Grok 4.20 Reasoning
Grok 4 20 0309 is an xAI Grok model for reasoning, coding, vision, and general conversational tasks.
- Input / output price
- $1.25 / $2.50 per 1M
- Context
- 1M tokens
- Released
- Mar 10, 2026
Paste into Claude Code, Cursor, or Codex
Help me set up the Respan gateway: fetch and follow https:/
Providers
2 providers, cheapest first, priced per 1M tokens after gateway discounts.
| Provider | Input | Output |
|---|---|---|
Perplexity perplexity/grok-4.20-reasoning | $1.25/M | $2.50/M |
xAI xai/grok-4.20-reasoning | $1.25/M | $2.50/M |
Is a provider down? Perplexity status, Grok status
Pricing
Averaged across 2 providers, in USD per 1M tokens after gateway discounts.
- Average input
- $1.25 per 1M
- Average output
- $2.50 per 1M
- Average cache read
- $0.20 per 1M
Cost by volume
Total cost from 0 to 1T tokens.
Throughput and latency
30-day averages from requests through the Respan gateway. Under each figure, every model on the gateway by its average, this one in blue.
Output speed
Higher is better11tokens/sacross providers
Response latency
Lower is better2.2sacross providers
Benchmarks
7 published scores from 2 sources, each linked to where it was published.
Published scores
| Benchmark | Score | Source | Published |
|---|---|---|---|
| GPQA DiamondEpoch AI | 89.3% | Epoch AI | Oct 5, 2026 |
| Chess PuzzlesEpoch AI | 29% | Epoch AI | Oct 28, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| OTIS Mock AIME 2024-2025Epoch AI | 92.2% | Epoch AI | Oct 5, 2026 |
| FrontierMath Tiers 1-3 v2Epoch AI | 44.9% | Epoch AI | Oct 5, 2026 |
| FrontierMath Tier 4 v2Epoch AI | 17.1% | Epoch AI | Oct 5, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| SimpleQA VerifiedEpoch AI | 30.2% | Epoch AI | Oct 5, 2026 |
Apps
Use Grok 4.20 Reasoning in the tools you already run. Each guide points the app at the Respan gateway.
Setup guides for more apps are in the integration docs.
Grok 4.20 Reasoning FAQ
Short answers, built from the data on this page.
Grok 4.20 Reasoning is a model from xAI, released on Mar 10, 2026. Grok 4 20 0309 is an xAI Grok model for reasoning, coding, vision, and general conversational tasks.
On the Respan gateway, Grok 4.20 Reasoning costs $1.25 per 1M input tokens and $2.50 per 1M output tokens on every provider, after gateway discounts.
Grok 4.20 Reasoning is available through 2 providers: Perplexity and xAI.
Grok 4.20 Reasoning accepts up to 1M tokens of context on its largest provider route.
Point any OpenAI-compatible SDK at https://gateway.respan.ai/v1 with your Respan API key and set the model to "xai/grok-4.20-reasoning". To set it up with a coding agent, copy the agent setup prompt at the top of this page.
Grok 4.20 Reasoning has 7 published benchmark scores, including GPQA Diamond 89.3%, OTIS Mock AIME 2024-2025 92.2%, and SimpleQA Verified 30.2%. Each score links to where it was published; the data is collected by Respan.
Certified where it counts.
Built to meet the security and privacy standards that enterprise and healthcare teams require.
ISO 27001
The internationally recognized standard for information security management.
SOC 2
Secure, compliant management of your data across all of our systems.
GDPR
Operated under GDPR, the world's strictest standard for data privacy.
HIPAA
HIPAA compliant, with a BAA available for healthcare teams.