.
Agentic / tool use1394
tools · reasoning · 200K ctx
One call, and every later step inherits its mistakes. This is where frontier quality is worth paying for — and it needs a big context window to hold the code it is reasoning about.
Gemini 2.5 Pro
Google · 9 qualified
14251$0.0575
Write the code
Produce the actual edits, one call per file or hunk.
Coding1478
tools
The bulk of the spend — twelve calls against the planner's one. A competent coding model produces the same diff here, so this is the step where the cheaper choice actually pays.
DeepSeek V4 Flash
via OpenRouter · 36 qualified
157912$0.0144
Review the diff
Check the changes against the plan and flag mistakes before a human sees them.
Coding1545
reasoning
Catching a bad edit is cheaper than shipping it, so the bar is higher than for writing — but it is only a couple of calls, so the price barely moves.
GLM-5.2
via DeepInfra · 4 qualified
15872$0.0265
Summarise for the human
Write the PR description and what changed.
Overall1053
Prose from a diff. Almost any model does this well, and paying frontier rates for it is pure waste.
Llama 3.2 1B Instruct
Meta · 177 qualified
10551$0.00007

Research agent

Cheap fan-out for gathering, one strong model for the synthesis.

Research inverts the coding shape: the many calls come first. Fetching and extracting from twenty sources is high-volume, low-judgement work, while the synthesis at the end is a single call that determines whether the output is worth reading. Spending frontier money on extraction is the classic mistake here.

$0.0310
per run, right model per step
$2.66
per run, all on Claude Opus 5
99%
$30.98 vs $2,655.00 per month at 1,000 runs
StepNeedsModelArenaCalls$ / run
Decide what to look for
Turn the question into concrete sub-questions and search targets.
Agentic / tool use1336
tools · reasoning
Cheap in tokens but sets the direction, so it is worth a capable model.
DeepSeek V4 Pro
DeepSeek · 17 qualified
13801$0.00157
Read and extract
Pull the relevant facts out of each fetched source.
Overall1128
128K ctx
Twenty calls over long documents — by far the largest token bill. This is mechanical extraction, so it needs context length far more than it needs intelligence.
GPT OSS 20B
OpenAI · 165 qualified
128820$0.00940
Write the answer
Reconcile the extracts, resolve contradictions, produce the output.
Overall1444
reasoning · 200K ctx
The only step a reader actually sees, and the one that has to notice when two sources disagree. Frontier quality, once.
MiMo-V2.5-Pro
Xiaomi · 11 qualified
14651$0.0200

Document processing pipeline

Classify cheaply at volume, extract carefully only where it matters.

A high-volume back-office shape: thousands of documents in, structured data out. The trick is that most documents need almost nothing done to them. Classifying first with a cheap model, then spending real money only on the ones that need extraction, is the difference between a viable pipeline and an unaffordable one.

$0.00066
per run, right model per step
$0.0872
per run, all on Claude Opus 5
99%
$33.07 vs $4,362.50 per month at 50,000 runs
StepNeedsModelArenaCalls$ / run
Classify the document
Decide what kind of document this is and whether it needs full extraction.
Overall978
Runs on every single document, so unit price dominates everything else. A short label from a cheap model is all this needs.
Llama 3.2 1B Instruct
Meta · 177 qualified
10551$0.00003
Extract the fields
Pull structured fields out of the documents that warrant it.
Overall1324
tools
Getting a field wrong is expensive downstream, so the bar rises — but tool use for schema-shaped output matters more here than raw intelligence.
GPT OSS 120B
OpenAI · 142 qualified
13661$0.00042
Verify the doubtful ones
Re-check extractions that look inconsistent or incomplete.
Overall1429
reasoning
Only about one document in seven reaches this step, which is what makes a frontier model affordable at fifty thousand runs a month.
Hunyuan Hy3
via OpenRouter · 16 qualified
144115%$0.00021

Customer support triage

Route everything cheaply; answer well only when a human isn't taking over.

The highest-volume shape of the four, and the most sensitive to unit price. Every incoming message gets classified; only a fraction get a drafted answer. The economics live entirely in keeping the per-message step cheap.

$0.00025
per run, right model per step
$0.0481
per run, all on Claude Opus 5
99%
$49.01 vs $9,625.00 per month at 200,000 runs
StepNeedsModelArenaCalls$ / run
Triage the message
Categorise, detect urgency and decide whether a human is needed.
Overall978
Two hundred thousand calls a month. A cent of difference per call is two thousand dollars, so this step is chosen on price almost alone.
Llama 3.2 1B Instruct
Meta · 177 qualified
10551$0.00001
Draft the reply
Write a grounded answer using the knowledge base.
Overall1354
tools · 128K ctx
The customer reads this, so quality matters — but only about 40% of messages get an automated reply at all, which keeps the cost of a better model in reach.
Qwen3.5 Flash
Alibaba · 121 qualified
139840%$0.00022
Summarise for escalation
Hand a human the context they need without making them read the thread.
Overall1053
Internal-facing prose on a small share of messages. Cheap is fine.
Llama 3.2 1B Instruct
Meta · 177 qualified
105515%$0.00001

Token costs only, at today’s prices, for the token volumes and call counts shown — a fractional call count means only that share of runs reaches the step. Excluded: your infrastructure, vector storage, the tool and API calls the agent makes, and retries. Arena scores are shown so you can see what each cheaper step trades away; the top overall score we track is 1504. The quality bar per step is our judgement, not a measurement — it is printed on every row so you can substitute your own.

Intelligence scores are community Arena ratings from LMArena / arena.ai, used under CC BY 4.0. Snapshot last refreshed 27 August 2026. Scores are a relative signal, not an absolute measure of capability. A Measured score was voted on directly; an Estimated score is inherited from an identical base model (a regional/creator-prefixed hosting duplicate). See our methodology.

FAQ

Why use different models in one workflow?

Because the steps have completely different requirements. A planner is called once and every later step inherits its mistakes, so frontier quality pays for itself. An implementer or classifier is called dozens or thousands of times and a mid-tier model produces the same result. Sizing each step separately is where the cost difference on this page comes from.

How are the models chosen?

For each step we take every model that clears a quality bar in the arena that matters for that job — and meets its tool-use, reasoning and context requirements — then pick the cheapest of those, priced at the cheapest major provider selling it. The bar per step is our editorial judgement, stated on each row so you can disagree with it.

Is the comparison against one model fair?

It is the baseline most teams actually run: pick the best model and use it for everything. Nobody should run a spam classifier on a frontier model, and that is exactly the point — the saving is large because the default is wasteful, not because the mixed setup cuts corners on the steps that matter.

Do these numbers include anything besides tokens?

No. These are input and output token costs at current prices for the token volumes shown. They exclude your own infrastructure, vector storage, tool and API calls made by the agent, and retries. Treat them as the model bill, not the total cost of ownership.

What quality signal is used?

Arena Elo from LMArena, the same source used across this site. Coverage differs by arena — overall 152, coding 94, math & reasoning 38, agentic / tool use 24 models scored — and the agentic arena is the thinnest, so where a step needs a broader pool we widen to the overall arena and label the row.

Related