grok-4.20-beta-0309-reasoning
xai · chat model
grok-4.20-beta-0309-reasoning is listed here as a chat model from xai. This page shows simple API pricing, token limits, and capability flags so you can compare it with similar options.
Input
$2.0000 / 1M tokens
Output
$6.0000 / 1M tokens
Cached input
$0.2000 / 1M tokens
Context
2.0M
Quick read
Best for
Use this page when you need a fast view of cost, context size, and supported features before testing the model in your own workload.
Things to verify
Always check the provider page for discounts, cache pricing, region rules, and any model limits that may not appear in public metadata.
Pricing
| Item | Price |
|---|---|
| Input | $2.0000 / 1M tokens |
| Output | $6.0000 / 1M tokens |
| Cached input | $0.2000 / 1M tokens |
| Embedding | $2.0000 / 1M tokens |
Token limits
Context window
2.0M
Max input tokens
2.0M
Max output tokens
2.0M
Max tokens
2.0M
Capabilities
| Capability | Supported |
|---|---|
| Vision | ✅ |
| Function calling | ✅ |
| Parallel function calling | — |
| Tool choice | ✅ |
| Prompt caching | ✅ |
| Reasoning | ✅ |
| Response schema | — |
| System messages | — |
| Audio input | — |
| Audio output | — |
| Web search | ✅ |
| PDF input | — |
| Video input | — |
Benchmarks
Most benchmark rows are attached to the base model family rather than this provider route. Open benchmark explorer
| Benchmark | Score | Metric | Scope | Checked | Source |
|---|---|---|---|---|---|
| ARC-AGI-2 | 15.9% | accuracy | Base model: grok-4 (Grok 4) | 2026-05-31 | Link |
| Vending-Bench | $4694.15 net worth | net worth | Base model: grok-4 (Grok 4) | 2026-05-31 | Link |
| Humanity's Last Exam | 50.7% (text-only subset) | accuracy | Base model: grok-4 (Grok 4 Heavy) | 2026-05-31 | Link |
| USAMO'25 | 61.9% | accuracy | Base model: grok-4 (Grok 4 Heavy) | 2026-05-31 | Link |
Sources
| Source links | |
| Pricing data | LiteLLM model cost map |
| Synced at | 2026-05-28 |
Docs
| Official docs |
Similar models
This list is ranked by overall similarity. Use filters to emphasize the lens that matters most for the replacement you are making.
Comparing from
| Model | Cost | Input shape | Features | Context | Why it is close |
|---|---|---|---|---|---|
| grok-4.20-beta-0309-reasoning xai | In $2.0000 / 1M tokens Out $6.0000 / 1M tokens | imagetext
Output: text | VisionFunction callingTool choicePrompt caching | 2.0M | Current model Reference row |
| Model | Cost | Input shape | Features | Context | Why it is close |
|---|---|---|---|---|---|
| grok-4.20-multi-agent-beta-0309 xai | In $2.0000 / 1M tokens Out $6.0000 / 1M tokens | imagetext
Output: text | VisionFunction callingTool choicePrompt caching | 2.0M | Same provider Overall 100% |
| grok-4.20-0309-reasoning xai | In $2.0000 / 1M tokens Out $6.0000 / 1M tokens | imagetext
Output: text | VisionFunction callingTool choiceReasoning | 2.0M | Same provider Overall 96% |
| grok-4.20-beta-0309-non-reasoning xai | In $2.0000 / 1M tokens Out $6.0000 / 1M tokens | imagetext
Output: text | VisionFunction callingTool choicePrompt caching | 2.0M | Same provider Overall 96% |
| o3 OpenAI | In $2.0000 / 1M tokens Out $8.0000 / 1M tokens | imagetext pdf
Output: text | VisionFunction callingTool choicePrompt caching | 100.0K | Text + image covered Overall 77% |
| o3-2025-04-16 OpenAI | In $2.0000 / 1M tokens Out $8.0000 / 1M tokens | imagetext pdf
Output: text | VisionFunction callingTool choicePrompt caching | 100.0K | Text + image covered Overall 77% |
| grok-4-1-fast xai | In $0.2000 / 1M tokens Out $0.5000 / 1M tokens | imagetext
Output: text | VisionFunction callingTool choicePrompt caching | 2.0M | Same provider Overall 76% |
| grok-4-1-fast-reasoning xai | In $0.2000 / 1M tokens Out $0.5000 / 1M tokens | imagetext
Output: text | VisionFunction callingTool choicePrompt caching | 2.0M | Same provider Overall 76% |
| grok-4-1-fast-reasoning-latest xai | In $0.2000 / 1M tokens Out $0.5000 / 1M tokens | imagetext
Output: text | VisionFunction callingTool choicePrompt caching | 2.0M | Same provider Overall 76% |
| gpt-5.1-codex-max OpenRouter | In $1.2500 / 1M tokens Out $10.0000 / 1M tokens | imagetext
Output: text | VisionFunction callingTool choicePrompt caching | 128.0K | Text + image covered Overall 74% |
| pixtral-large-2411 Mistral | In $2.0000 / 1M tokens Out $6.0000 / 1M tokens | imagetext
Output: text | VisionFunction callingTool choice | 128.0K | Text + image covered Overall 72% |
| gpt-5.2 OpenRouter | In $1.7500 / 1M tokens Out $14.0000 / 1M tokens | imagetext file
Output: text | VisionFunction callingTool choicePrompt caching | 128.0K | Text + image covered Overall 66% |
| mistral-large-2407 azure_ai | In $2.0000 / 1M tokens Out $6.0000 / 1M tokens | imagetext
Output: text | Function callingTool choice | 4.1K | Partial I/O overlap Overall 56% Missing image |
| mistral-large-latest azure_ai | In $2.0000 / 1M tokens Out $6.0000 / 1M tokens | imagetext
Output: text | Function callingTool choice | 4.1K | Partial I/O overlap Overall 56% Missing image |
| eu.mistral.pixtral-large-2502-v1:0 bedrock_converse | In $2.0000 / 1M tokens Out $6.0000 / 1M tokens | imagetext
Output: image, text | Function calling | 4.1K | Text + image covered Overall 56% |
| mistral-large-2411 Mistral | In $2.0000 / 1M tokens Out $6.0000 / 1M tokens | imagetext
Output: text | Function callingTool choice | 128.0K | Partial I/O overlap Overall 56% Missing image |
| open-mixtral-8x22b Mistral | In $2.0000 / 1M tokens Out $6.0000 / 1M tokens | imagetext
Output: text | Function callingTool choice | 8.2K | Partial I/O overlap Overall 55% Missing image |
No models match this filter.