GitHub Copilot + Google Plugin Capabilities#

Date: April 15, 2026 For: Guillaume Descoteaux-Isabelle Context: Evaluating cloud AI provider plugins for OpenClaw to complement local Ollama inference on Mac Mini. Guillaume has existing GitHub Copilot and OpenAI Codex subscriptions.

---

Executive Summary#

• The GitHub Copilot provider is a bundled, first-class OpenClaw extension that gives Guillaume $0 marginal cost access to 17+ models — including GPT-4.1, GPT-5 family (5-mini, 5.2, 5.3-Codex, 5.4), Claude Sonnet/Opus 4.5–4.6, Claude Haiku 4.5, Gemini 2.5 Pro, and more. Authentication uses a GitHub device-login flow; no API key needed. GPT-4.1 usage is unlimited for paid Copilot users; premium models consume monthly quota (300/mo on Pro, 1,500/mo on Pro+). (Source: GitHub Copilot Docs, GitHub Copilot Plans)
• The Google plugin is a multi-capability powerhouse — providing Gemini LLM chat, image generation (Gemini Flash Image), video generation (Veo 3.1), music generation (Lyria 3), media understanding, and web search via Gemini Grounding. Requires a separate GEMINI_API_KEY from Google AI Studio (free tier available with rate limits). (Source: OpenClaw monorepo extensions/google/)
• The Perplexity plugin is a web-search-only provider (not an LLM provider) with structured search, domain filtering, and AI-synthesized answers. Requires its own subscription — $20/month for API access. (Source: OpenClaw extensions/perplexity/, Perplexity Pricing)
• All three cloud plugins run simultaneously alongside local Ollama using OpenClaw's primary + fallbacks routing model. Each occupies a different capability niche (LLM inference vs. web search vs. media generation). (Source: OpenClaw model providers documentation)
• Anthropic blocked direct OAuth tokens on April 4, 2026 for all consumer subscription tiers (Free/Pro/Max/Team). However, Claude models remain accessible at $0 via the Copilot provider — the Anthropic block only affects direct Anthropic API tokens, not Copilot's proxy access. (Source: TechCrunch, dev.to, aitoolsrecap.com)

---

Copilot Provider Deep Dive#

Architecture#

The github-copilot provider is a bundled OpenClaw extension maintained in the official monorepo at extensions/github-copilot/. It is enabled by default and handles authentication, model discovery, transport selection, and token exchange — all without requiring a separate API key or VS Code. (Source: OpenClaw monorepo — extensions/github-copilot/openclaw.plugin.json)

Authentication: OAuth Device-Login Flow#

# One-time setup
openclaw models auth login-github-copilot
# 1. OpenClaw prints a URL and device code
# 2. Visit the URL in your browser
# 3. Enter the device code
# 4. Authorize — token stored in auth profile

At runtime, OpenClaw exchanges the stored GitHub token for a short-lived Copilot API token. The device-login flow token takes precedence over environment variables.

Environment variable fallbacks (if device-login not used):

(Source: OpenClaw extensions/github-copilot/ source code)

Transport Auto-Selection#

The provider automatically selects the correct API transport based on the model ID:

// From extensions/github-copilot/models.ts
export function resolveCopilotTransportApi(
  modelId: string,
): "anthropic-messages" | "openai-responses" {
  return (normalizeOptionalLowercaseString(modelId) ?? "").includes("claude")
    ? "anthropic-messages"
    : "openai-responses";
}

• Claude model IDs → anthropic-messages transport
• GPT/o-series/Gemini → openai-responses transport
• Selection is automatic — no user configuration needed

Complete Model Catalog (Corrected, April 2026)#

⚠️ Critical correction: The initial research listed gpt-4o as a current model. GPT-4o is deprecated in GitHub Copilot, replaced by GPT-4.1. All configuration examples in this document use the corrected model IDs. (Source: GitHub blog changelog)

(Source: GitHub Copilot Supported Models, reviewer verification April 2026)

Forward compatibility: The provider has a catch-all mechanism — any unknown model ID is accepted and synthesized as a dynamic model definition. If GitHub Copilot adds gpt-6 tomorrow, you set it in config without waiting for an OpenClaw update. The Copilot API rejects unavailable models at request time.

Premium Request Quotas#

While all model costs through the Copilot provider are technically $0, GitHub enforces premium request quotas for certain models. This is a critical nuance the initial research oversimplified.

Key facts:

• GPT-4.1 is unlimited for all paid Copilot users — does not consume premium requests
• GPT-5 mini code completions are unlimited
• Premium models (Claude Opus, GPT-5.4, o1) consume monthly quota
• Additional requests: $0.04/request beyond monthly quota on all paid tiers
• Model availability depends on plan tier — Free and Student plans cannot manually select flagship models

(Source: GitHub Copilot Plans & Pricing, GitHub Copilot Docs)

Copilot vs Direct API Access: Tradeoffs#

For most of Guillaume's workflows, the Copilot provider offers excellent value. For intensive agentic workloads requiring large context windows or sustained high-throughput, direct API keys may be worth the cost.

Memory Search Embeddings#

The Copilot provider also serves as an embedding provider for OpenClaw's memory search — a valuable bonus feature:

• Auto-detected at priority 15 (after local embeddings, before paid OpenAI)
• Discovers embedding models from the Copilot /models endpoint
• Prefers text-embedding-3-small
• No separate API key needed — reuses Copilot auth

{
  agents: {
    defaults: {
      memorySearch: {
        provider: "github-copilot",
        model: "text-embedding-3-small"
      }
    }
  }
}

(Source: OpenClaw extensions/github-copilot/ source code)

Anthropic OAuth Block — What It Means#

On April 4, 2026, Anthropic blocked all consumer subscription OAuth tokens (Free, Pro, Max, Team) in third-party tools including OpenClaw. This means:

• ❌ You cannot use your personal Anthropic account to access Claude directly in OpenClaw
• ✅ You can still use Claude models via the Copilot provider — Copilot's proxy access is unaffected
• ✅ You can use a separate Anthropic API key (pay-as-you-go billing) if you need direct Anthropic access

For Guillaume: this block is irrelevant because Claude access via Copilot subscription still works fine. (Source: Confirmed via TechCrunch, dev.to, natural20.com, kersai.com)

---

Google Plugin Deep Dive#

Overview#

The Google plugin (extensions/google/ in the OpenClaw monorepo) is the most capability-rich single plugin in OpenClaw. It registers itself as a provider for five distinct capability contracts: media understanding, image generation, music generation, video generation, and web search. (Source: OpenClaw monorepo extensions/google/openclaw.plugin.json)

Complete Capabilities Matrix#

Available Models#

⚠️ Note on model naming: Some model names (e.g., "Gemini 3.1 Pro") from the initial research may be preview/speculative naming. Verified current models include Gemini 2.5 Pro and Gemini 3 Flash. Always check openclaw models list --provider google for the latest available models.

Authentication#

Method 1: API Key (recommended)

# Get a key from Google AI Studio (https://aistudio.google.com/)
export GEMINI_API_KEY="your-key-here"
# Or use OpenClaw onboarding:
openclaw onboard --auth-choice gemini-api-key

Method 2: Gemini CLI OAuth (unofficial)

# Install Gemini CLI
brew install gemini-cli  # or: npm install -g @google/gemini-cli
# Login via OpenClaw
openclaw models auth login --provider google-gemini-cli --set-default

⚠️ The OAuth method is an unofficial integration — some users report Google account restrictions. The API key method is more reliable.

API key rotation: Google supports multiple API keys for high-throughput use:

• GEMINI_API_KEYS (comma-separated)
• GEMINI_API_KEY_1, GEMINI_API_KEY_2, etc.
• GOOGLE_API_KEY (fallback)
• OPENCLAW_LIVE_GEMINI_KEY (single override)

Google API Free Tier Limits (April 2026)#

Google AI Studio offers a free tier with no billing required, but with rate limits:

Important changes (early 2026):

• December 2025: Google reduced free limits by 50–80% due to abuse
• March/April 2026: Pro models now require paid tier — free tier only works with Flash and Flash-Lite models
• Paid tier pricing: Gemini 2.5 Pro at ~$1.25/M input tokens, $10/M output tokens; Flash models significantly cheaper ($0.10/M input)

(Source: Google AI Studio pricing, bswen.com free tier limits)

Plugin Manifest Contracts#

{
  "contracts": {
    "mediaUnderstandingProviders": ["google"],
    "imageGenerationProviders": ["google"],
    "musicGenerationProviders": ["google"],
    "videoGenerationProviders": ["google"],
    "webSearchProviders": ["gemini"]
  }
}

This makes the Google plugin the only single plugin that provides five distinct capability types. No other plugin comes close to this breadth.

---

Perplexity Plugin#

Role: Dedicated Web Search Provider#

The Perplexity plugin (extensions/perplexity/ in the OpenClaw monorepo) is a web search provider only — it is NOT an LLM provider. It gives OpenClaw agents the ability to search the web with rich filtering, complementing local models that have no internet access. (Source: OpenClaw extensions/perplexity/openclaw.plugin.json)

Configuration#

openclaw plugins install @openclaw/perplexity-plugin
openclaw config set 'tools.web.search' --json '{
  "provider": "perplexity",
  "apiKey": "$PERPLEXITY_API_KEY"
}'

Three configuration fields:

Two Search Modes (Auto-Selected by Key Prefix)#

Native API filtering (pplx- keys only):

• Country: 2-letter code (us, ca, fr)
• Language: ISO 639-1 (en, fr)
• Date range: day, week, month, year
• Domain filters: allow/deny list (max 20 domains)
• Content budget: max_tokens, max_tokens_per_page

Perplexity vs Google (Gemini Grounding) for Web Search#

When to use Perplexity instead of Google:

• You need date-range filtering (e.g., "only results from last week")
• You need domain-specific filtering (e.g., "only results from arxiv.org")
• You want structured citation data separate from the LLM response
• You're using OpenRouter and want to consolidate API keys

When to use Google instead of Perplexity:

• You already have a Gemini API key (no additional subscription needed)
• You want search results integrated directly into the LLM conversation
• You want to minimize the number of services you manage

Perplexity Pricing#

No free API tier. API access requires paid credits:

For Guillaume's usage: Light web-search augmentation would cost approximately $20/month (Pro sub) + $5–10/month in token usage = ~$25–30/month.

(Source: Perplexity Pricing, deploybase.ai pricing)

---

How Cloud + Local Work Together#

OpenClaw's Routing Model#

OpenClaw uses a primary + fallbacks model configuration per agent. This is an ordered failover chain — not round-robin or load-balanced.

{
  agents: {
    defaults: {
      // LLM: Copilot primary (unlimited GPT-4.1), local fallback
      model: {
        primary: "github-copilot/gpt-4.1",
        fallbacks: ["github-copilot/gpt-5.2", "ollama/gemma4", "ollama/llama3.3"]
      },
      // Image generation: Google (only option — Ollama can't do this)
      imageGenerationModel: {
        primary: "google/gemini-3.1-flash-image-preview"
      },
      // Memory embeddings: Copilot (free with subscription)
      memorySearch: {
        provider: "github-copilot",
        model: "text-embedding-3-small"
      }
    }
  },
  tools: {
    web: {
      search: {
        // Choose: "gemini" (free tier) or "perplexity" ($20/mo)
        provider: "gemini"
      }
    }
  }
}

Practical Routing Decisions#

Privacy-Based Routing#

OpenClaw supports policy-based routing that automatically directs sensitive work to local models:

{
  models: {
    routing: {
      policy: {
        sensitive: "ollama/*",              // Private data stays local
        general: "github-copilot/gpt-4.1",  // General tasks use cloud
        code: "github-copilot/gpt-5.3-codex" // Code tasks use optimized model
      }
    }
  }
}

Failover Behavior#

1. OpenClaw tries the primary model first
2. On failure (rate limit, timeout, context overflow, overload), falls to next in fallbacks
3. Each provider classifies its own error types via classifyFailoverReason
4. Cooldown probes prevent hammering a failed provider
5. Session-override persistence lets a conversation stick to a provider mid-session

Practical example: If Guillaume hits his 300 monthly premium requests on Copilot/Claude Opus, the failover chain automatically routes to ollama/gemma4 locally — ensuring uninterrupted service without manual intervention.

---

Cost Analysis#

What Guillaume Already Pays For#

What Needs Separate API Keys#

Total Incremental Cost Scenarios#

Bottom line: Guillaume's existing Copilot subscription already provides substantial cloud AI access at no additional cost. The Google plugin's free tier adds multimodal capabilities for $0. Perplexity is the main optional expense at ~$25–30/month. The Copilot provider alone — with 17+ models, unlimited GPT-4.1, and free embeddings — represents exceptional value relative to direct API pricing.

Premium Request Budget Planning#

With Copilot Pro (300 premium requests/month):

If Guillaume needs more premium requests, options include:

• Upgrade to Copilot Pro+ ($39/month) for 1,500 requests/month
• Purchase additional requests at $0.04/request
• Route more queries to Ollama local models or GPT-4.1 (unlimited)

---

Sources#

Official Documentation & Source Code#

1. OpenClaw GitHub Repository — https://github.com/openclaw/openclaw (~250K stars)
   • extensions/github-copilot/openclaw.plugin.json — Copilot plugin manifest
   • extensions/github-copilot/models-defaults.ts — Default Copilot model catalog
   • extensions/github-copilot/models.ts — Transport selection + forward-compat logic
   • extensions/google/openclaw.plugin.json — Google plugin manifest
   • extensions/perplexity/openclaw.plugin.json — Perplexity plugin manifest
   • docs/providers/github-copilot.md — Copilot provider setup guide
   • docs/providers/google.md — Google/Gemini provider setup guide
   • docs/providers/perplexity-provider.md — Perplexity provider setup guide
2. GitHub Copilot Supported Models — https://docs.github.com/en/copilot/reference/ai-models/supported-models
3. GitHub Copilot Plans & Pricing — https://github.com/features/copilot/plans
4. GitHub Copilot Docs — Plans — https://docs.github.com/en/copilot/get-started/plans

Deprecation & Model Changes#

5. GPT-4o / Claude Deprecation in Copilot — https://github.blog/changelog/2026-01-13-upcoming-deprecation-of-select-github-copilot-models-from-claude-and-openai/
6. Copilot Model Comparison — https://docs.github.com/en/copilot/reference/ai-models/model-comparison
7. Student Plan Model Removal — https://piunikaweb.com/2026/03/14/github-copilot-student-plan-removes-premium-models-like-claude-opus-and-sonnet/

Pricing Sources#

8. Perplexity Pricing 2026 — https://screenapp.io/blog/perplexity-pricing
9. Perplexity API Token Costs — https://deploybase.ai/articles/perplexity-api-pricing
10. Google Gemini API Free Tier — https://findskill.ai/blog/gemini-api-pricing-guide/
11. Google AI Studio Free Tier Limits — https://docs.bswen.com/blog/2026-03-23-google-ai-studio-free-tier-limits/
12. Gemini API Paid Pricing — https://deploybase.ai/articles/gemini-api-pricing-2026

Anthropic OAuth Block#

13. Anthropic OAuth Block (April 4, 2026) — Confirmed via dev.to, TechCrunch, natural20.com, kersai.com, aitoolsrecap.com

Comparison & Analysis#

14. OpenClaw vs Hermes Agent Comparison — https://www.vibesparking.com/en/blog/ai/openclaw/2026-04-09-openclaw-vs-hermes-agent-deep-comparison/
15. Hermes Migration from OpenClaw — https://hermes-agent.nousresearch.com/docs/guides/migrate-from-openclaw/
16. Verdent.ai: Claw Code vs OpenClaw — https://www.verdent.ai/guides/claw-code-claude-code-vs-openclaw
17. Copilot Practical Guide (Microsoft Tech Community) — https://techcommunity.microsoft.com/blog/azuredevcommunityblog/choosing-the-right-model-in-github-copilot-a-practical-guide-for-developers/4491623

---

Final document compiled April 15, 2026. All reviewer corrections incorporated. GPT-4o references replaced with GPT-4.1. GPT-5 family and Claude Opus/Haiku models added. Premium request quota information included. All claims sourced.