Deprecation scheduled
The maker plans to deprecate it on 31 Jan 2027, within the next 180 days.
xAI · Chat
Latest Grok 4 with vision and tool support.
Evidence and sources
The maker plans to deprecate it on 31 Jan 2027, within the next 180 days.
Maker's price: $6.00 blended / 1M, pricier than 7 of 9 priced peers.
Supported operations and provider-stated features
| 256K | $3.00cache read $0.75 | $15.00 | |
| 256K | $2.85 | $14.25 | |
| 262K | $3.00 | $15.00 | |
| 256K | $3.00 | $15.00 | |
| 256K | $3.00cache read $0.75 | $15.00 | |
| 256K | $3.00 | $15.00 | |
| 256K | $3.00cache read $0.75 | $15.00 | |
| —Not published by the provider | $3.00 | $15.00 | |
| 256K | $3.00>128k $6.00cache read $0.75 | $15.00>128k $30.00cache write $3.00 | |
| —Not published by the provider | $3.00 | $15.00 |
Showing 10 of 19: the maker's own listing first, then the cheapest per 1M input tokens from each provider.
Also sold by Abacus, Aihubmix, Llmgateway Providers, Oci, Poe, Replicate, Vercel AI Gateway.
2 listings without a price are hidden.
Named effort levels run from lowest to highest. Select a result to see its source details.
| Benchmark | Score |
|---|---|
| Safety: BBQ - BBQ accuracy | |
| AIR-Bench: AIRBench 2024 - #1: Confidentiality | |
| AIR-Bench: AIRBench 2024 - #2: Integrity | |
| AIR-Bench: AIRBench 2024 - #3: Availability |
| Benchmark | Score |
|---|---|
| Apex | |
| AIME 2025 | |
| Apex Shortlist | |
| BRUMO 2025 |
| Benchmark | Score |
|---|---|
| CMIMC 2025 | |
| HMMT Feb 2025 | |
| HMMT Nov 2025 | |
| IMO 2025 | |
| Kangaroo 2025 1-2 | |
| Kangaroo 2025 3-4 | |
| Kangaroo 2025 5-6 | |
| Kangaroo 2025 7-8 | |
| Kangaroo 2025 9-10 | |
| Kangaroo 2025 11-12 | |
| Project Euler | |
| SMT 2025 |
| Benchmark | grok-4 |
|---|---|
| ALT_バイアス | |
| ALT_倫理・道徳 | |
| ALT_制御性 | |
| ALT_堅牢性 |
Data credits: Aider LLM Leaderboards (Aider-AI), Apache-2.0 (licence) · Epoch AI Benchmarking Hub, CC BY 4.0 (licence) · Data by LLM Stats · LMArena, CC BY 4.0 (licence) · Berkeley Function-Calling Leaderboard (Gorilla, UC Berkeley), Apache-2.0 (licence) · CyBench — cite Zhang et al. 2025 · EQ-Bench (Samuel J. Paech) — cite paech2023eqbench · FinSearchComp, CC BY 4.0 (licence) · Galileo Agent Leaderboard, Apache-2.0 (licence) · Stanford HELM (Stanford CRFM); scenario scores from Capabilities, Safety, Long Context, MedHELM, AIR-Bench, MMLU and Finance · MathArena (ETH SRI / INSAIT), MIT — cite dekoninck2026matharena (licence) · Nejumi Leaderboard 4, Weights & Biases Japan; public publisher-selected numeric evaluation results · Phare (Giskard), CC BY 4.0 (licence) · Clinical Benchmarks (clinicalbenchmarks.ai), CC BY 4.0; fractions converted to percentages; source documents retain their own terms (licence)
news.ycombinator.com
news.ycombinator.com
191 points, 96 comments
news.ycombinator.com
2 points, 1 comment
news.ycombinator.com
Also known as: azure_ai/grok-4, grok-4-0709, grok-4-search, oci/xai.grok-4, replicate/xai/grok-4, vercel_ai_gateway/xai/grok-4, x-ai/grok-4, xai/grok-4
Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works