xAI's frontier model for long-running agents, coding, knowledge work, and visual projects
Grok 4.6 by xai is offered by 30 providers on this page. Public prices are shown for 29 of them. Its official list price is $2.00 per 1M input tokens and $6.00 per 1M output tokens. It also has 1 free ($0) channel; free tiers usually carry rate limits, and subscription-covered access bills $0 per token only after the subscription fee.
Artificial Analysis rates it 44.3 on the Intelligence Index, with 76.8 for coding and 53 for agentic tasks. Against its lowest blended price of $3.00 per 1M, that is roughly 15 index points per dollar, which is the value ratio the leaderboards rank on. Median output speed is 59 tokens per second, with 37.63s to the first token. Running one task of the Artificial Analysis suite costs about $1.4848, which reflects how many tokens its reasoning consumes rather than the unit price alone.
The context window is 500,000 tokens at the reference host, but hosts report different limits, from 200,000 to 524,288, so the usable window depends on the provider you pick. It supports reasoning, tool use, and structured output. Accepted input modalities are Text, Image, and PDF. Its training knowledge cuts off at 2026-02-01.
Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| Kenari grok-4-6 | Gateway | Free | — | — | 500,000 | 500,000 | ||
| Perplexity Agent | Gateway | $2.00 tiered >200K: $4.00 | $6.00 | $0.50 | — | 500,000 | 500,000 | |
| NanoGPT | Gateway | $2.00 | $6.00 | $0.50 | — | 500,000 | 450,000 | |
| Kilo Gateway | Gateway | $2.00 | $6.00 | $0.50 | — | 500,000 | 450,000 | |
| Abacus | Gateway | $2.00 | $6.00 | $0.50 | — | 500,000 | 32,768 | |
| 302.AI | Gateway | $2.00 | $6.00 | — | — | 500,000 | 500,000 | |
| OpenRouter | Gateway | $2.00 tiered >200K: $4.00 | $6.00 | $0.50 | — | 500,000 | 450,000 | |
| Azure | Cloud | $2.00 | $6.00 | $0.50 | — | 200,000 ⚠ | 128,000 | beta |
| ZenMux | Gateway | $2.00 tiered >200K: $4.00 | $6.00 | $0.50 | — | 500,000 | 500,000 | |
| OCI Generative AI xai.grok-4.6 | Cloud | $2.00 tiered >200K: $4.00 | $6.00 | $0.50 | — | 500,000 | 500,000 | |
| xAIOfficial | First-party | $2.00 tiered >200K: $4.00 | $6.00 | $0.50 | — | 500,000 | 500,000 | |
Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.
Interleaved thinking (reasoning between tool calls) is declared by 1 of 30 providers.
3 / 30 providers expose no reasoning control (reasoning_options: []).
1 more channels offer $0 (Kenari); free tiers usually have rate limits and no SLA, excluded from ranking.
| Name | Conditions | Score | Metric | Source |
|---|---|---|---|---|
| CursorBench | variant: high effort · v4.0 | 40.4 | score | Source ↗ |
| DeepSWE | variant: high effort · v1.1 | 65.2 | score | Source ↗ |
| EEBench | variant: high effort | 53 | score | Source ↗ |
| AA-Briefcase | variant: high effort · v1.1 | 1546 | Elo | Source ↗ |
| Terminal-Bench | variant: high effort · v4.0 | 20.3 | score | Source ↗ |
| Harvey Legal Agent Benchmark | variant: high effort | 15.8 | score | Source ↗ |
| HealthBench | variant: high effort; professional | 48.5 | score | Source ↗ |
| GDPval | variant: high effort | 1605 | Elo | Source ↗ |
The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.
Individual evaluations run by Artificial Analysis, on the same reasoning tier as the intelligence score above. Each benchmark has its own task set and harness, so rows are not comparable with one another. The Intelligence Index above draws on a different, newer set of evaluations.