# Grok 4.3

> xAI's current flagship: 1M-token context, reasoning and tool calling, tuned for agentic chat and coding.

_The Frontier Model Matrix · /models/grok-4-3 · [JSON](/api/models/grok-4-3) · [all The Frontier Model Matrix](/models)_

- **name:** Grok 4.3
- **vendor:** xAI
- **model_id:** grok-4.3
- **context_window:** 1M
- **max_output:** 30K
- **input_per_mtok:** $1.25
- **output_per_mtok:** $2.50
- **strengths:** xAI's current flagship: 1M-token context, reasoning and tool calling, tuned for agentic chat and coding.
- **provider:** xAI
- **family:** Grok 4
- **release_date:** — (verify-against-primary-at-build)
- **last_updated:** 2026-06-15
- **open_weights:** false (source: https://docs.x.ai/docs/models)
- **license:** proprietary (source: https://docs.x.ai/docs/models)
- **params_total:** — (verify-against-primary-at-build)
- **params_active:** — (verify-against-primary-at-build)
- **tool_call:** true (source: https://models.dev/models/xai/grok-4.3/)
- **reasoning:** always (source: https://models.dev/models/xai/grok-4.3/)
- **structured_output:** true (source: https://models.dev/models/xai/grok-4.3/)
- **attachment:** — (verify-against-primary-at-build)
- **temperature:** true (source: https://models.dev/models/xai/grok-4.3/)
- **knowledge_cutoff:** — (verify-against-primary-at-build)
- **context_advertised:** 1M (source: https://models.dev/models/xai/grok-4.3/)
- **context_effective:** — (verify-against-primary-at-build)
- **price_input:** $1.25 (source: https://models.dev/models/xai/grok-4.3/)
- **price_output:** $2.50 (source: https://models.dev/models/xai/grok-4.3/)
- **price_cache_read:** — (verify-against-primary-at-build)
- **price_cache_write:** — (verify-against-primary-at-build)
- **cost_per_full_window:** — (verify-against-primary-at-build)
- **cost_per_agent_task:** — (verify-against-primary-at-build)
- **modalities:** text-in,text-out (source: https://models.dev/models/xai/grok-4.3/)
- **gpqa_diamond:** — (verify-against-primary-at-build)
- **swe_bench_verified:** — (verify-against-primary-at-build)
- **terminal_bench:** — (verify-against-primary-at-build)
- **tau2_bench:** — (verify-against-primary-at-build)
- **bfcl_tool_use:** — (verify-against-primary-at-build)
- **aa_index:** — (verify-against-primary-at-build)
- **lmarena_elo:** — (verify-against-primary-at-build)
- **tokens_per_sec:** — (verify-against-primary-at-build)
- **ttft:** — (verify-against-primary-at-build)
- **hallucination_rate:** — (verify-against-primary-at-build)
- **agent_readiness_score:** — (verify-against-primary-at-build)
- **score_confidence:** partial
- **source_url:** https://models.dev/models/xai/grok-4.3/
- **source_type:** models.dev
- **last_verified:** 2026-06-15
- **_provenance_note:** Required context_window (1M) and price ($1.25/$2.50) cross-confirmed by xAI's own docs (https://docs.x.ai/docs/models) AND models.dev. release_date/knowledge_cutoff left as placeholders (sources conflicted).