Skip to content

feat: add google/gemini-4-carbon (tool-verified) - #13

Merged
VickyXAI merged 1 commit into
mainfrom
feat/gemini-4-carbon
Nov 11, 2026
Merged

VickyXAI merged 1 commit into
mainfrom
feat/gemini-4-carbon

Conversation

@VickyXAI

Copy link
Copy Markdown
Contributor

Adds google/gemini-4-carbon to the capability snapshot: 1M context, 65,536 max output, vision, supportsTools: true. Carbon is Google's most capable Gemini 4 reasoning model (complex SWE, deep math/science, long agent work); Argon is the efficient Gemini 4.

Tool evidence. On the BlockRun base gateway, a two-round tool history through both the stream and non-stream paths returned Carbon's own next tool call (finish_reason: tool_calls), with no fallback. That is recorded in scripts/probe-tools.json along with where it came from. It was not run through probe-model-profiles.mjs, so there is no latency profile yet, and a re-probe overwrites the entry. Carbon joins VERIFIED_TOOL_FALLBACKS, the same admission rule as GPT-6.1 Sol and DeepSeek V4.1 Flash (#10).

Not live yet. The gateway listing is BlockRunAI/blockrun#1035. Until it deploys, blockrun.ai does not list Carbon. VERIFIED_TOOL_FALLBACKS only offers models that are priced in the host's live catalog (modelPricing), so nothing routes to Carbon before then.

Generated file. model-capabilities.ts is exactly what sync-model-capabilities.mjs outputs for the 2026-11-08 catalog plus a Carbon row; I ran the script to confirm. The current live listing also has anthropic/claude-fable-5.2, which I left for its own sync. Argon and Mistral Large 4 are unchanged (fail closed), and a new test now pins both.

Decision snapshot. Across all 88 decisions, no primary, tier or cost changes. The 20 tool decisions each gain Carbon as a trailing fallback candidate (candidates=N goes up by 1).

Tests: npm run check passes (typecheck, 192/192 vitest, build). dist/ is rebuilt.

Pricing for hosts: $2/$10 per 1M (cache $0.10) through 2026-11-30, then $4/$20 (cache $0.20), the same as Argon. Router-core takes pricing from the host catalog.

🤖 Generated with Claude Code

Gemini 4 Carbon is Google's most capable Gemini 4 reasoning model (complex
software engineering, deep math and science, long agent work); Argon is the
efficient Gemini 4. Same shape as Argon: 1M context, 65,536 max output,
vision. The gateway listing is BlockRunAI/blockrun#1035; until that deploys,
blockrun.ai's /api/v1/models does not carry it.

Unlike Argon, Carbon has tool evidence: on the BlockRun base gateway a
two-round tool history through both the stream and non-stream paths returned
Carbon's own next tool call (finish_reason tool_calls), no fallback. It is
recorded in probe-tools.json with its source (not probe-model-profiles.mjs, so
no latency profile), written supportsTools: true, and joins
VERIFIED_TOOL_FALLBACKS, which only offers a model the host's live catalog
prices, so nothing routes to it before the gateway lists it.

model-capabilities.ts is the sync script's output for the 2026-11-08 catalog
plus a Carbon row (verified by running it); a newer live listing also carries
anthropic/claude-fable-5.2, left for its own sync. Argon and Mistral Large 4
stay fail-closed, now pinned by a test.

Decision snapshot: 0 of 88 primaries, tiers or costs move; the 20 tool
decisions gain Carbon as a trailing fallback candidate. README counts and
dist/ updated.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
@VickyXAI
VickyXAI merged commit 2c2d0a5 into main Nov 11, 2026
2 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant