Auto-generated page. This page is automatically built by a scheduled CI pipeline that runs twice daily. The data below is a snapshot of five public sources, cross-referenced programmatically.
Last generated: 2026-11-19 11:09 UTC
Data sources:
- OpenCode Go API – unauthenticated metadata endpoint listing all models in the Go catalog
- Models.dev – provider/model metadata including costs, release dates, and deprecation status
- OpenCode Go Documentation – official docs page, source of the documented model list
- OpenCode Go console – public Go plan page with per-model request estimates
- Artificial Analysis – independent benchmark scores used for the value ranking
This is an unofficial tracker. Not affiliated with or endorsed by OpenCode or Anomaly.
If you spot missing or incorrect information, please reach out so I can fix or improve the page generation.
This page tracks every model available through OpenCode Go, the $10/month subscription for open coding models. The pipeline queries the five sources above, merges their data, and regenerates this page.
Looking for a single model? The model details page lists benchmarks, pricing, request estimates and availability for each of the 42 models.
Quick Stats#
| Metric | Count |
|---|---|
| Documented (listed on Go docs page) | 32 |
| API metadata endpoint (all models in catalog) | 31 |
| Models.dev registry | 42 |
| Undocumented (in API metadata, not on docs page) | 0 |
| Deprecated | 9 |
| Total tracked | 42 |
The 32 documented models match what a typical Go subscriber sees when running /models in the OpenCode TUI. The API metadata endpoint returns the same 31 models: since November 2026 the docs page no longer publishes a separate subscriber shortlist, so its per-model table and the catalog match one-to-one.
Benchmarks & Value#
Pricing alone does not tell you which model to use. This section adds independent benchmark data from Artificial Analysis — the same evaluations run for the closed frontier models — and ranks the Go catalogue for the Go plan.
Three numbers drive the ranking:
- Intelligence Index — Artificial Analysis’ composite across reasoning, coding, knowledge and agentic evaluations, out of 100. Higher is better.
- Req/5h — requests per 5-hour window on Go. On a flat $10 plan every model costs the same, so this is what separates them.
- Index × Req/5h — capability per window. This is the sort order below.
Value score = Intelligence Index ÷ blended list price (input:output 1:3). It prices the public list price, not your Go subscription, so treat it as a market signal rather than what you will pay.
Benchmark data exists for 19 of the 42 tracked models, and 16 of those have a composite index. Preview, contributor and free-tier variants usually fall through — see benchmark coverage for the gaps.
Where to start#
| Model | On Go docs | Index | Req/5h | Index × req/5h | Speed | TTFT | Value | Best coding eval |
|---|---|---|---|---|---|---|---|---|
| MiMo-V2.6-Flash | yes | 26.7 | 30,100 | 804,503 | 41 | 4.9 s | 109.1 | T-B 4.0 22.7% |
| DeepSeek V4.1 Flash 1017 | yes | 18.5 | 43,300 | 801,619 | 146 | 1.2 s | 38.0 | T-B 4.0 9.1% |
| GLM-5.3-Flash | yes | 27.8 | 6,320 | 175,720 | 57 | 3.3 s | 67.4 | T-B 4.0 32.8% |
| GLM-5.3 | yes | 23.1 | 6,600 | 152,512 | 65 | 2.9 s | 6.3 | T-B 4.0 34.8% |
| Claude Haiku 5.5 | yes | 29.9 | 3,850 | 115,016 | 227 | 19.0 s | 74.7 | T-B 4.0 21.7% |
On Go docs: yes marks a model on the official Go docs list – what a typical subscriber sees with /models. — means it is in the API catalog but not documented there: usually usable, but it depends on your subscription, so check /models in the TUI.
Speed (tok/s) and TTFT (seconds to first token) are Artificial Analysis’ measurements on each model’s own vendor API, not on OpenCode Go. They are the right tiebreaker when capability and quota are close: a model that answers four times faster changes how an agent session feels, even when the index is a point lower.
Interactive explorer#
Filter by benchmark tag, cap the price, and click any column header to sort. First click sorts best-first (cheapest-first for price), second click reverses it. Everything runs client-side — no tracking, no requests.
- AA Index
- Artificial Analysis composite, 0–100. Higher is better.
- Value
- Index ÷ blended $/1M: capability per dollar.
- T-B 4.0
- Terminal-Bench 4.0 — task completion in a real terminal. The closest public proxy for a coding agent.
- FC 2.0
- FrontierCode 2.0 — hard multi-file software engineering.
- $/1M
- Blended list price per 1M tokens, input:output 1:3. Not the Go price.
- Req/5h
- Requests per 5-hour window on the Go plan, from the public Go plan page. ∞ = free, unlimited. Blank = no estimate published for it.
- Speed
- Output tokens per second, measured by Artificial Analysis against the model’s own (first-party) API — not OpenCode Go’s serving path, so treat it as relative. The same open-weight model runs at very different speeds on different hosts.
- TTFT
- Seconds until the first output token, same measurement. Low is better; reasoning models can still take much longer to produce a first answer token, which the details page reports separately.
- SciCode / GPQA
- Scientific Python; graduate-level science reasoning.
| Model | Index | Value | T-B 4.0 | FC 2.0 | $/1M | Req/5h | Speed | TTFT |
|---|---|---|---|---|---|---|---|---|
| Qwen4 MaxAlibabaagentic coding+2↗ | 42.9 | 11.4 | 48.5% | 26.5% | $3.75 | 463 | 56 | 6.3 s |
| Hy4Tencentagentic coding+2↗ | 34.6 | 16.6 | 37.4% | 31.4% | $2.08 | 2,710 | 95 | 2.6 s |
| Kimi K3.1 ProKimiagentic coding+3↗ | 46.5 | 5.8 | 67.2% | 25.5% | $8.00 | 147 | 31 | 3.6 s |
| MiniMax M3.1 FlashMiniMaxbest value+2↗ | 29.1 | 59.6 | 25.8% | 20.8% | $0.49 | 3,880 | 128 | 1.3 s |
| DeepSeek V4.1 Flash 1017DeepSeeklong context↗ | 18.5 | 38.0 | 9.1% | 6.1% | $0.49 | 43,300 | 146 | 1.2 s |
| Gemini 4 ArgonGoogleagentic coding+3↗ | 47.6 | 6.0 | 55.1% | 25.0% | $8.00 | 566 | 58 | 15.1 s |
| Claude Haiku 5.5Anthropicbest value+2↗ | 29.9 | 74.7 | 21.7% | 23.2% | $0.40 | 3,850 | 227 | 19.0 s |
| MiMo-V2.6-ProXiaomilong context↗ | 29.9 | 39.3 | 34.8% | 24.0% | $0.76 | 3,260 | 56 | 3.9 s |
| MiMo-V2.6-FlashXiaomibest value+2↗ | 26.7 | 109.1 | 22.7% | 21.6% | $0.24 | 30,100 | 41 | 4.9 s |
| GPT-6 LunaOpenAIbest value+1↗ | 23.5 | 58.6 | 8.1% | 18.4% | $0.40 | 4,230 | 100 | 16.2 s |
| Grok 4.7SpaceXAIstrong↗ | 31.1 | 6.2 | 16.2% | 21.8% | $5.00 | 169 | 68 | 14.6 s |
| Step 5 PreviewStepFunlong context↗ | 28.5 | 12.5 | 33.3% | 12.0% | $2.27 | 426 | 156 | 0.9 s |
| GLM-5.3-FlashZ AIbest value+2↗ | 27.8 | 67.4 | 32.8% | 17.6% | $0.41 | 6,320 | 57 | 3.3 s |
| GLM-5.3Z AIlong context↗ | 23.1 | 6.3 | 34.8% | 12.7% | $3.65 | 6,600 | 65 | 2.9 s |
| LongCat-2.0LongCatlong context↗ | — | — | 0.0% | — | $0.97 | 11,400 | 58 | 3.3 s |
| Kimi K2.7 CodeKimi↗ | — | — | 1.0% | — | $3.24 | 994 | 56 | 6.3 s |
| Qwen3.7 PlusAlibabalong context↗ | — | — | 1.0% | — | $1.30 | 4,310 | 56 | 2.8 s |
| MiniMax-M3MiniMaxlong context↗ | 18.9 | 19.4 | 2.0% | 21.9% | $0.97 | 3,210 | 91 | 2.3 s |
| DeepSeek V4 ProDeepSeeklong context↗ | 23.1 | 14.0 | 14.1% | 17.1% | $1.65 | 1,040 | 87 | 2.4 s |
All benchmark scores#
Same columns as the key above, sorted by intelligence index. No JavaScript needed.
| Model | AA Index | Value | T-Bench 4.0 | FrontierCode 2.0 | SciCode | GPQA | Blended $/1M | Go req/5h | Speed (tok/s) | TTFT | Time/Task |
|---|---|---|---|---|---|---|---|---|---|---|---|
| Gemini 4 Argon | 47.6 | 6.0 | 55.1% | 25.0% | 58.9% | — | $8.00 | 566 | 58 | 15.1 s | 29.1 min |
| Kimi K3.1 Pro | 46.5 | 5.8 | 67.2% | 25.5% | 60.8% | — | $8.00 | 147 | 31 | 3.6 s | 39.3 min |
| Qwen4 Max | 42.9 | 11.4 | 48.5% | 26.5% | — | — | $3.75 | 463 | 56 | 6.3 s | 31.4 min |
| Hy4 | 34.6 | 16.6 | 37.4% | 31.4% | — | — | $2.08 | 2,710 | 95 | 2.6 s | 13.6 min |
| Grok 4.7 | 31.1 | 6.2 | 16.2% | 21.8% | 54.9% | — | $5.00 | 169 | 68 | 14.6 s | 10.5 min |
| MiMo-V2.6-Pro | 29.9 | 39.3 | 34.8% | 24.0% | 60.9% | — | $0.76 | 3,260 | 56 | 3.9 s | 36.0 min |
| Claude Haiku 5.5 | 29.9 | 74.7 | 21.7% | 23.2% | 48.7% | — | $0.40 | 3,850 | 227 | 19.0 s | 6.5 min |
| MiniMax M3.1 Flash | 29.1 | 59.6 | 25.8% | 20.8% | 53.4% | — | $0.49 | 3,880 | 128 | 1.3 s | 17.9 min |
| Step 5 Preview | 28.5 | 12.5 | 33.3% | 12.0% | 58.9% | — | $2.27 | 426 | 156 | 0.9 s | 12.1 min |
| GLM-5.3-Flash | 27.8 | 67.4 | 32.8% | 17.6% | 51.6% | 91.2% | $0.41 | 6,320 | 57 | 3.3 s | 39.4 min |
| MiMo-V2.6-Flash | 26.7 | 109.1 | 22.7% | 21.6% | 51.3% | — | $0.24 | 30,100 | 41 | 4.9 s | 53.1 min |
| GPT-6 Luna | 23.5 | 58.6 | 8.1% | 18.4% | 51.7% | — | $0.40 | 4,230 | 100 | 16.2 s | 7.3 min |
| GLM-5.3 | 23.1 | 6.3 | 34.8% | 12.7% | 42.0% | — | $3.65 | 6,600 | 65 | 2.9 s | 13.4 min |
| DeepSeek V4 Pro | 23.1 | 14.0 | 14.1% | 17.1% | 51.0% | 92.8% | $1.65 | 1,040 | 87 | 2.4 s | 18.9 min |
| MiniMax-M3 | 18.9 | 19.4 | 2.0% | 21.9% | 47.1% | 92.9% | $0.97 | 3,210 | 91 | 2.3 s | 16.7 min |
| DeepSeek V4.1 Flash 1017 | 18.5 | 38.0 | 9.1% | 6.1% | 38.5% | — | $0.49 | 43,300 | 146 | 1.2 s | 7.4 min |
Models with individual benchmark results but no composite index yet (Artificial Analysis has not finished scoring them):
| Model | T-Bench 4.0 | FrontierCode 2.0 | SciCode |
|---|---|---|---|
| LongCat-2.0 | 0.0% | — | 36.3% |
| Kimi K2.7 Code | 1.0% | — | 47.8% |
| Qwen3.7 Plus | 1.0% | — | 46.1% |
Benchmark coverage#
No benchmark data exists for 23 of 42 models. Artificial Analysis only evaluates publicly available endpoints, so preview, contributor and free-tier variants usually fall through the cracks:
Beam Free, Cat Jam Free, Crouton Alpha Free, GLM-5.2, GPT-5.6 Luna, Gemini 4 Argon Contributor, Hy3, Hy4 flash Free, Hy4 preview, Iceman Contributor Free, Kimi K3, LongCat 2.5 Free, LongCat 2.5 Preview Free, MiMo V2.5, MiMo V2.5 Pro, MiniMax M3.1 Flash Free, MiniMax-M2.7, Muse Spark 1.2 Contributor, Muse Spark 1.3 Contributor, Qwen3.8 Flash, Qwen3.8 Max, Space Bunny, Step 5 Preview Free
How to read this#
- The index is a composite, not a coding score. A model can rank high overall and still lose on agentic coding — check T-B 4.0 before trusting a top-of-table position.
- Small score differences do not matter. Treat gaps under two index points as noise.
- Speed is a separate axis. A model can win on index and quota and still feel sluggish: check Speed and TTFT before committing to it for interactive work. AA measures the vendor API, not the Go plan, so compare models against each other rather than trusting the absolute number.
- A high value score is not a recommendation. It means cheap capability, not the right capability. The cheapest model that fails your task is the most expensive one you can pick.
- Vendor-reported numbers and independent ones share a column. Where a score is marked as vendor-reported, treat it as an upper bound.
Scores are refreshed when the tracker runs and are sourced from Artificial Analysis; the full methodology explains how the index is built.
Changelog#
Changes detected since previous snapshot (2026-11-16).
Removed from API#
| Date | Model |
|---|---|
| 2026-11-19 | GLM-5.2 removed from OpenCode Go API |
Marked as Deprecated#
| Date | Model |
|---|---|
| 2026-11-19 | GLM-5.2 marked as deprecated |
Removed Models#
No longer available from any source. Dates come from the tracked history.
| Model | Removed |
|---|---|
| DeepSeek V4 Flash | 2026-11-10 |
| GLM-5 | 2026-11-10 |
| GLM-5.1 | 2026-11-10 |
| Hy3 Preview | 2026-11-10 |
| Kimi K2.5 | 2026-11-10 |
| Kimi K2.6 | 2026-11-10 |
| MiMo V2 Omni | 2026-11-10 |
| MiMo V2 Pro | 2026-11-10 |
| MiniMax M2.5 | 2026-11-10 |
| Qwen3.5 Plus | 2026-11-10 |
| Qwen3.6 Plus | 2026-11-10 |
| Qwen3.7 Max | 2026-11-10 |
Tracked History#
Every addition and removal recorded since tracking began (5 dates), newest first.
| Date | Change | Models |
|---|---|---|
| 2026-11-16 | Added | Hy4 flash Free, Qwen4 Max |
| 2026-11-10 | Added | Beam Free, Cat Jam Free, Claude Haiku 5.5, Crouton Alpha Free, DeepSeek V4.1 Flash 1017, GLM-5.2, +28 more |
| 2026-11-10 | Removed | DeepSeek V4 Flash, GLM-5, GLM-5.1, Hy3 Preview, Kimi K2.5, Kimi K2.6, +6 more |
| 2026-06-04 | Added | Qwen3.7 Plus |
| 2026-06-02 | Added | DeepSeek V4 Flash, DeepSeek V4 Pro, GLM-5, GLM-5.1, Hy3 Preview, Kimi K2.5, +11 more |
All Models#
| Model | Documented | Status | Release | Context | Input $/1M | Output $/1M | Cache Read | Req/5h | Sources |
|---|---|---|---|---|---|---|---|---|---|
| Qwen4 Max | yes | active | 2026-11-16 | 1M | $1.50 | $4.50 | $0.07 | 463 | API Models.dev Docs |
| Hy4 flash Free | yes | active | 2026-11-16 | 1M | $0 | $0 | $0 | ∞ | API Models.dev Docs |
| Hy4 | yes | active | 2026-11-04 | 1M | $0.83 | $2.50 | $0.04 | 2,710 | API Models.dev Docs |
| Crouton Alpha Free | removed | 2026-11-03 | 1M | $0 | $0 | $0 | — | Models.dev | |
| LongCat 2.5 Free | yes | active | 2026-11-02 | 1M | $0 | $0 | $0 | ∞ | API Models.dev Docs |
| Iceman Contributor Free | yes | active | 2026-10-24 | 262K | $0 | $0 | $0 | ∞ | API Models.dev Docs |
| Kimi K3.1 Pro | yes | active | 2026-10-23 | 1M | $2.00 | $10.00 | $0.20 | 147 | API Models.dev Docs |
| MiniMax M3.1 Flash Free | removed | 2026-10-19 | 1M | $0 | $0 | $0 | — | Models.dev | |
| MiniMax M3.1 Flash | yes | active | 2026-10-19 | 1M | $0.15 | $0.60 | $0.01 | 3,880 | API Models.dev Docs |
| DeepSeek V4.1 Flash 1017 | yes | active | 2026-10-17 | 1M | $0.15 | $0.60 | $0.003 | 43,300 | API Models.dev Docs |
| Gemini 4 Argon Contributor | removed | 2026-10-13 | 1M | $4.00 | $20.00 | $0.20 | — | Models.dev | |
| Gemini 4 Argon | yes | active | 2026-10-13 | 1M | $2.00 | $10.00 | $0.10 | 566 | API Models.dev Docs |
| Cat Jam Free | removed | 2026-10-12 | 1M | $0 | $0 | $0 | — | Models.dev | |
| Claude Haiku 5.5 | yes | active | 2026-10-07 | 1M | $0.10 | $0.50 | $0.01 | 3,850 | API Models.dev Docs |
| Beam Free | yes | active | 2026-10-05 | 1M | $0 | $0 | $0 | ∞ | API Models.dev Docs |
| LongCat 2.5 Preview Free | removed | 2026-09-25 | 1M | $0 | $0 | $0 | — | Models.dev | |
| Space Bunny | removed | 2026-09-23 | 1M | $0.15 | $0.60 | $0.03 | — | Models.dev | |
| MiMo-V2.6-Pro | yes | active | 2026-09-22 | 1M | $0.43 | $0.87 | $0.0036 | 3,260 | API Models.dev Docs |
| MiMo-V2.6-Flash | yes | active | 2026-09-22 | 1M | $0.14 | $0.28 | $0.0028 | 30,100 | API Models.dev Docs |
| GPT-6 Luna | yes | active | 2026-09-22 | 1M | $0.10 | $0.50 | $0.01 | 4,230 | API Models.dev Docs |
| Grok 4.7 | yes | active | 2026-09-21 | 500K | $2.00 | $6.00 | $0.50 | 169 | API Models.dev Docs |
| Step 5 Preview Free | removed | 2026-09-16 | 1M | $0 | $0 | $0 | — | Models.dev | |
| Step 5 Preview | yes | active | 2026-09-16 | 1M | $1.00 | $2.70 | $0.10 | 426 | API Models.dev Docs |
| Muse Spark 1.3 Contributor | yes | active | 2026-09-02 | 1M | $0.10 | $0.20 | $0.002 | 45,300 | API Models.dev Docs |
| Hy4 preview | yes | active | 2026-08-28 | 1M | $0.83 | $2.50 | $0.04 | 1,350 | API Models.dev Docs |
| Qwen3.8 Flash | yes | active | 2026-08-26 | 1M | $0.15 | $0.47 | $0.02 | 5,400 | API Models.dev Docs |
| GLM-5.3-Flash | yes | active | 2026-08-26 | 1M | $0.15 | $0.50 | $0.03 | 6,320 | API Models.dev Docs |
| GLM-5.3 | yes | active | 2026-08-14 | 1M | $1.40 | $4.40 | $0.26 | 6,600 | API Models.dev Docs |
| Muse Spark 1.2 Contributor | yes | active | 2026-08-05 | 1M | $0.10 | $0.20 | $0.002 | 45,300 | API Models.dev Docs |
| Qwen3.8 Max | yes | active | 2026-08-03 | 1M | $2.00 | $6.00 | $0.25 | 162 | API Models.dev Docs |
| Kimi K3 | yes | active | 2026-07-16 | 1M | $3.00 | $15.00 | $0.30 | 98 | API Models.dev Docs |
| GPT-5.6 Luna | yes | active | 2026-07-09 | 1M | $0.20 | $1.20 | $0.02 | 2,050 | API Models.dev Docs |
| Hy3 | yes | active | 2026-07-06 | 256K | $0.14 | $0.58 | $0.04 | 4,300 | API Models.dev Docs |
| LongCat-2.0 | yes | active | 2026-06-30 | 1M | $0.30 | $1.20 | $0.006 | 11,400 | API Models.dev Docs |
| GLM-5.2 | yes | 2026-06-13 | 1M | $1.40 | $4.40 | $0.26 | 792 | Models.dev Docs | |
| Kimi K2.7 Code | yes | active | 2026-06-12 | 262K | $0.95 | $4.00 | $0.19 | 994 | API Models.dev Docs |
| Qwen3.7 Plus | yes | active | 2026-06-02 | 1M | $0.40 | $1.60 | $0.04 | 4,310 | API Models.dev Docs |
| MiniMax-M3 | yes | active | 2026-06-01 | 1M | $0.30 | $1.20 | $0.06 | 3,210 | API Models.dev Docs |
| DeepSeek V4 Pro | yes | active | 2026-04-24 | 1M | $0.66 | $1.98 | $0.02 | 1,040 | API Models.dev Docs |
| MiMo V2.5 Pro | removed | active | 2026-04-22 | 1M | $0.43 | $0.87 | $0.0036 | — | Models.dev |
| MiMo V2.5 | removed | active | 2026-04-22 | 1M | $0.14 | $0.28 | $0.0028 | — | Models.dev |
| MiniMax-M2.7 | removed | 2026-03-18 | 205K | $0.30 | $1.20 | $0.06 | — | Models.dev |
Model details#
Benchmarks, pricing, request estimates and source availability for every model are on the model details page.
Undocumented Models#
None this run: every model in the API metadata endpoint also appears in the model table on the official Go documentation page. The page previously published a shorter subscriber list; since November 2026 the docs table covers the whole catalog, so this split no longer separates restricted models.
Deprecated Models#
These models are marked as deprecated in Models.dev. They may still be available through the API but are likely to be removed.
| Model | Release Date | Replacement |
|---|---|---|
| Crouton Alpha Free | 2026-11-03 | — |
| MiniMax M3.1 Flash Free | 2026-10-19 | — |
| Gemini 4 Argon Contributor | 2026-10-13 | — |
| Cat Jam Free | 2026-10-12 | — |
| LongCat 2.5 Preview Free | 2026-09-25 | — |
| Space Bunny | 2026-09-23 | — |
| Step 5 Preview Free | 2026-09-16 | — |
| GLM-5.2 | 2026-06-13 | — |
| MiniMax-M2.7 | 2026-03-18 | — |
Source Availability Matrix#
| Model | API | Models.dev | Docs | Status |
|---|---|---|---|---|
| Qwen4 Max | yes | yes | yes | active |
| Hy4 flash Free | yes | yes | yes | active |
| Hy4 | yes | yes | yes | active |
| Crouton Alpha Free | — | yes | — | deprecated |
| LongCat 2.5 Free | yes | yes | yes | active |
| Iceman Contributor Free | yes | yes | yes | active |
| Kimi K3.1 Pro | yes | yes | yes | active |
| MiniMax M3.1 Flash Free | — | yes | — | deprecated |
| MiniMax M3.1 Flash | yes | yes | yes | active |
| DeepSeek V4.1 Flash 1017 | yes | yes | yes | active |
| Gemini 4 Argon Contributor | — | yes | — | deprecated |
| Gemini 4 Argon | yes | yes | yes | active |
| Cat Jam Free | — | yes | — | deprecated |
| Claude Haiku 5.5 | yes | yes | yes | active |
| Beam Free | yes | yes | yes | active |
| LongCat 2.5 Preview Free | — | yes | — | deprecated |
| Space Bunny | — | yes | — | deprecated |
| MiMo-V2.6-Pro | yes | yes | yes | active |
| MiMo-V2.6-Flash | yes | yes | yes | active |
| GPT-6 Luna | yes | yes | yes | active |
| Grok 4.7 | yes | yes | yes | active |
| Step 5 Preview Free | — | yes | — | deprecated |
| Step 5 Preview | yes | yes | yes | active |
| Muse Spark 1.3 Contributor | yes | yes | yes | active |
| Hy4 preview | yes | yes | yes | active |
| Qwen3.8 Flash | yes | yes | yes | active |
| GLM-5.3-Flash | yes | yes | yes | active |
| GLM-5.3 | yes | yes | yes | active |
| Muse Spark 1.2 Contributor | yes | yes | yes | active |
| Qwen3.8 Max | yes | yes | yes | active |
| Kimi K3 | yes | yes | yes | active |
| GPT-5.6 Luna | yes | yes | yes | active |
| Hy3 | yes | yes | yes | active |
| LongCat-2.0 | yes | yes | yes | active |
| GLM-5.2 | — | yes | yes | deprecated |
| Kimi K2.7 Code | yes | yes | yes | active |
| Qwen3.7 Plus | yes | yes | yes | active |
| MiniMax-M3 | yes | yes | yes | active |
| DeepSeek V4 Pro | yes | yes | yes | active |
| MiMo V2.5 Pro | — | yes | — | active |
| MiMo V2.5 | — | yes | — | active |
| MiniMax-M2.7 | — | yes | — | deprecated |
About This Page#
This page is automatically generated by a scheduled CI pipeline that queries five publicly accessible sources:
- OpenCode Go API – the unauthenticated metadata endpoint listing all models in the Go catalog
- Models.dev – provider/model metadata including costs, release dates, and deprecation status
- OpenCode Go Documentation – the official docs page, source of the documented model list
- OpenCode Go console – the public Go plan page, source of the per-model request estimates
- Artificial Analysis – independent benchmark scores and public API pricing used for the value ranking
What this tracker can and cannot tell you#
What it verifies: which models exist in each public data source, their release dates, pricing, deprecation status, and when models are added to or removed from those sources.
What it cannot verify: which models your specific subscription entitles you to. The API metadata endpoint is unauthenticated and lists models that may not be available to all subscribers. To see which models you can actually use, run /models in the OpenCode TUI – that command authenticates with your API key.
The “Documented” column above reflects which models appear in the model table on the official docs page – those typically match what a standard Go subscription includes, but this is not independently verified by this tracker. Since November 2026 that table covers the whole catalog, so it no longer separates restricted models from standard ones.
This is an unofficial tracker. It is not affiliated with or endorsed by OpenCode or Anomaly.
See Also#
- OpenCode Go: Can $10/Month Open Models Replace Frontier APIs? — my detailed benchmark and analysis of the Go model lineup
- Building an LLM Gateway with LiteLLM and OpenCode Go Router — how I built a gateway to route between Go models
- OpenCode Go official page
