grok-4
xai · chat model
grok-4 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
$3.0000 / 1M tokens
Output
$15.0000 / 1M tokens
Cached input
N/A
Context
256.0K
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 | $3.0000 / 1M tokens |
| Output | $15.0000 / 1M tokens |
| Embedding | $3.0000 / 1M tokens |
Token limits
Context window
256.0K
Max input tokens
256.0K
Max output tokens
256.0K
Max tokens
256.0K
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 xai | In $3.0000 / 1M tokens Out $15.0000 / 1M tokens | imagetext
Output: text | Function callingTool choicePrompt cachingWeb search | 256.0K | Current model Reference row |
| Model | Cost | Input shape | Features | Context | Why it is close |
|---|---|---|---|---|---|
| grok-4-0709 xai | In $3.0000 / 1M tokens Out $15.0000 / 1M tokens | imagetext
Output: text | Function callingTool choicePrompt cachingWeb search | 256.0K | Same provider Overall 100% |
| grok-4-latest xai | In $3.0000 / 1M tokens Out $15.0000 / 1M tokens | imagetext
Output: text | Function callingTool choicePrompt cachingWeb search | 256.0K | Same provider Overall 100% |
| grok-4 vercel_ai_gateway | In $3.0000 / 1M tokens Out $15.0000 / 1M tokens | imagetext
Output: text | Function callingTool choice | 256.0K | Text + image covered Overall 88% |
| claude-3-7-sonnet-latest deepinfra | In $3.3000 / 1M tokens Out $16.5000 / 1M tokens | imagetext
Output: text | Function callingTool choice | 200.0K | Text + image covered Overall 82% |
| claude-4-sonnet deepinfra | In $3.3000 / 1M tokens Out $16.5000 / 1M tokens | imagetext
Output: text | Function callingTool choice | 200.0K | Text + image covered Overall 82% |
| grok-3 xai | In $3.0000 / 1M tokens Out $15.0000 / 1M tokens | imagetext
Output: text | Function callingTool choicePrompt cachingWeb search | 131.1K | Same provider Overall 81% Missing image |
| grok-3-beta xai | In $3.0000 / 1M tokens Out $15.0000 / 1M tokens | imagetext
Output: text | Function callingTool choicePrompt cachingWeb search | 131.1K | Same provider Overall 81% Missing image |
| grok-3-latest xai | In $3.0000 / 1M tokens Out $15.0000 / 1M tokens | imagetext
Output: text | Function callingTool choicePrompt cachingWeb search | 131.1K | Same provider Overall 81% Missing image |
| grok-3-fast-beta xai | In $5.0000 / 1M tokens Out $25.0000 / 1M tokens | imagetext
Output: text | Function callingTool choicePrompt cachingWeb search | 131.1K | Same provider Overall 73% Missing image |
| grok-4.20-beta-0309-non-reasoning xai | In $2.0000 / 1M tokens Out $6.0000 / 1M tokens | imagetext
Output: text | Function callingTool choicePrompt cachingWeb search | 2.0M | Same provider Overall 72% |
| anthropic.claude-sonnet-4-6 bedrock_converse | In $3.0000 / 1M tokens Out $15.0000 / 1M tokens | imagetext pdf
Output: text | Function callingTool choicePrompt caching | 64.0K | Text + image covered Overall 72% |
| global.anthropic.claude-sonnet-4-6 bedrock_converse | In $3.0000 / 1M tokens Out $15.0000 / 1M tokens | imagetext pdf
Output: text | Function callingTool choicePrompt caching | 64.0K | Text + image covered Overall 72% |
| anthropic.claude-3-5-sonnet-20241022-v2:0 Bedrock | In $3.0000 / 1M tokens Out $15.0000 / 1M tokens | imagetext pdf
Output: text | Function callingTool choicePrompt caching | 8.2K | Text + image covered Overall 70% |
| grok-4.20-multi-agent-beta-0309 xai | In $2.0000 / 1M tokens Out $6.0000 / 1M tokens | imagetext
Output: text | Function callingTool choicePrompt cachingWeb search | 2.0M | Same provider Overall 69% |
| anthropic.claude-3-7-sonnet-20250219-v1:0 bedrock_converse | In $3.0000 / 1M tokens Out $15.0000 / 1M tokens | imagetext pdf
Output: text | Function callingTool choicePrompt caching | 8.2K | Text + image covered Overall 69% |
| grok-4-fast-reasoning xai | In $0.2000 / 1M tokens Out $0.5000 / 1M tokens | imagetext
Output: text | Function callingTool choicePrompt cachingWeb search | 2.0M | Same provider Overall 68% |
| grok-4-fast-non-reasoning xai | In $0.2000 / 1M tokens Out $0.5000 / 1M tokens | imagetext
Output: text | Function callingTool choicePrompt cachingWeb search | 2.0M | Same provider Overall 68% |
| anthropic.claude-3-5-sonnet-20240620-v1:0 Bedrock | In $3.0000 / 1M tokens Out $15.0000 / 1M tokens | imagetext pdf
Output: text | Function callingTool choice | 4.1K | Text + image covered Overall 67% |
| anthropic.claude-3-sonnet-20240229-v1:0 Bedrock | In $3.0000 / 1M tokens Out $15.0000 / 1M tokens | imagetext pdf
Output: text | Function callingTool choice | 4.1K | Text + image covered Overall 67% |
No models match this filter.