Codex CLI 0.160 and GPT-6.1 Sol
CLI 0.160.0 improves task history, session recovery, and opt-in Guardian reviews. GPT-6.1 Sol arrived September 29; model availability depends on the plan, client, and workspace.
/coding-agentscodex
OpenAI
OpenAI Codex
OpenAI's local and cloud coding agent for terminal work, desktop multi-agent workflows, code review, and hosted tasks.
CLICloudDesktopIDEWebMobileActiveOpen sourceBYOKMCP Yes
Recent product updates
Reviewed
Selected releases and additions, with links to the original announcements.
Attributed output
GitHub public-attribution count, 2026-06-09
5.1M PRsAttributed outputGitHub public-attribution count, 2026-06-09Commits and PRs on public GitHub provably produced by this agent. Exact if it is visible through its own bot or workflow, an estimate if measured through attribution it declares (these can swing 30 to 40 percent between measurement runs at multi-million scale), and a floor either way.Index rank · all agents
#2 of 40 CLI agents
#2Index rank · all agents#2 of 40 CLI agentsRanked by agent-opened PRs in the trailing 4 complete weeks, matching the index. Agents without a tracked PR series follow, ordered by total attributed output. Other filters or sorts change the list position.Business signal
Weekly Codex users · Jun 2026
5M+ weeklyBusiness signalWeekly Codex users · Jun 2026Included with eligible plans
Entry price
Plan allowance and token credits
Included with eligible plansEntry pricePlan allowance and token credits21,715,713
npm demand/wk
Adjusted from raw npm channel
21,715,713npm demand/wkAdjusted from raw npm channelWeekly package downloads as an install-demand floor; adjusted when the vendor's main install channel is no longer npm.617,003,601
npm installs to date
415,997,487 excluding the CI spike
617,003,601npm installs to date415,997,487 excluding the CI spikeTotal npm downloads of this agent's package(s) summed across every tracked week since it was first published. A floor, like the weekly figure. Where a one-week automated/CI burst inflated the total, the baseline-only figure is shown too.From the public record
What the public PRs reveal
50 PRs · 49 repositories
Search window: – · captured Oct 14, 2026 (UTC)
Codex-attributed work gets CodeRabbit follow-ups
Separate study: CodeRabbit follow-ups, May 25–October 11, 2026
In CodeRabbit’s May 25–October 11 audit, we found 6 original PRs crediting Codex, followed by 7 CodeRabbit auto-fix PRs; 5 follow-ups were merged. This cohort was selected through CodeRabbit, so it cannot tell us what fraction of this agent’s overall work receives follow-up fixes. Credits can name a model without identifying its client.
Specific work you can inspect
BazaarPlusPlus/BazaarPlusPlus: “fix(mod): restore combat status toggle and native UI layering” (merged). portingpete/The-Darkness-Recomp: “Keep keyboard prompts after level-loading texture eviction” (merged).
This is a sample of publicly attributed work, not total usage or a market-share estimate. Repositories are not customers. Attribution is declared in metadata, not independently verified tool execution; it does not prove exclusive authorship or autonomy. PR status is recorded at capture; merged does not establish correctness.
Method and audit data
Up to 50 most recently created public PR search results within the audit window; post-filtered for body attribution or Codex branch. A recent convenience sample, not a random or exhaustive sample.
Returned records dated Oct 11, 2026–Oct 11, 2026.
Download the dated audit evidence (JSON)Activity Over Time
Weekly attributed output on public GitHub. Output visible through the agent's own bot or workflow is exact; output measured through declared attribution is an estimate. Window: 2025-02-03 to 2026-10-12.
npm Installs Over Time
Weekly npm downloads since 2025-04-14, the install-demand trajectory. Toggle Ex-CI spike to remove the one-week automated burst.
Market
Developer output
Public pull requests from Codex cloud
Counted from the pull requests Codex's cloud service opens. That cloud path is well-covered (about 86% merge), but the match is inferred from public pull-request signals rather than an exact bot identity, so treat the count as an estimate, not an exact figure. Codex's local command-line work runs under the developer's own identity, so that output is largely invisible to public attribution and not in this count, making the total a floor. An earlier signal was retired in late 2025 and replaced, so the series stays continuous.
Last full week (ending 2026-10-18): 324K agent-marked PRs (+7% week over week), search estimate.
Distinct users: 6,187 humans opened the 12,000 most recently sampled PRs, about 1.9 PRs per person.
Merge rate: 87.3% of its pull requests get merged (1,539,137 of 1,764,025 over 8 settled weeks, 2026-08-10 to 2026-10-04). The window ends about ten days back so recently-opened PRs have had time to merge.
GitHub review activity: 3.3% of its merged PRs had at least one GitHub review record before merging; the other 96.7% had none. This is a broad weekly signal and can include bot reviews; the human-review read below comes from the enriched PR sample.
In significant repos (company-owned or 10+ stars), 28.6% of its merged PRs got a human review. Across all sampled repos, the rate is 19.2%. Human review means a non-author, non-bot GitHub reviewer in the PR-lifecycle sample.
Median time to merge: 8 min. The unreviewed median is 0.1h. The human-reviewed median is 2.5h. From a 120-PR sample merged 2026-07-30 to 2026-08-28.
Test-inclusion: 69.2% of its sampled merged PRs touch a test file. This is a rough read on production readiness. 7 large PRs hit GitHub's 100-file path read cap, so treat this as a floor.
Flow share: 0.2% of the 1999 most recent public PRs sampled (4 PRs, 2 windows, last 2026-09-27).
Snapshot 2026-06-09, confidence Medium, tracked since 2026-06-09, +3.6% over 7 days. Read the methodology.
- Index rank · all agents
- #2 of 47 · #2 among CLI agents
- Demand share
- 50.8% of tracked npm demand floor
- Business signal
- 5M+ weekly Weekly Codex users · Jun 2026
- GitHub share
- 7.3% of tracked stars
- npm channel
- 13.2M raw downloads/week (npm primary)
Best fit
OpenAI-native teamsParallel cloud tasksCode reviewKnowledge-work apps
Direct competitors
- OpenAI says non-developers are about 20% of Codex users and are growing more than 3x as fast as developers.
- Codex revenue is not disclosed separately from ChatGPT, Business, Enterprise, or API consumption.
npm channel caveat: npm primaryExpandHide
Codex has a steady npm install channel (~6M/week) plus a one-week spike in early May 2026.
Daily npm installs sit around 0.8-1M (~6M/week) before and after the spike, so distribution did not stop. For one week (Apr 30 to May 6, 2026) daily downloads jumped 30-50x to 13-46M, then fell straight back to baseline. That sudden-then-gone shape is characteristic of automated or CI traffic around a release (a transitive dependency or pinned action), not a durable change in active users, so the demand figure here uses the trailing 4-week average and excludes the spike.
- Demand floor
- 21.7M / wk
- Latest npm week
- 13.2M
- Peak npm week
- 130.5M
- 4-week average
- 21.7M
Trailing 4-week average; release spike excluded from demand floor
Complete Mon-Sun week when cron-backed
Observed public npm range
As of 2026-10-18
All sourced signals (2)ExpandHide
| Signal | Value | Type | Confidence |
|---|---|---|---|
| GitHub stars | 126,462 | Public metric | High |
| npm downloads (2026-09-18 to 2026-09-24) | 18,949,447 | Public metric | High |
Where OpenAI Codex Works
Languages
TypeScript33%
Python24%
JavaScript12%
Rust8%
HTML5%
Go4%
Frameworks
React22%
Next.js16%
Flutter11%
.NET8%
SwiftUI6%
Astro6%
Industries
AI/ML41%
Devtools13%
Gaming9%
Finance6%
Media4%
Healthcare3%
Countries
China14%
United States of America14%
Japan7%
Germany5%
United Kingdom5%
Brazil4%
Share of OpenAI Codex's own classified sampled work by segment; countries reflect where its PR authors are based. Full breakdowns: Languages, Frameworks, Industries, Map.
Pricing And Economics
ExpandHide
Pricing snapshot: 2026-09-25. Check the vendor for current terms.
Codex usage is included with eligible ChatGPT plans, with plan-specific limits and credits. API-key usage follows API pricing.
- Entry price
- Included with eligible plans
- Top self-serve price
- n/a
- Pricing unit
- Plan allowance and token credits
- Token transparency
- Token rate card
- Included usage
- Larger tasks, higher reasoning effort, and faster speed settings can consume more of the allowance.
- Overage path
- Model availability depends on your plan and workspace.
Retail Token Equivalent
Allowance is not a fixed token entitlement. Consult the linked vendor pricing and your account’s usage limits.
| Plan | Price | Allowance | Unit | Token / Overage Notes |
|---|
Unit Economics (Measured)
Mean API-retail cost per completed task on the Artificial Analysis coding agent index (358 tasks across 3 suites, pass@1 over 3 runs, snapshot 2026-06-09). These are pay-per-token API costs, not subscription effective costs.
| Harness | AA index | Cost / task | Tokens / task | Time / task |
|---|---|---|---|---|
| Codex, GPT-5.5 (xhigh) | 65.3 | $4.33 | 4.8M | 9m |
| Codex, GPT-5.5 (medium) | 60.4 | $2.21 | 2.8M | 7m |
| Codex, GPT-5.4 (medium) | 53.6 | $2.09 | 2.5M | 7m |
Summary checked 2026-09-25.
Codex usage is included with eligible ChatGPT plans, with plan-specific limits and credits. API-key usage follows API pricing.
- Larger tasks, higher reasoning effort, and faster speed settings can consume more of the allowance.
- Model availability depends on your plan and workspace.
Company And Funding
ExpandHide
- Ownership
- Private
- Founded
- 2015
- Headquarters
- San Francisco, CA
- Employees
- ~9,300
- Total raised
- ~$180B
- Most recent round
- Series G, $122B (Mar 2026)
- Round leads
- SoftBank, Andreessen Horowitz, Amazon, Nvidia
OpenAI operates as a capped-profit company controlled by the OpenAI nonprofit. Codex is an OpenAI product, not a separately financed entity.
Parent-company total.
Notable investors
MicrosoftSoftBankNvidiaAmazonThrive CapitalMGX
Enterprise And Security
ExpandHide
- SSO / SCIM
- Yes
- Deployment
- Cloud-only
- Trains on your code
- Not trained on your code
- Zero data retention
- Enterprise tier
Compliance
SOC 2 Type IIGDPRCSA STAR
Admin controls
SAML SSO / SCIMAudit logsData residency
OpenAI does not train on Business, Enterprise, or API data by default. Zero data retention is available for eligible endpoints with a qualifying use case.
Product
Providers
OpenAI
Model families
GPT-6.1 SolGPT-6 AstraGPT-6 SolGPT-6 LunaGPT-5.6 SolGPT-5.6 TerraGPT-5.6 Luna
Capabilities
Repo editingTerminal commandsCloud tasksSubagentsCode reviewMCPWeb searchImage input
Tradeoffs
- Fast-moving model availability
- Pricing differs across ChatGPT plan, Business Codex, and API-key modes