Reasoning Grok for document-heavy analysis and long-horizon tool use
Specification
xai listing
Price
US dollars per million tokens · xai list price
Batch and priority prices
US dollars per million tokens · per listing
| Price | Listing | $/M |
|---|---|---|
| Batch input | xai | $1.00 |
| Batch output | xai | $2.00 |
Batch input is 20% below the interactive input price at the same listing.
Long-context price tiers
the rate above each context threshold
| Above | Price | $/M |
|---|---|---|
| 200K | Cache read | $0.40 |
| 200K | Input | $2.50 |
| 200K | Output | $5.00 |
Quality
6 benchmarks · 1 source
Every score
one row per source and configuration — nothing averaged away
| Benchmark | Score | Configuration | Source | Run |
|---|---|---|---|---|
| GPQA diamond | 89.3 ±1.9 | default | Epoch AI | 2026-07-13 |
| OTIS Mock AIME 2024-2025 | 92.2 ±3.3 | default | Epoch AI | 2026-07-13 |
| Chess Puzzles | 29.0 ±4.6 | default | Epoch AI | 2026-10-13 |
| FrontierMath-Tiers-1-3-v2 | 44.9 ±3.0 | default | Epoch AI | 2026-07-13 |
| SimpleQA Verified | 30.2 ±1.5 | default | Epoch AI | 2026-08-27 |
| FrontierMath-Tier-4-v2 | 17.1 ±5.9 | default | Epoch AI | 2026-07-13 |
The leading figure for a benchmark is the median across its configurations, so one heroic high-effort run cannot set the number.
Available from 8 hosts
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| xaivendor | $1.25 | $2.50 | $0.20 | — | 1M | 1M | — |
| kilo · x-ai | $1.25 | $2.50 | $0.20 | — | 2M | 1.8M | — |
| nano-gpt · x-ai | $1.25 | $2.50 | $0.20 | — | 2M | 131K | — |
| openrouter · x-ai | $1.25 | $2.50 | $0.20 | — | 2M | 1.8M | — |
| venice | $1.42 | $2.83 | $0.23 | — | 2M | 128K | — |
| kyma · kyma | $1.763 | $3.528 | — | — | 2M | 8K | — |
| oci · oci | $3.00 | $15.00 | — | — | 131K | 131K | — |
| ofox · x-ai | $4.00 | $12.00 | $0.40 | — | 2M | 128K | — |
Price history
append-only observations · a listing writes a row only when its price moves
| Date | Host | Field | $/M |
|---|---|---|---|
| 2026-09-02 | nano-gpt · x-ai | Cache read | $1.00 |
| 2026-10-19 | nano-gpt · x-ai | Cache read | $0.20 |
| 2026-09-02 | nano-gpt · x-ai | Input | $2.00 |
| 2026-10-19 | nano-gpt · x-ai | Input | $1.25 |
| 2026-09-02 | nano-gpt · x-ai | Output | $6.00 |
| 2026-10-19 | nano-gpt · x-ai | Output | $2.50 |
Other listings of this model
this page is one of them
The corpus files Grok 4.20 (Reasoning) under several keys. This page is the grok-4-20 listing. The full record — every host, every price and every benchmark score — is on the main Grok 4.20 (Reasoning) page.
More from xAI
most-hosted first