Grok 4
by xAI
Prices last updated November 19, 2026
xAI's flagship reasoning model from July 2025 (grok-4-0709), with image input and a 256K-token context window. xAI has since retired it from its API in favour of Grok 4.20 and later Grok models.
Price Comparison
Compare pricing across 1 provider serving Grok 4
| Provider | Input $/1M | Output $/1M | Context | Speed | TTFT | Status |
|---|---|---|---|---|---|---|
Replicate | $7.20 ● | $36.00 | — | — | — | Down |
Benchmarks
Independent results for Grok 4, as each source publishes them. Where a source tested several versions (effort levels, thinking modes, dated snapshots), the best one is shown and named under "As tested". Scores from different sources use different scales and aren't comparable with each other.
| Benchmark | Score | Rank | As tested |
|---|---|---|---|
| Overall | |||
Epoch Capabilities IndexEpoch AI One score combining a model's results across many benchmarks, on a common scale. | 146.9±1.5 | #87 of 258 | Grok 4 |
| Reasoning | |||
GPQA DiamondEpoch AI Graduate-level multiple-choice questions in biology, physics and chemistry, written to be hard to look up. | 87.0%±3.9 | #76 of 232 | grok-4-0709 |
| Math | |||
OTIS Mock AIMEEpoch AI Competition maths problems from the OTIS mock AIME exams (2024-2025). | 84.0%±9.8 | #94 of 215 | grok-4-0709 |
| Coding | |||
Text Arena: CodingLMArena Text Arena votes on coding prompts only. | 1,435±7 8,011 votes | #186 of 421 | Grok 4 (0709) Nov 2026 |
| Chat | |||
Text ArenaLMArena Human votes on chat answers across all kinds of prompts (style-controlled). | 1,411±4 39,568 votes | #160 of 426 | Grok 4 (0709) Nov 2026 |
| Vision | |||
Vision ArenaLMArena Human votes on answers to prompts that include images (style-controlled). | 1,184±7 30,106 votes | #106 of 168 | Grok 4 (0709) Nov 2026 |
Epoch AI: Epoch runs each benchmark itself on the models it evaluates, with the same harness for every model. The Epoch Capabilities Index combines many benchmarks into one score. Data: Epoch AI, 'Capabilities & benchmarking', epoch.ai/benchmarks (CC BY 4.0).
LMArena: People compare two anonymous models side by side and vote for the better answer; ratings come from those votes (Bradley-Terry, style-controlled for text and vision). Data: LMArena (arena.ai) leaderboard dataset (CC BY 4.0).
Rank is among all models the source ranks, including ones we don't list.