Muse Glimmer 30B: A Practical Local Model for OpenClaw
Muse Glimmer 30B local guide: 24 GB hardware fit, llama.cpp setup catches, OpenClaw limits, vendor benchmarks, and a practical evaluation plan.
Models
LLM Models
Current AI model guides organized by active, preview, restricted, and historical status, with source-labeled pricing and benchmark evidence.
Use this section to answer two separate questions: what is newest, and what can be used normally today. An announced model can be newer without being generally available.
Active Models
These are the current generally usable lanes in this comparison set.
Claude Sonnet 5
The first Claude cost/performance test before Opus API pricing: 1M context, 128K maximum output, $2/$10 introductory pricing through August 31, then $3/$15. Launch comparisons are vendor evidence; retain Opus for highest-accuracy arbitration.
Claude Opus 5
The new premium Claude baseline for architecture, consequential agentic coding, knowledge work, and final arbitration. It keeps $5/$25 pricing, adds five effort levels, and scored 61 at max effort on the Artificial Analysis Intelligence Index.
GLM-5.2
Z.AI’s current flagship coding model: 1M context, 128K maximum output, $1.40/$4.40 input/output pricing, and Artificial Analysis Index 51. Treat it as a value lane to test, not a proven Opus replacement.
Kimi K3
Moonshot’s newest Kimi flagship: 2.8T vendor-stated parameters, 1M context, native vision, $0.30/$3/$15 cache-hit/input/output pricing, and Artificial Analysis Index 57. Official weights and serving materials are released under the Kimi K3 License; self-hosting cost and AIHackers CAR remain unverified.
Kimi K2.7 Code
Moonshot’s cheaper routine Kimi coding API lane, with base and HighSpeed model IDs, 256K context, multimodal input, required thinking mode, and $0.95/$4.00 cache-miss input/output pricing.
GPT-5.6 Sol, Terra, and Luna
OpenAI’s generally available family across ChatGPT, Codex, and API: Sol is the flagship at $5/$30, Terra is the balanced tier at $2/$12, and Luna is the high-volume tier at $0.20/$1.20. These are standard short-context rates; requests above 272K input use higher long-context rates. See GPT-5.6 Luna Is OpenAI’s Value Default for subscription ranges, API economics, and the CAR decision.
DeepSeek V4 Flash 0731
DeepSeek’s direct-API and MIT-weight value candidate: 1M context, $0.14 cache-miss input, $0.0028 cache-hit input, and $0.28 output. Artificial Analysis scores 0731 at 50 and places it on its intelligence-versus-cost Pareto frontier; high output use, an 84% hallucination rate, and site-owned not-run status keep it in the evaluate-first lane.
Active supporting lanes
- GPT-5.5 — retained for existing integrations and historical comparisons.
- MiniMax M3 — 1M-context value coding-agent lane to test.
- Xiaomi MiMo — low-cost long-context and open-weight evaluation lane.
- Gemini 3 Flash — Gemini high-context value lane.
- Gemma 4 — local and open model family.
Guarded and restricted: Fable and Mythos
Claude Fable 5 and Mythos 5
Keep these models out of default routing for different reasons. Anthropic restored Fable globally on native Claude surfaces July 1, but included usage is plan-specific, cloud rollout is incomplete, and safeguards and retention still matter. Mythos remains approved-organization access.
- Fable 5: restored globally on native Claude surfaces; $10/$50 guarded escalation, not a default lane.
- Mythos 5: restored to approved US organizations; not a self-serve production option.
- Default premium lane: use Opus 5 after Sonnet 5; keep Fable guarded and Mythos access-specific.
Current Evidence Table
benchmark artifact
Current Model Status, Cost, and Evidence
| Model | Provider | Status | Context | Input price | Output price | Coding signal | Tool-use signal | Benchmark evidence | Speed | Verdict | Sources | Checked |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| GPT-5.6 Sol | OpenAI | active Generally available through ChatGPT paid plans, Codex paid plans, and the OpenAI API; plan and effort options vary. | 1.05M | $5.00 / 1M | $30.00 / 1M | Artificial Analysis reports 80 on its Coding Agent Index at max effort; OpenAI reports 64.6% on SWE-bench Pro. | Generally available in API and paid Codex plans; max and ultra modes are vendor-documented. |
| OpenAI announced a selected-customer Cerebras preview for July; production latency is not verified. | Generally available flagship; test on real tasks and apply stronger controls for agentic or cyber work. | OpenAI GPT-5.6 general availability [archive], OpenAI API pricing [archive], Artificial Analysis GPT-5.6 evaluation [archive], Agent Arena leaderboard, OpenAI GPT-5.6 availability [archive], OpenAI GPT-5.6 system card | 2026-08-01 |
| GPT-5.6 Terra | OpenAI | active Generally available through ChatGPT Work, Codex including Free and Go, and the OpenAI API. | 1.05M | $2.00 / 1M | $12.00 / 1M | Artificial Analysis reports 77 on its Coding Agent Index at max effort; OpenAI reports 63.4% on SWE-bench Pro. | Generally available in API and Codex, including the Free and Go Codex lane. |
| not verified | Generally available balanced lane; compare accepted-task cost with Sol, Luna, and other providers. | OpenAI GPT-5.6 general availability [archive], OpenAI GPT-5.6 price update [archive], OpenAI API pricing [archive], Artificial Analysis GPT-5.6 evaluation [archive], Agent Arena leaderboard, OpenAI GPT-5.6 availability [archive], OpenAI GPT-5.6 system card | 2026-08-01 |
| GPT-5.6 Luna | OpenAI | active Generally available through paid ChatGPT Work/Codex plans and the OpenAI API. | 1.05M | $0.20 / 1M | $1.20 / 1M | Artificial Analysis reports 75 on its Coding Agent Index at max effort; BenchLM ranks Luna #6/129 in coding with an Estimated overall position. | Generally available in API and paid Codex plans. |
| Vendor-positioned as fastest; measured production latency is not verified. | Generally available lowest-cost GPT-5.6 tier; verify quality and cost per accepted task. | OpenAI GPT-5.6 general availability [archive], OpenAI GPT-5.6 price update [archive], OpenAI API pricing [archive], OpenAI GPT-5.6 Luna model page [archive], Artificial Analysis GPT-5.6 evaluation [archive], Agent Arena leaderboard, BenchLM GPT-5.6 Luna profile [archive], OpenAI GPT-5.6 availability [archive], OpenAI GPT-5.6 system card | 2026-08-01 |
| DeepSeek V4 Flash 0731 | DeepSeek | active Official 0731 release available through DeepSeek's direct API; MIT-licensed weights are published separately. OpenCode's promotional free route has unverified backend revision identity. | 1M | $0.14 / 1M | $0.28 / 1M | Artificial Analysis reports Intelligence Index 50, one point behind GPT-5.6 Luna at max effort; this is shortlist evidence, not a universal coding-quality claim. | DeepSeek documents tool calls, Responses API, and Anthropic-compatible access; real harness behavior remains workload-specific. |
| Independent write-up reports about 206M total output tokens for the Intelligence Index; production speed and accepted-task efficiency are not verified. | Direct-API and open-weight value candidate; test accepted-task cost, token use, hallucinations, and tool behavior before production routing. | DeepSeek V4 Flash 0731 update [archive], DeepSeek V4 Flash 0731 model card [archive], DeepSeek API pricing [archive], Artificial Analysis DeepSeek V4 Flash 0731, OpenCode Zen pricing [archive], AIHackers app-hacking field test | 2026-08-01 |
| GPT-5.5 | OpenAI | active Generally available prior-generation OpenAI model retained for existing integrations and comparisons. | 1.05M API; 400K Codex | $5.00 / 1M | $30.00 / 1M | not verified | not verified | not verified | not verified | Primary coding seat while ChatGPT/Codex limits fit the workload. | OpenAI GPT-5.5 API model page, OpenAI GPT-5.5 ChatGPT limits, Artificial Analysis: GPT-5.5, LMArena leaderboard dataset | 2026-06-28 |
| Claude Sonnet 5 | Anthropic | active Generally available across Claude plans, Claude Code, the Claude API, GitHub Copilot, and supported AWS paths. | 1M | $2.00 / 1M | $10.00 / 1M | Anthropic reports substantial coding and agentic gains over Sonnet 4.6; independent normalized results are pending. | Available in Claude Code and the Claude API; adaptive thinking is on by default. |
| No site-owned normalized latency result is verified. | First Claude cost/performance test before Opus 5; escalate only when the premium pass changes the accepted result. | Anthropic Claude Sonnet 5 launch [archive], Claude Sonnet 5 migration guide [archive], GitHub Copilot Claude Sonnet 5 launch [archive], Claude Sonnet 5 on AWS [archive], Artificial Analysis: Claude Opus 5 [archive] | 2026-07-25 |
| Claude Opus 5 | Anthropic | active Current premium Claude baseline; default on Max, strongest Pro model, and available through the Claude API and supported cloud platforms. | 1M | $5.00 / 1M | $25.00 / 1M | Anthropic reports major agentic-coding gains; Artificial Analysis reports joint first on its Coding Agent Index at xhigh. | Thinking is on by default; five effort settings materially change cost, latency, and task performance. |
| Artificial Analysis reports high/xhigh/max AA-Briefcase runtimes of 25.7/34.3/36.2 minutes per task; Fast mode is a separate API research preview. | Premium escalation for consequential agentic and knowledge work; compare complete-task cost against Sonnet 5 before default routing. | Anthropic Claude Opus 5 launch [archive], What's new in Claude Opus 5 [archive], Claude Opus 5 system card [archive], Claude models overview [archive], Claude API pricing [archive], Artificial Analysis: Claude Opus 5 [archive], Artificial Analysis: Claude Opus 5 on AA-Briefcase [archive] | 2026-07-25 |
| Claude Opus 4.8 | Anthropic | historical Still available, but superseded by Opus 5 for current premium comparisons. | 1M | $5.00 / 1M | $25.00 / 1M | Historical premium Claude baseline; use Opus 5 for new task-level comparisons. | Still available for pinned integrations; new Claude premium routing should test Opus 5. |
| Artificial Analysis measured 57.3 output tokens/s; provider and workload latency vary. | Historical premium baseline. Use Claude Opus 5 for current Claude premium routing. | Claude models overview [archive], Claude API pricing [archive], Artificial Analysis: Claude Opus 4.8 [archive], Artificial Analysis Intelligence Index v4.1, LMArena leaderboard dataset, Berkeley Function Calling Leaderboard | 2026-07-25 |
| Claude Fable 5 | Anthropic | active Generally available; temporary subscription allowances ended July 7 and current subscription use is through usage credits. | 1M | $10.00 / 1M | $50.00 / 1M | Anthropic reports frontier launch results; independent reproducible ranking is pending. | Guarded-domain requests can refuse or fall back; verify account behavior before routing. |
| Task latency varies; compare complete-task runtime before escalation. | High-cost guarded escalation only; use Opus 5 as the practical Claude premium baseline. | Claude models overview [archive], Claude API pricing [archive], Anthropic Fable 5 and Mythos 5 [archive], Anthropic Fable/Mythos access statement [archive], Anthropic Fable 5 redeployment [archive], Artificial Analysis: Claude Opus 5 [archive], Artificial Analysis: Claude Opus 5 on AA-Briefcase [archive] | 2026-07-25 |
| Claude Mythos 5 | Anthropic | restricted Restored to a set of approved US organizations; broader Glasswing access remains restricted. | 1M | $10.00 / 1M | $50.00 / 1M | General coding quality is not independently verified for an accessible production route. | Invitation-only research access; account and compliance approval required. |
| not verified | Restricted research context, not a normal production or buying recommendation. | Claude models overview [archive], Claude API pricing [archive], Anthropic Fable 5 and Mythos 5 [archive], Anthropic Fable/Mythos access statement [archive], Anthropic Fable 5 redeployment [archive] | 2026-07-01 |
| Kimi K3 | Moonshot AI | active Active Kimi API/product flagship; official weights and serving materials released under the Kimi K3 License. | 1M | $3.00 / 1M | $15.00 / 1M | Moonshot reports strong max-reasoning launch-suite coding and agent results; AIHackers repo eval is not verified. | Kimi API and Kimi Code support K3; Kimi docs warn to preserve full assistant history and avoid mid-session model switching. |
| Artificial Analysis reports 62 output tokens/s and flags high verbosity; measure total output cost per accepted task. | Test as Kimi's newest 1M-context frontier-adjacent lane; keep K2.7 Code for cheaper routine Kimi coding until K3 passes local CAR tests. | Kimi K3 launch blog [archive], Kimi K3 quickstart [archive], Kimi K3 API pricing [archive], Kimi K3 weights and license [archive], Kimi current model list [archive], Kimi Code model configuration, Artificial Analysis: Kimi K3 [archive] | 2026-08-01 |
| GLM-5.2 | Z.AI | active Current Z.AI flagship coding model and supported-tool value lane. | 1M | $1.40 / 1M | $4.40 / 1M | Z.AI reports 62.1 on SWE-Bench Pro and 81.0 on Terminal-Bench 2.1. | Supported-tool coding lane; BFCL score not imported. |
| Artificial Analysis flags higher output-token use; measure total cost per successful task. | July value pick to test for supported coding-tool workflows; keep Opus/GPT for final arbitration until local evals pass. | Z.AI GLM-5.2 overview [archive], Z.AI pricing [archive], Artificial Analysis: GLM-5.2 article [archive], Artificial Analysis Intelligence Index v4.1, SWE-bench, Berkeley Function Calling Leaderboard | 2026-06-28 |
| Kimi K2.7 Code | Moonshot AI | active Cheaper routine Kimi coding API lane; HighSpeed is the same model at higher token prices. | 256K | $0.95 / 1M | $4.00 / 1M | Kimi K2.7 Code remains the lower-cost 256K coding lane after K3; independent normalized benchmarks are not imported. | OpenAI-compatible API; thinking mode required in the documented K2.7 Code quickstart. |
| HighSpeed model ID exists at a higher token price; latency not independently measured here. | Cheaper routine Kimi coding API lane when Kimi routing fits and 256K context is enough. | Kimi K2.7 Code quickstart [archive], Kimi K2.7 Code pricing [archive], Kimi Code K2.7 release notes [archive], SWE-bench, Berkeley Function Calling Leaderboard | 2026-06-28 |
Independent, vendor, historical-preview, and site-owned evidence are labeled separately. Model availability, a weight release, or a vendor benchmark does not establish cost per successful task.
Do not compare scores without matching the benchmark variant and harness. SWE-bench Verified, SWE-Bench Pro, Terminal-Bench, Artificial Analysis, vendor preference tests, and site-owned repository tests answer different questions. Use How to Read AI Benchmarks to turn those results into a shortlist before running your own tasks.
Historical Guides
These pages remain indexable for older integrations, pricing history, and search intent. They are not current recommendations.
- Claude Opus 4.5 — historical Opus reference; use Opus 5.
- Claude Opus 4.8 — prior premium baseline; use Opus 5 for current routing.
- Claude Sonnet 4.6 — prior daily-production baseline; use Sonnet 5 for current routing.
- Kimi K2.5 — historical and older free-access context; use K3 for latest-Kimi searches and K2.7 Code for cheaper routine coding.
- GLM-5.1 — prior GLM release; use GLM-5.2.
- GLM 4.7 — legacy GLM guide.
Older model names can still be correct when a tool genuinely exposes that version or a dated article describes the period. They should not be relabeled as current leaders.
Selection Shortcuts
| Need | Start with | Escalate or compare with |
|---|---|---|
| Daily Claude production | Sonnet 5 | Opus 5 |
| Premium Claude review | Opus 5 | Fable only after access, cost, and compliance checks |
| Low-cost long-context coding | GLM-5.2 | Opus 5 or GPT-5.6 for arbitration |
| Latest Kimi frontier test | Kimi K3 | Opus 5 or GPT-5.6 for arbitration |
| Cheaper Kimi coding API | Kimi K2.7 Code | GLM-5.2 when 1M context matters |
| OpenAI production | GPT-5.6 Terra or Luna | GPT-5.6 Sol for harder work |
| Lowest-cost direct API or MIT weights | DeepSeek V4 Flash 0731 | Luna, GLM-5.2, or a stronger reviewed lane when acceptance fails |
| Local or private inference | Gemma 4 | Compare hardware and quantization fit |
See Budget Tier, Mid-Range, Premium, and Smart Spend for workload-specific decisions.
Related links
Last verified: August 1, 2026. Model access, prices, limits, safeguards, open-weight status, and benchmark positions can change independently.
Claude Opus 5: Cost, Benchmarks, and When to Use It
Claude Opus 5 pricing, availability, effort levels, independent cost-per-task evidence, migration changes, and practical routing against Sonnet 5 and Fable.
Kimi K3: Benchmarks, Pricing, and Open-Weights Status
Kimi K3 is Moonshot's 2.8T flagship with 1M context, source-labeled benchmark evidence, $3/$15 API pricing, and released weights under the Kimi K3 License.
Claude Sonnet 5 Guide
Claude Sonnet 5 pricing, 1M context, API migration changes, tokenizer cost implications, availability, and source-labeled launch evidence.
GPT-5.6 Sol, Terra, and Luna Guide
Current GPT-5.6 Sol, Terra, and Luna access, short- and long-context pricing, independent benchmark signals, and deployment controls.
Claude Opus 4.8 Historical Guide
Claude Opus 4.8 historical pricing and benchmark context, retained for older integrations after Opus 5 became the premium Claude baseline.
GLM-5.2: July Value Coding Pick
GLM-5.2 is the July best value coding model to test: 1M context, AA Index 51, $1.40/$4.40 API pricing, and Opus 4.8 comparison math.
Kimi K2.7 Code: Coding Model Guide
Kimi K2.7 Code is Moonshot's cheaper routine coding lane after K3: 256K context, base/HighSpeed pricing, source-labeled benchmark deltas, and eval caveats.
Xiaomi MiMo Guide: V2.5 API, Pricing & Open Weights
Source-backed guide to Xiaomi MiMo V2.5 API, Token Plan limits, open weights, pricing, hardware reality, privacy caveats, and where it fits.
MiniMax M3: Value Coding Model Guide
MiniMax M3 is a value coding model candidate with 1M context, multimodal input, Token Plan economics, and vendor-reported benchmark strength. Test it before replacing premium lanes.
GLM-5.1: Prior Low-Cost Coding Model Guide
GLM-5.1 is Z.AI's prior low-cost coding model context. Use GLM-5.2 for the current 1M-context GLM coding-model guide.
Gemma 4: Private Local AI From Phone to PC
Gemma 4 explained: official release facts, offline iPhone support for the edge models, and which version to start with on standard local hardware.
Qwen 3.6 Plus Preview: Free 1M-Context Eval on OpenRouter
Qwen 3.6 Plus Preview is currently a free OpenRouter-hosted eval path with a 1M token context window. Here is what is verified, what is still missing, and when value hunters should use it.
Gemini 3 Flash: 78% SWE-bench, $0.50/1M Input, 8x Cheaper Than Claude Opus
Google's Gemini 3 Flash delivers frontier coding performance with $0.50/1M input tokens, 65K output limit, and 1M context. Full benchmarks, pricing breakdown, and when to choose it over Claude Opus 4.5 or Kimi k2.5.
Kimi K2.5 Historical Guide
Historical Kimi K2.5 capabilities, benchmarks, and older free-access routes. Use Kimi K3 for newest-Kimi decisions and K2.7 Code for cheaper coding decisions.
GLM 4.7: Legacy Z.AI Model Guide
Legacy guide for Z.AI GLM 4.7. GLM-5.2 is now the current Z.AI coding-plan model; use this page for historical context and GLM-4.7 fallback routing.
Claude Opus 4.5 Historical Guide
Historical Claude Opus 4.5 guide with current routing notes. Compare Sonnet 5, Opus 5, restored Fable 5, and GPT-5.6 before buying premium capacity.