OpenCode Go Plus
$60–$240 monthly usage value depending on the model. Five-hour limit: 20% of its monthly allowance; weekly: 50%.
Published terms checked 2026-09-29
Works with
OpenCode · Claude Code · Codex · Hermes · ZCode · Pi · jcode · Kilo Code CLI
Model access
30 named models
Billing
$40 / month
$60–$240 monthly usage value depending on the model. Five-hour limit: 20% of its monthly allowance; weekly: 50%.
Allowance by model
USD usage value, not cash credit. Five-hour and weekly values are calculated from the published 20% and 50% rules. Do not sum across models. *Unlimited applies only to the named temporary free models.
- GLM-5.3-Flash
- 5 hours$36Week$90Month$180
- GLM-5.3
- 5 hours$24Week$60Month$120
- GLM-5.2
- 5 hours$36Week$90Month$180
- Kimi K3
- 5 hours$12Week$30Month$60
- Kimi K2.7 Code
- 5 hours$36Week$90Month$180
- Kimi K2.6
- 5 hours$48Week$120Month$240
- LongCat-2.0
- 5 hours$48Week$120Month$240
- LongCat 2.5 Preview Free
- 5 hoursUnlimited*WeekUnlimited*MonthUnlimited*
| Model | 5 hours | Week | Month |
|---|---|---|---|
| GLM-5.3-Flash | $36 | $90 | $180 |
| GLM-5.3 | $24 | $60 | $120 |
| GLM-5.2 | $36 | $90 | $180 |
| Kimi K3 | $12 | $30 | $60 |
| Kimi K2.7 Code | $36 | $90 | $180 |
| Kimi K2.6 | $48 | $120 | $240 |
| LongCat-2.0 | $48 | $120 | $240 |
| LongCat 2.5 Preview Free | Unlimited* | Unlimited* | Unlimited* |
Token accounting rates
USD per million tokens. A dash means no cache-write rate is listed, not a zero rate. DeepSeek peak: Monday–Friday 01:00–04:00 and 06:00–10:00 UTC; all other times are off-peak. Context thresholds and temporary free pricing are shown per row. These Go rates are identical on Go Plus.
- GLM-5.3-Flash
- Input$0.15Output$0.50Cache read$0.03Cache write-Monthly limit$180
- GLM-5.3
- Input$1.40Output$4.40Cache read$0.26Cache write-Monthly limit$120
- GLM-5.2
- Input$1.40Output$4.40Cache read$0.26Cache write-Monthly limit$180
- Kimi K3
- Input$3.00Output$15.00Cache read$0.30Cache write-Monthly limit$60
- Kimi K2.7 Code
- Input$0.95Output$4.00Cache read$0.19Cache write-Monthly limit$180
- Kimi K2.6
- Input$0.95Output$4.00Cache read$0.16Cache write-Monthly limit$240
- LongCat-2.0
- Input$0.30Output$1.20Cache read$0.006Cache write-Monthly limit$240
- LongCat 2.5 Preview Free
- InputFreeOutputFreeCache readFreeCache write-Monthly limitUnlimited
| Model / condition | Input | Output | Cache read | Cache write | Monthly limit |
|---|---|---|---|---|---|
| GLM-5.3-Flash | $0.15 | $0.50 | $0.03 | - | $180 |
| GLM-5.3 | $1.40 | $4.40 | $0.26 | - | $120 |
| GLM-5.2 | $1.40 | $4.40 | $0.26 | - | $180 |
| Kimi K3 | $3.00 | $15.00 | $0.30 | - | $60 |
| Kimi K2.7 Code | $0.95 | $4.00 | $0.19 | - | $180 |
| Kimi K2.6 | $0.95 | $4.00 | $0.16 | - | $240 |
| LongCat-2.0 | $0.30 | $1.20 | $0.006 | - | $240 |
| LongCat 2.5 Preview Free | Free | Free | Free | - | Unlimited |
Provider request estimates
OpenCode estimates, not guaranteed request quotas. They assume specific input, cached-input and output mixes. Actual workload and cache behavior can materially change these counts. Unlimited free-model rows are temporary offers.
- GLM-5.3-Flash
- 5 hours18,960Week47,370Month94,740
- GLM-5.3
- 5 hours1,760Week4,320Month8,640
- GLM-5.2
- 5 hours2,640Week6,450Month12,900
- Kimi K3
- 5 hours440Week1,000Month1,960
- Kimi K2.7 Code
- 5 hours4,050Week10,140Month20,250
- Kimi K2.6
- 5 hours4,600Week11,520Month23,000
- LongCat-2.0
- 5 hours45,600Week114,400Month228,800
- LongCat 2.5 Preview Free
- 5 hoursUnlimitedWeekUnlimitedMonthUnlimited
| Model | 5 hours | Week | Month |
|---|---|---|---|
| GLM-5.3-Flash | 18,960 | 47,370 | 94,740 |
| GLM-5.3 | 1,760 | 4,320 | 8,640 |
| GLM-5.2 | 2,640 | 6,450 | 12,900 |
| Kimi K3 | 440 | 1,000 | 1,960 |
| Kimi K2.7 Code | 4,050 | 10,140 | 20,250 |
| Kimi K2.6 | 4,600 | 11,520 | 23,000 |
| LongCat-2.0 | 45,600 | 114,400 | 228,800 |
| LongCat 2.5 Preview Free | Unlimited | Unlimited | Unlimited |
Token mix behind request estimates
OpenCode’s assumed token mix, not a measurement of your workload. Its request estimates depend heavily on cache reads. Use your own recorded token categories for workload comparisons.
- Grok 4.7/4.6
- Input / request390Cached / request32,500Output / request120
- GLM-5.3-Flash
- Input / request1,000Cached / request55,000Output / request200
- GLM-5.3/5.2
- Input / request700Cached / request52,000Output / request150
- GPT 6 Luna
- Input / request1,000Cached / request50,000Output / request220
- GPT 5.6 Luna
- Input / request1,000Cached / request50,000Output / request220
- Kimi K3
- Input / request1,050Cached / request76,500Output / request300
- Kimi K2.7/K2.6
- Input / request870Cached / request55,000Output / request200
- LongCat-2.0
- Input / request920Cached / request88,900Output / request200
| Model | Input / request | Cached / request | Output / request |
|---|---|---|---|
| Grok 4.7/4.6 | 390 | 32,500 | 120 |
| GLM-5.3-Flash | 1,000 | 55,000 | 200 |
| GLM-5.3/5.2 | 700 | 52,000 | 150 |
| GPT 6 Luna | 1,000 | 50,000 | 220 |
| GPT 5.6 Luna | 1,000 | 50,000 | 220 |
| Kimi K3 | 1,050 | 76,500 | 300 |
| Kimi K2.7/K2.6 | 870 | 55,000 | 200 |
| LongCat-2.0 | 920 | 88,900 | 200 |
Training and data retention
Provider-published terms. DeepSeek zero-day retention depends on a monthly agreement currently valid through October 31, 2026. Muse Spark Contributor permits training and has regional restrictions. GPT Luna abuse-monitoring logs may be retained up to 30 days; Grok stored-data features affect retention.
- Grok 4.7
- Model trainingNot usedRetention30 days
- Grok 4.6
- Model trainingNot usedRetention30 days
- GPT 6 Luna
- Model trainingNot usedRetention30 days
- GPT 5.6 Luna
- Model trainingNot usedRetention30 days
- GLM-5.3-Flash
- Model trainingNot usedRetention0 days
- GLM-5.3
- Model trainingNot usedRetention0 days
- GLM-5.2
- Model trainingNot usedRetention0 days
- Kimi K3
- Model trainingNot usedRetention0 days
| Model | Model training | Retention |
|---|---|---|
| Grok 4.7 | Not used | 30 days |
| Grok 4.6 | Not used | 30 days |
| GPT 6 Luna | Not used | 30 days |
| GPT 5.6 Luna | Not used | 30 days |
| GLM-5.3-Flash | Not used | 0 days |
| GLM-5.3 | Not used | 0 days |
| GLM-5.2 | Not used | 0 days |
| Kimi K3 | Not used | 0 days |
Validated coding clients
Validation is not a guarantee for every future client release. All clients must preserve stable session identification; proxies must forward it. Copilot Chat, Kimi Code, DeepSeek Harness and MiMo Code have documented missing or incomplete support in investigated versions.
- OpenCode
- Session support / requirementConnect Go using /connect, then choose a model with the opencode-go/ prefix.
- Hermes
- Session support / requirementRequires the session-header change in PR #101864, merged after v0.21.0. Version 0.21.0 alone is insufficient.
- Claude Code
- Session support / requirementNative session identification is recognized; no custom-header wrapper required.
- Codex
- Session support / requirementNative session identification is recognized. Some versions and proxies omit it; forwarding must retain it.
- ZCode
- Session support / requirementIts native header is recognized. The separate x-opencode-session request is no longer required.
- Pi
- Session support / requirementUse a current build that sends OpenCode session information.
- jcode
- Session support / requirementRequires version 0.81.6 or later.
- Kilo Code CLI
- Session support / requirementRequires the session-header fix in PR #13752. This validation covers the CLI, not the VS Code extension.
| Client | Session support / requirement |
|---|---|
| OpenCode | Connect Go using /connect, then choose a model with the opencode-go/ prefix. |
| Hermes | Requires the session-header change in PR #101864, merged after v0.21.0. Version 0.21.0 alone is insufficient. |
| Claude Code | Native session identification is recognized; no custom-header wrapper required. |
| Codex | Native session identification is recognized. Some versions and proxies omit it; forwarding must retain it. |
| ZCode | Its native header is recognized. The separate x-opencode-session request is no longer required. |
| Pi | Use a current build that sends OpenCode session information. |
| jcode | Requires version 0.81.6 or later. |
| Kilo Code CLI | Requires the session-header fix in PR #13752. This validation covers the CLI, not the VS Code extension. |
API model IDs & endpoints
These endpoints consume the Go subscription allowance. They do not establish direct-provider API pricing or a separate pay-as-you-go entitlement. Preserve the client and session headers required by Go.
- Grok 4.7
- API model IDgrok-4.7Endpointhttps://opencode.ai/zen/go/v1/responsesSDK package@ai-sdk/openai
- Grok 4.6
- API model IDgrok-4.6Endpointhttps://opencode.ai/zen/go/v1/responsesSDK package@ai-sdk/openai
- GPT 6 Luna
- API model IDgpt-6-lunaEndpointhttps://opencode.ai/zen/go/v1/responsesSDK package@ai-sdk/openai
- GPT 5.6 Luna
- API model IDgpt-5.6-lunaEndpointhttps://opencode.ai/zen/go/v1/responsesSDK package@ai-sdk/openai
- GLM-5.3-Flash
- API model IDglm-5.3-flashEndpointhttps://opencode.ai/zen/go/v1/chat/completionsSDK package@ai-sdk/openai-compatible
- GLM-5.3
- API model IDglm-5.3Endpointhttps://opencode.ai/zen/go/v1/chat/completionsSDK package@ai-sdk/openai-compatible
- GLM-5.2
- API model IDglm-5.2Endpointhttps://opencode.ai/zen/go/v1/chat/completionsSDK package@ai-sdk/openai-compatible
- Kimi K3
- API model IDkimi-k3Endpointhttps://opencode.ai/zen/go/v1/chat/completionsSDK package@ai-sdk/openai-compatible
| Model | API model ID | Endpoint | SDK package |
|---|---|---|---|
| Grok 4.7 | grok-4.7 | https://opencode.ai/zen/go/v1/responses | @ai-sdk/openai |
| Grok 4.6 | grok-4.6 | https://opencode.ai/zen/go/v1/responses | @ai-sdk/openai |
| GPT 6 Luna | gpt-6-luna | https://opencode.ai/zen/go/v1/responses | @ai-sdk/openai |
| GPT 5.6 Luna | gpt-5.6-luna | https://opencode.ai/zen/go/v1/responses | @ai-sdk/openai |
| GLM-5.3-Flash | glm-5.3-flash | https://opencode.ai/zen/go/v1/chat/completions | @ai-sdk/openai-compatible |
| GLM-5.3 | glm-5.3 | https://opencode.ai/zen/go/v1/chat/completions | @ai-sdk/openai-compatible |
| GLM-5.2 | glm-5.2 | https://opencode.ai/zen/go/v1/chat/completions | @ai-sdk/openai-compatible |
| Kimi K3 | kimi-k3 | https://opencode.ai/zen/go/v1/chat/completions | @ai-sdk/openai-compatible |
- How usage is counted
- Input, output and cached tokens consume the selected model’s dollar-denominated allowance at Go rates. These are usage accounting rates, not an extra invoice on top of the subscription. Model allowance values are not balances to add together. Source ↗
- When you reach a limit
- Requests are blocked unless you enable Use balance and have paid Console credits. That opt-in continues requests using pay-as-you-go credits. Free models remain available. Source ↗
- Privacy matters by model
- Muse Spark Contributor allows prompts and completions to be used for training and is not zero-data-retention. Grok and GPT Luna list 30-day retention. Other listed models show zero-day retention; DeepSeek’s agreement is currently valid through October 31, 2026. Source ↗
- Workspace and client requirements
- One Go or Go Plus subscriber per workspace. Designed for coding-agent requests. Clients need their own user agent and stable session identification. Validated clients and version restrictions are listed below. Source ↗
- Regional and temporary access
- Muse Spark Contributor is limited to regions allowed by Meta. LongCat 2.5 Preview Free and Space Bunny Free are temporary offers. OpenCode may change models and allowances. Source ↗
- Renewal and cancellation
- Recurring charges continue until you cancel through account settings. The general paid-service terms do not specify a Go-specific refund entitlement or when remaining access ends after cancellation. Source ↗
- Reset and billing details still to check
- The cited terms give five-hour, weekly and monthly limits but do not establish the exact reset anchor, cross-model consumption rules, rollover or a Go-specific refund policy. Check the Console before relying on those details. Source ↗
Published terms checked 2026-09-29. Provider terms can change.
Go and Go Plus share this model lineup, with different model-specific usage allowances. Temporary free models can change.
Included coding models30
Provider lineup ↗- Grok 4.7
- Grok 4.6
- GLM-5.3-Flash
- GLM-5.3
- GLM-5.2
- GPT 6 Luna
- GPT 5.6 Luna
- Kimi K3
- Kimi K2.7 Code
- Kimi K2.6
- LongCat-2.0
- LongCat 2.5 Preview FreeTemporary free or preview availability.
Model access checked 2026-09-28. Named access does not establish how much of that model a plan includes or a predictable usage allowance.
Free models remain available. Enable Use balance with paid Console credits to continue on pay-as-you-go pricing after an included limit. Otherwise requests are blocked.
Published terms, sources & history
Published price and access do not establish a numeric allowance.
Included usage
Model-dependent monthly allowances, with five-hour and weekly limits.
Compatible tools
OpenCode · Claude Code · Codex · Hermes
After the limit
Optional Zen balance can fund usage after the included limit; free models remain available.
- Official current price, access and usage terms; catalog admission date, not a historical launch date checked Sep 28, 2026
Catalog record opencode-go-plus@2026-09-28. Catalog dates identify recorded rule versions. New admissions do not establish a provider launch date. Provider credits are specific to that provider. Listing a price does not establish capacity, equivalent experience or that a plan could replace another.