xAI · Chat
Grok 4.6
Grok 4.6 is xAI's multimodal chat and reasoning model with function calling, structured outputs, adjustable reasoning effort (low/medium/high/xhigh), and a 500K-token context window.
- llminfo IQ
- 138.0
- Maker's price
- $3.00 blended / 1M
- Max context
- 2M
- Listings
- 63
Evidence and sources
Advantages and trade-offs
Compared with 10 chat models, picked mainly by popularity and IQ
Advantages
Handles unusually long context
Advertised pdf input support
PDF input advertised by 3 of the 9 peers that list their features.
Trade-offs
Costs more than most peers
Maker's price: $3.00 blended / 1M, pricier than 6 of 9 priced peers.
No open weights
The weights aren't public, so you can't run it yourself.
Input & output
as stated by the model's providersCapabilities
Supported operations and provider-stated features
Listings
| 500K | $2.00>200k $4.00cache read $0.50 | $6.00>200k $12.00 | $2.00 | |
| 500K | $1.60cache read $0.40 | $4.80 | — | |
| 500K | $1.60cache read $0.40 | $4.80 | — | |
| —Not published by the provider | $1.90 | $5.70 | — | |
| 500K | $2.00cache read $0.50 | $6.00 | — | |
| 200K | $2.00>200k $4.00cache read $0.50 | $6.00>200k $12.00 | — | |
| 524K | $2.00>200k $4.00cache read $0.50 | $6.00>200k $12.00 | — | |
| 500K | $2.00cache read $0.50 | $6.00 | — | |
| 500K | $2.00cache read $0.50 | $6.00 | — | |
| 500K | $2.00cache read $0.50 | $6.00 | — |
Showing 10 of 56: the maker's own listing first, then the cheapest per 1M input tokens from each provider.
Also sold by Abacus, Cheapest Token, Cloudflare AI Gateway, Cometapi, Commandcode, Crossmodel, Databricks, Eden AI, Evolink, Fastrouter, Github Copilot, Gmicloud, Kenari, Kilo, Llmgateway, Llmgateway Providers, Meganova, Merge Gateway, NanoGPT, Near AI, Neon, Oci, Ofox, Opper, Orcarouter, Perplexity, Perplexity Agent, Prime, Requesty, Venice, Vercel, Wavespeed, Zenmux.
7 listings without a price are hidden.
Included in plans
Benchmarks
Named effort levels run from lowest to highest. Select a result to see its source details.
Human preference
| Benchmark | High |
|---|---|
| Arena ELO | |
| Chinese | |
| Creative Writing | |
| Document |
Show 55 more benchmarksHide 55 benchmarks
Multilingual
Show 34 more resultsHide 34 results
Coding
General
| Benchmark | Score |
|---|---|
| typos | |
| AMPS_Hard | |
| connections | |
| consecutive_events |
Show 15 more benchmarksHide 15 benchmarks
| Benchmark | Score |
|---|---|
| integrals_with_game | |
| javascript | |
| logic_with_navigation | |
| olympiad | |
| paraphrase | |
| plot_unscrambling | |
| python | |
| simplify | |
| spatial | |
| story_generation | |
| summarize | |
| tablejoin | |
| tablereformat | |
| theory_of_mind | |
| typescript |
Long context
Agentic
Show results from 2 providers and OpenRouter's automatic routingHide results from 2 providers and OpenRouter's automatic routing
- OpenRouter's automatic routing
- xAI
- Amazon Bedrock
| Benchmark | Score |
|---|---|
| Tax Agent Bench | |
| Finance Agent (v2) | |
| Harvey's Legal Agent Benchmark v1 | |
| Terminal-Bench 2.1 |
Show 2 more benchmarksHide 2 benchmarks
| Benchmark | Score |
|---|---|
| Terminal-Bench 4.0 | |
| Terminal-Bench-Science |
Reasoning
Science
Show results from 2 providers and OpenRouter's automatic routingHide results from 2 providers and OpenRouter's automatic routing
- OpenRouter's automatic routing
- xAI
- Amazon Bedrock
Math
Vision
Factuality
Instruction following
Knowledge
OCR
Other
Show 2 more resultsHide 2 results
Show 10 more resultsHide 10 results
Data credits: Data by LLM Stats · Epoch AI Benchmarking Hub, CC BY 4.0 (licence) · Clinical Benchmarks (clinicalbenchmarks.ai), CC BY 4.0; fractions converted to percentages; source documents retain their own terms (licence) · LMArena, CC BY 4.0 (licence) · Baromètre de l’écriture IA, Johannes Eva; public numeric ranking data, © 2026 Johannes Eva, no results licence stated · BullshitBench by Peter Gostev, MIT (licence) · CyberGym leaderboard (Wang, Shi, He, Cai, Zhang, Song; UC Berkeley), ICLR 2026. Results evaluated and submitted by the listed teams. No licence is stated for the result data; the repository's Apache-2.0 licence covers its code only. · Deep20Bench edition 1.1, Patrick Heusser. Results CC BY 4.0; native question scores and fraction-to-percent success rates. (licence) · Keelemudelite mõõdupuu: Independent LLM leaderboard for Estonian. Eesti Keele Instituut. https://moodupuu.eki.ee, CC BY 4.0. Latest per-benchmark results selected with partial-run flags retained. (licence) · OpenRouter public benchmark leaderboard and search-lane exports, CC BY 4.0. Fractional source scores converted to percentages; immutable dated snapshots. (licence) · LLM Chess by Maxim Saplin, Apache-2.0 (Copyright [2024] [Maxim Saplin]) (licence) · MineBench, MIT (licence) · Outback Yak Research, NepNewsBench v2 research draft. Public numerical aggregates from a candidate preview that the publisher says is not evidence of publication; no release licence assigned and none asserted here.
Around the web
- Discussion
- DeepSeek v4.1 Flash matched Opus5.5 and Grok4.7 on a diplomatic negotiation evalDiscussion
2 points, 0 comments
news.ycombinator.com
- HN discussion 50576967Discussion
news.ycombinator.com
- HN discussion 50578814Discussion
news.ycombinator.com
- HN discussion 50578886Discussion
news.ycombinator.com
Also known as: aihubmix/grok-4.6, aws-bedrock/grok-4-6, azure_ai/grok-4.6, bedrock_mantle/us-gov-east-1/xai.grok-4.6, bedrock_mantle/us-gov-west-1/xai.grok-4.6, bedrock_mantle/xai.grok-4.6, databricks/databricks-grok-4-6, github_copilot/grok-4.6, global.xai.grok-4.6, gmi/xai/grok4.6, grok 4.6, grok-4-6, grok-4.6-high, grok-4.6-xhigh, grok/grok-4.6, perplexity/xai/grok-4.6, spacexai/grok-4.6, us-gov.xai.grok-4.6, us.xai.grok-4.6, vertex-openai/grok-4-6, vertex_ai/xai/grok-4.6, x-ai/grok-4-6, x-ai/grok-4.6, x-ai/grok-4.6:batch, xai.grok-4.6, xai/grok-4-6, xai/grok-4.6, xai/grok4.6
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