Files
agent-estate-wiki/systems/opencode-go.md
T
Hermes Wiki Audit 729bb597cf audit(2026-11-11): the audit's own 429 killed the 11-10 window; stocktake + radar recover with output
Window 2026-11-10 23:59 -> 2026-11-11 23:59 (two windows: the 11-10 audit failed).

NEW incident: incidents/2026-11-10-wiki-audit-429-all-targets-skipped.md
 - cbfe434a3b5e ran 23:59:54.486572 -> 2026-11-11 00:12:29.646987 = 12m35s, failed, delivery suppressed
 - RuntimeError: HTTP 429 ... all targets skipped by pre-dispatch filters (credits 100% conn:3021bab6)
   reset after 6h24m31s; 6 candidates, attempted 0; tenant tn-5ud77abtl1 quota exceeded
 - incident row cbfe43_ed01845310d8 (rate_limit) alerted_at NULL, closed_at NULL = only open row
 - consequence: the 2026-11-10 window was never audited; non-clean last_status 1 -> 2

RESOLVED with output (dated Recovery sections added):
 - stocktake 1a8e90ea2271 03:00:56.081504 -> 04:11:38.724852 = 1h10m42s, 36 stale re-verified -> 0
 - job radar stage1 07:01:08 -> 07:37:34 = 36m26s, first handoff since 2026-11-06 (22,682 B)
 - radar stage2 recovery fire 07:35:56 -> 08:03:47 closed row 5fc292_773822455856 resolved

UPDATED pages: current-state.md, systems/scheduled-tasks.md, systems/opencode-go.md
(opencode-zen 401 api_key_expired now observed 7x, paired with nous 404 credits 14x),
incidents/2026-10-22-nous-portal-refresh-token-invalid.md, index.md, log.md
2026-11-12 00:16:39 +08:00

9.9 KiB
Raw Blame History

title, type, status, created, updated, verified_on, confidence, tags, sources
title type status created updated verified_on confidence tags sources
OpenCode Go system active 2026-07-29 2026-11-11 2026-11-11 high
opencode
provider
models
subscription
limits
https://opencode.ai/docs/go/

OpenCode Go

Low cost subscription for open coding models — $5 first month, then $10/month. Designed for international users, models hosted in US, EU, and Singapore.

How It Works

  1. Sign in to OpenCode Zen, subscribe to Go, copy your API key
  2. Run /connect in the TUI, select OpenCode Go, paste your API key
  3. Run /models to see available models

Only one member per workspace can subscribe.

Note (2026-10-20): the pricing and dollar-limit tables below are vendor-published figures for the OpenCode Go product, not a measurement of this estate. Nothing in ~/.hermes/config.yaml or jobs.json shows an OpenCode Go provider in use — the estate routes through LiteLLM, OmniRoute (omni-101) and Omniroute:20128. Treat this page as reference material for the subscription, not as a description of a configured provider.

Usage Limits

Window Dollar Limit
5 hours $12
Weekly $30
Monthly $60

Limits are in dollar value, so your actual request count depends on the model. Cheaper models (DeepSeek V4 Flash, MiMo-V2.5) get far more requests than expensive ones (Kimi K3, Grok 4.5).

Estimated Requests Per Window

Based on typical Go usage patterns:

Model Per 5h Per Week Per Month
Grok 4.5 120 300 600
GLM-5.2 880 2,150 4,300
GLM-5.1 880 2,150 4,300
Kimi K3 110 250 490
Kimi K2.7 Code 1,350 3,380 6,750
Kimi K2.6 1,150 2,880 5,750
MiMo-V2.5 30,100 75,200 150,400
MiMo-V2.5-Pro 3,250 8,150 16,300
MiniMax M3 3,200 8,000 16,000
MiniMax M2.7 3,400 8,500 17,000
Qwen3.7 Max 950 2,390 4,770
Qwen3.7 Plus 4,300 10,800 21,600
Qwen3.6 Plus 3,300 8,200 16,300
DeepSeek V4 Pro 3,450 8,550 17,150
DeepSeek V4 Flash 31,650 79,050 158,150
Hy3 4,300 10,750 21,500

Token Estimates Per Request

Model Input Tokens Cached Tokens Output Tokens
Grok 4.5 1,100 71,500 220
GLM-5.2/5.1 700 52,000 150
Kimi K3 1,050 76,500 300
Kimi K2.7/K2.6 870 55,000 200
DeepSeek V4 Pro 750 82,000 290
DeepSeek V4 Flash 790 68,000 280
MiniMax M3 510 56,000 190
MiniMax M2.7 300 55,000 125
MiMo-V2.5 830 71,500 295
MiMo-V2.5-Pro 790 86,000 305
Qwen3.7 Max 420 66,000 200
Qwen3.7 Plus 500 57,000 190
Qwen3.6 Plus 500 57,000 190
Hy3 830 71,500 295

Per-Model Pricing & Monthly Usage Included

Model Input $/1M Output $/1M Cached Read $/1M Monthly Usage
Grok 4.5 $2.00 $6.00 $0.30 $15
GLM-5.2 $1.40 $4.40 $0.26 $60
GLM-5.1 $1.40 $4.40 $0.26 $60
Kimi K3 $3.00 $15.00 $0.30 $15
Kimi K2.7 Code $0.95 $4.00 $0.19 $60
Kimi K2.6 $0.95 $4.00 $0.16 $60
MiMo V2.5 $0.14 $0.28 $0.0028 $60
MiMo V2.5 Pro $0.435 $0.87 $0.0036 $15
MiniMax M3 $0.30 $1.20 $0.06 $60
MiniMax M2.7 $0.30 $1.20 $0.06 $60
Qwen3.7 Max $2.50 $7.50 $0.50 $60
Qwen3.7 Plus (≤256K) $0.40 $1.60 $0.04 $60
Qwen3.7 Plus (>256K) $1.20 $4.80 $0.12 $60
Qwen3.6 Plus (≤256K) $0.50 $3.00 $0.05 $60
Qwen3.6 Plus (>256K) $2.00 $6.00 $0.20 $60
DeepSeek V4 Pro $0.435 $0.87 $0.0036 $15
DeepSeek V4 Flash $0.14 $0.28 $0.0028 $60
Hy3 $0.14 $0.58 $0.035 $60

Track usage in the console.

If you reach the usage limit, you can continue using the free models.

Usage Beyond Limits

If you also have credits on your Zen balance, enable the Use balance option in the console. Go will fall back to your Zen balance after reaching usage limits instead of blocking requests.

Why Some Models Have Lower Usage

With Go, you pay $10/month and they aim to give you 6x that in usage ($60). For most models, this works through bulk discounts and reserved GPU capacity. For some models (Grok 4.5, Kimi K3, MiMo V2.5 Pro, DeepSeek V4 Pro), they haven't negotiated discounts yet — so the usage multiplier is lower (you get a little more than paying directly, just not the full 6x).

Available Models

Model Model ID Endpoint SDK Package
Grok 4.5 grok-4.5 https://opencode.ai/zen/go/v1/chat/completions @ai-sdk/openai-compatible
GLM-5.2 glm-5.2 same same
GLM-5.1 glm-5.1 same same
Kimi K3 kimi-k3 same same
Kimi K2.7 Code kimi-k2.7-code same same
Kimi K2.6 kimi-k2.6 same same
DeepSeek V4 Pro deepseek-v4-pro same same
DeepSeek V4 Flash deepseek-v4-flash same same
MiMo-V2.5 mimo-v2.5 same same
MiMo-V2.5-Pro mimo-v2.5-pro same same
MiniMax M3 minimax-m3 https://opencode.ai/zen/go/v1/messages @ai-sdk/anthropic
MiniMax M2.7 minimax-m2.7 same same
MiniMax M2.5 minimax-m2.5 same same
Qwen3.7 Max qwen3.7-max same same
Qwen3.7 Plus qwen3.7-plus same same
Qwen3.6 Plus qwen3.6-plus same same
Hy3 hy3 https://opencode.ai/zen/go/v1/chat/completions @ai-sdk/openai-compatible

2026-11-08 00:0x-00:5x AWST — the stored credential is expired (401 api_key_expired)

Status: active as a configuration, dead as a credential. Two independent live probes in this window both returned HTTP 401 on the Go endpoint:

probe 1 (this audit, 2026-11-08 00:2x):  zen_go_http=401
  {"error":{"type":"authentication_error","code":"api_key_expired",
    "message":"This API key has expired. Create a new API key in OpenCode Console and
                replace it in your client or secret store. …"}}
  — the same 401 for `https://opencode.ai/zen/go/v1/models`, and `~/.local/share/opencode/auth.json`
    still lists an *OpenCode Go api* entry (the CLI's own store).
probe 2 (2026-11-07):  provider=opencode-go (fields `key`, `type`) → HTTP 401, body
    `{"error":{"type":"authentication_error","code":"api_key_expired", …}}`
  • This is upstream expiry, not a Hermes fault: the key was issued by the OpenCode console and has run out. Hermes is still configured for the provider (opencode-go/<model-id>, per the table above), and router bridges exist (ollama-opencode-go-deepseek-v4-flash, -glm-5*, -grok-4_6, -kimi-k2_5, …).
  • No 2026-11-07 execution failed on an auth error — the day's three failures were all the gateway restart drain (incidents/2026-11-07-cron-claim-loss-in-gateway-restart-drain), so nothing in the fleet was actually consuming this provider in-window. The risk is latent: anything pinned to it fails on first use.
  • To restore: mint a new key in the OpenCode console, then replace it in both stores — the Hermes provider entry and ~/.local/share/opencode/auth.json — and re-probe …/zen/go/v1/models for a 200. (Keys live in the vault; this page records only their state — the hermes-api-vault skill (vault-backed; no value is stored in this wiki).)

Config format: opencode-go/<model-id> (e.g. opencode-go/kimi-k3)

Model list API: https://opencode.ai/zen/go/v1/models

2026-11-11 — the expired credential is no longer latent: it is in the live fallback path

The 2026-11-08 record above closed with "No execution failed on an auth error — nothing in the fleet was actually consuming this provider in-window. The risk is latent: anything pinned to it fails on first use." That latent risk has now fired, repeatedly.

  • fallback_providers[1] is opencode-zen / deepseek-v4.1-flash (https://opencode.ai/zen/v1, api_mode: chat_completions) — i.e. the second hop of every session fallback chain.

  • On 2026-11-11 it produced 7 × HTTP 401 api_key_expired, each one immediately after the hop above it (nous anthropic/claude-haiku-4.5) returned 404 insufficient_credits_for_paid_model:

    # nous 404 opencode-zen 401
    1 07:01:11 07:01:13
    2 07:19:28 07:19:30
    3 08:03:38 08:03:40
    4 13:03:27 13:03:28
    5 13:19:31 13:19:33
    6 18:03:38 18:03:39
    7 19:19:37 19:19:39
  • Two consecutive dead hops on one chain: a paid model with no credit, then an expired key. Every affected turn has to fall through to custom:guacano / custom:litellm / kilocode to succeed.

  • ⚠ Nothing in the fleet is pinned to opencode-zen — no cron job names it — so this never shows up as a job failure. It shows up only as agent.chat_completion_helpers: Streaming failed before delivery: Error code: 401 in ~/.hermes/logs/errors.log. → incidents/2026-10-22-nous-portal-refresh-token-invalid

To restore: mint a new key in the OpenCode console and replace it in both stores (the Hermes provider entry and ~/.local/share/opencode/auth.json), then re-probe …/zen/go/v1/models for a 200 — or remove opencode-zen from fallback_providers, since a dead second hop costs a round-trip on every retry. Keys live in the vault; this page records only their state — the hermes-api-vault skill (vault-backed; no value is stored in this wiki).

Privacy

Zero-retention policy from providers — your data is not used for model training.

Goals

  • Make AI coding accessible via low cost subscription
  • Provide reliable access to the best open coding models
  • Curate tested and benchmarked models for coding agent use
  • No lock-in (use any other provider too)