Vendor pricing
OpenCode Zen / Go models model pricing
Every OpenCode Zen / Go models model JP prices, side by side — input, output, and cache rates per million tokens.
| Model | Input (USD / 1M) | Output (USD / 1M) | Cache read (USD / 1M) |
|---|---|---|---|
| Big Pickle | $0.00 | $0.00 | — |
| GLM 5.3 Flash | $0.15 | $0.50 | $0.03 |
| GLM 5.3 | $1.40 | $4.40 | $0.26 |
| GLM 5.2 | $1.40 | $4.40 | $0.26 |
| GLM 5.1 | $1.40 | $4.40 | $0.26 |
| Kimi K3 | $3.00 | $15.00 | $0.30 |
| Kimi K2.7 Code | $0.95 | $4.00 | $0.19 |
| Kimi K2.6 | $0.95 | $4.00 | $0.16 |
| LongCat 2.0 | $0.30 | $1.20 | $0.006 |
| MiMo V2.5 | $0.14 | $0.28 | $0.0028 |
| MiMo V2.5 Pro | $0.435 | $0.87 | $0.003625 |
| MiniMax M3 | $0.30 | $1.20 | $0.06 |
| MiniMax M2.7 | $0.30 | $1.20 | $0.06 |
| Qwen 3.8 Max | $2.00 | $6.00 | $0.25 |
| Qwen 3.8 Flash | $0.15 | $0.47 | $0.016 |
| Qwen 3.7 Max | $2.50 | $7.50 | $0.50 |
| Qwen 3.7 Plus | $0.40 | $1.60 | $0.04 |
| Qwen 3.6 Plus Base rates match Zen. The context premium is retained from earlier Go pricing and is absent from the current Go table. | $0.50 | $3.00 | $0.05 |
| Qwen 3.5 Plus | $0.20 | $1.20 | $0.02 |
| Hy4 Preview | $0.834 | $2.501 | $0.042 |
| Hy3 | $0.14 | $0.58 | $0.035 |
| Space Bunny | $0.15 | $0.60 | $0.03 |
| MiniMax M2.5 Base rates match Zen. The cache-write rate is retained from earlier Go pricing and is absent from current tables. | $0.30 | $1.20 | $0.06 |
| Union Alpha Historical bundled rate; not verified against current published pricing. | $0.00 | $0.00 | — |
| MiMo V2.6 Flash | $0.14 | $0.28 | $0.0028 |
| MiMo V2.6 Pro | $0.435 | $0.87 | $0.003625 |
| GPT-5-Codex · Zen | $1.07 | $8.50 | $0.107 |
| GPT-5.1-Codex · Zen | $1.07 | $8.50 | $0.107 |
| Grok 4.7 · OpenCode | $2.00 | $6.00 | $0.50 |
| Grok 4.6 · OpenCode | $2.00 | $6.00 | $0.50 |
| Grok 4.5 · OpenCode | $2.00 | $6.00 | $0.30 |
| Grok Build 0.1 · OpenCode | $1.00 | $2.00 | $0.20 |
Notional list price. OpenCode Zen / Go models usage on a subscription is metered as a flat plan, so these per-token figures are list price, not spend.
How to read this table
Prices are USD per million tokens from the bundled table. Historical rates that could not be verified are labelled beside the model. Cache reads usually cost less than full input (often about a tenth for Claude/OpenAI/Gemini); context thresholds vary by model and gateway; a recorded context tier reprices the whole request.
Subscription note
OpenCode Zen serves its own house models free; OpenCode Go ($10/month) meters glm-*, kimi-*, qwen-*, minimax-*, mimo-, longcat- and hy- models at published per-token rates. JP mirrors those Go list prices as notional figures.
Common questions
- Which OpenCode Zen / Go models model is cheapest?
- The flash / mini / haiku tiers are the lowest per-token; the pro / opus tiers cost more but reason harder. The table shows the exact rates.
Track your real cost with JP the Cat
A live menu-bar total, priced to the cent from your local logs — including the cache-write split most tools miss.
Download MeowPrefer Homebrew? Install the same signed, notarized app from JP's public tap.
brew tap 8bittts/jpthecat
brew trust 8bittts/jpthecat
brew install --cask jpthecat