SWE-agent: how many tokens per task, and what does it cost?
SWE-agent publishes no per-task cost or token figure in the AgentBurn index. AgentBurn snapshot 2026-10-27. Every figure carries a provenance label: source-backed, derived, or left empty when no public basis exists.
What it is. Princeton agent with a bespoke computer interface for repository tasks
SWE-agent showed that the agent-computer interface matters as much as the model: it gives the LLM a windowed file viewer, edit commands with linting feedback and a guardrailed shell. That interface work alone produced a 3.3x improvement on SWE-bench, and it remains the reference harness behind the mini-SWE-agent bash-only leaderboard.
| Tokens per task | not published | Not published |
|---|---|---|
| Cost per task | not published | Not published |
| Success rate | not published | Not published |
| Cost per solved task | not published | — |
| Tool calls per task | not published | — |
| Retry overhead | not published | — |
| Minutes per task | not published | — |
| Estimated runs per day | null (model estimate) | Not published |
Where the tokens go
This is the per-task split AgentBurn records for SWE-agent, step by step.
| Step | What happens | Share of tokens | Tool calls |
|---|---|---|---|
| Open issue | Loads the problem statement and the repo layout | 10% | 5 |
| Search files | Uses windowed file viewer and search commands | 24% | 20 |
| Edit with linting | Applies edits; lint errors are fed straight back | 28% | 18 |
| Run tests | Executes the target tests and reads the diff output | 24% | 18 |
| Submit patch | Emits the final diff for evaluation | 14% | 9 |
What each number is based on
AgentBurn labels every field. Source-backed means the cited page states the figure; derived means a formula on this page produced it; not published means no public basis exists and the field is left empty rather than estimated.
| Field | Basis | Note |
|---|---|---|
| tokensPerTask | Not published | No usable public source for per-task tokens. |
| costPerTaskUsd | Not published | No usable public source for per-task cost. |
| successRatePct | Not published | No public task success rate. |
| runsPerDay | Not published | No public run volume. |
Frequently asked
How many tokens does SWE-agent use per task?
No public tokens-per-task figure exists for SWE-agent; AgentBurn leaves the field empty rather than estimating it.
What does SWE-agent cost per task?
No public per-task cost exists for SWE-agent, so it is recorded as not published.
Is this a vendor list price?
No. It is a per-task figure from a cited source, not a rate card; the two are not comparable.
Sources
- SWE-agent repository and agent-computer interface documentation
- Vendor site: https://swe-agent.com
- Repository: https://github.com/SWE-agent/SWE-agent
- Paper: https://arxiv.org/abs/2405.15793
- Open dataset: /data/projects.json
- Methodology: how these numbers are built
Cite this page
AgentBurn (2026-10-27). "SWE-agent". https://getagentburn.com/projects/swe-agent/
Machine-readable: projects.json · Markdown version