Choose ChatGPT-plan coding access or a separately selected OpenCode provider. Codex — Plus: $20.00/month. OpenCode — OpenCode Go — optional provider: $10.00/month (Optional hosted provider; not the price of the open-source agent)
Last verified
Plan decision matrix
Selected plans for this decision. Follow the pricing guides for all tiers. Currencies, billing periods and quota units retain their original scope.
FactOpenCode Go — optional provider: $10.00/month (Optional hosted provider; not the price of the open-source agent)OpenCode Go · OpenCode Zen
Usage limits
FactPlus: Approximate official local-message estimates per five-hour period vary by model in a shared pool; additional weekly limits may apply. These estimates are not fixed message limits.Codex pricing and usage limits · Codex pricing
FactOpenCode Go — optional provider: Go ($10/month): each model has its own monthly usage-value limit, $15–$60 depending on the model; the 5-hour limit is 20% and the weekly limit 50% of it. A $60 model allows $12 / 5 hours and $30 / week. Base usage value; effective allowance varies by model. This is not a universal request quota or equal capacity across models.OpenCode Go
Available interfaces (product scope)
FactProduct interfaces: ChatGPT desktop app, Web, Codex CLI, IDE extension, Codex cloud, iOS. Plan-specific eligibility is not implied.Codex pricing · Codex models
FactPlus: Additional credits can extend usage after included limits; credit consumption varies by model and speed.Codex pricing and usage limits
FactOpenCode Go — optional provider: OpenCode Zen balance can be used beyond Go caps when that option is enabled.OpenCode Go · OpenCode Zen
Choose according to your requirements
Choose Codex if…
Derived decision you want Codex app, CLI and cloud access under Plus.
FactPlus: Approximate official local-message estimates per five-hour period vary by model in a shared pool; additional weekly limits may apply. These estimates are not fixed message limits.Codex pricing and usage limits · Codex pricing
FactProduct interfaces: ChatGPT desktop app, Web, Codex CLI, IDE extension, Codex cloud, iOS. Plan-specific eligibility is not implied.Codex pricing · Codex models
FactIncluded ChatGPT subscription usage, with separate API/provider access where configuredCodex pricing · Codex models
FactPlus: Additional credits can extend usage after included limits; credit consumption varies by model and speed.Codex pricing and usage limits
Choose OpenCode if…
Derived decision you want a separate OpenCode Go provider with optional Zen balance.
FactOpenCode Go — optional provider: Go ($10/month): each model has its own monthly usage-value limit, $15–$60 depending on the model; the 5-hour limit is 20% and the weekly limit 50% of it. A $60 model allows $12 / 5 hours and $30 / week. Base usage value; effective allowance varies by model. This is not a universal request quota or equal capacity across models.OpenCode Go
FactOpenCode Go — optional provider: OpenCode through the OpenCode Go providerOpenCode Go · OpenCode Zen
FactOpenCode Go — optional provider: OpenCode Zen balance can be used beyond Go caps when that option is enabled.OpenCode Go · OpenCode Zen
What this comparison cannot establish
Published quotas use different units and workloads. These records cannot establish relative coding output or a universal winner. A missing numeric allowance is Unknown, not unlimited.
Not directly comparable One side has no verified numeric limit in this window.
Codex: Numeric capacity beyond the cited plan rules and workload-specific throughput are Unknown in this comparison.
OpenCode: Numeric capacity beyond the cited plan rules and workload-specific throughput are Unknown in this comparison.
Recommendations on this page are conditional. There is no global winner score.
Official source conflict
Official sources disagree
Unknown — conflicting GPT-5.4 availability in Codex for ChatGPT-signed-in users
Source A:Codex pricing — The Codex pricing table still displays legacy GPT-5.4 and GPT-5.4 mini rows.
Source B:Using Codex with your ChatGPT plan — The Help Center states those models are no longer available in Codex for users signed in with ChatGPT from August 31, 2026.
Applies to: ChatGPT-signed-in Codex users after 2026-08-31
Decision impact: Do not treat GPT-5.4 as a current Codex ChatGPT-login model. API-provider rows remain a separate access path.
TraceCheck status: Unresolved — Derived outputs must not treat one side as settled Fact.
Last checked Sep 8, 2026, 6:00 PM UTC
Official sources and verification
Last verified · Codex
Usage evidence reviewed . Other product facts retain their earlier verification date.
Official sources conflict Official sources conflict. The Codex pricing table still displays legacy GPT-5.4 and GPT-5.4 mini rows, while the Help Center states those models are no longer available in Codex for users signed in with ChatGPT from August 31, 2026.
Codex now recommends GPT-6.1 Sol and adds GPT-6 Sol and GPT-6 Luna. GPT-5.3-Codex-Spark retired on September 14, and GPT-5.5 retires from ChatGPT-signed-in Codex on October 14, 2026. — Codex models on Plus: GPT-6 Astra, GPT-5.6 Sol, GPT-5.6 Terra, GPT-5.6 Luna; Pro also GPT-5.3-Codex-Spark → GPT-6.1 Sol (recommended), GPT-6 Astra, GPT-6 Sol and GPT-6 Luna, with GPT-5.6 Sol, Terra and Luna available during the rollout. Spark retired September 14, 2026; GPT-5.5 retires October 14, 2026. Verified Oct 11, 2026, 9:30 AM UTC.
Codex Plus limits now list the GPT-6 models: GPT-6.1 Sol 15–160, GPT-6 Sol 15–150 and GPT-6 Luna 350–3,000 local messages per five hours. GPT-5.6 Terra has no row. — Plus approximate local messages per five hours: GPT-6 Astra 5–45, GPT-5.6 Sol 10–100, GPT-5.6 Terra 25–200, GPT-5.6 Luna 250–2,000 → Plus and Standard Business approximate local messages per five hours: GPT-6.1 Sol 15–160, GPT-6 Astra 5–45, GPT-6 Sol 15–150, GPT-6 Luna 350–3,000, GPT-5.6 Sol 10–100, GPT-5.6 Luna 250–2,000. Verified Oct 11, 2026, 9:30 AM UTC.
Codex Pro is now three plans ($100, $200 and $500 per month), and Pro plans currently have no five-hour limit. The Pro 5x and 20x message columns are gone from the usage table. — Pro was one plan from $100/month with official 5x and 20x capacity columns of approximate local messages per five hours (GPT-6 Astra 25–225 at 5x, 100–900 at 20x) → Pro plans at $100, $200 or $500 per month. Pro plans currently have no five-hour limit; weekly limits may apply. Ultrafast mode is on Pro $500. Verified Oct 11, 2026, 9:30 AM UTC.
Codex Plus approximate five-hour local-message ranges re-verified from the official Plus column; they are not a single collapsed quota. — Unknown — current model-specific message estimates require re-verification. A shared five-hour allowance applies, and additional weekly limits may apply. → Approximate official local-message estimates per five-hour period from the Plus column: GPT-6 Astra 5–45; GPT-5.6 Sol 10–100; GPT-5.6 Terra 25–200; GPT-5.6 Luna 250–2,000. Shared pool; weekly limits may apply; estimates are not fixed limits.. Verified Sep 7, 2026, 4:00 PM UTC.
OpenCode Go now has two tiers, Go ($10/month) and Go Plus ($40/month), and measures limits per model as a monthly dollar amount. — OpenCode Go $10/month with base limits of $12 per 5 hours, $30 per week and $60 per month in usage value → Go $10/month and Go Plus $40/month. Limits are per-model monthly dollar amounts ($15–$60 on Go, $60–$240 on Go Plus) with 5-hour and weekly limits at 20% and 50% of each. Verified Oct 11, 2026, 12:30 AM UTC.