grok-4
replicate · chat model
grok-4 is listed here as a chat model from replicate. This page shows simple API pricing, token limits, and capability flags so you can compare it with similar options.
Input
$7.2000 / 1M tokens
Output
$36.0000 / 1M tokens
Cached input
N/A
Context
N/A
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 | $7.2000 / 1M tokens |
| Output | $36.0000 / 1M tokens |
| Embedding | $7.2000 / 1M tokens |
Token limits
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 replicate | In $7.2000 / 1M tokens Out $36.0000 / 1M tokens | text
Output: text | Function callingSystem messages | N/A | Current model Reference row |
| Model | Cost | Input shape | Features | Context | Why it is close |
|---|---|---|---|---|---|
| mistral.mistral-large-2402-v1:0 Bedrock | In $10.4000 / 1M tokens Out $31.2000 / 1M tokens | text
Output: text | Function calling | 8.2K | Text covered Overall 68% |
| mistral.mistral-large-2402-v1:0 Bedrock | In $8.0000 / 1M tokens Out $24.0000 / 1M tokens | text
Output: text | Function calling | 8.2K | Text covered Overall 68% |
| mistral.mistral-large-2402-v1:0 Bedrock | In $8.0000 / 1M tokens Out $24.0000 / 1M tokens | text
Output: text | Function calling | 8.2K | Text covered Overall 68% |
| mistral.mistral-large-2402-v1:0 Bedrock | In $8.0000 / 1M tokens Out $24.0000 / 1M tokens | text
Output: text | Function calling | 8.2K | Text covered Overall 68% |
| deepseek-v3 replicate | In $1.4500 / 1M tokens Out $1.4500 / 1M tokens | text
Output: text | Function callingSystem messages | 8.2K | Same provider Overall 67% |
| qwen3-235b-a22b-instruct-2507 replicate | In $0.2640 / 1M tokens Out $1.0600 / 1M tokens | text
Output: text | Function callingSystem messages | N/A | Same provider Overall 66% |
| gpt-oss-120b replicate | In $0.1800 / 1M tokens Out $0.7200 / 1M tokens | text
Output: text | Function callingSystem messages | N/A | Same provider Overall 65% |
| gpt-oss-20b replicate | In $0.0900 / 1M tokens Out $0.3600 / 1M tokens | text
Output: text | Function callingSystem messages | N/A | Same provider Overall 65% |
| granite-3.3-8b-instruct replicate | In $0.0300 / 1M tokens Out $0.2500 / 1M tokens | text
Output: text | Function callingSystem messages | N/A | Same provider Overall 65% |
| deepseek-v3.1 replicate | In $0.6720 / 1M tokens Out $2.0160 / 1M tokens | text
Output: text | Function callingSystem messages | 163.8K | Same provider Overall 58% |
| minimax.minimax-m2.1 Bedrock | In $0.3600 / 1M tokens Out $1.4400 / 1M tokens | text
Output: text | Function callingSystem messages | 8.2K | Text covered Overall 58% |
| mistral.mistral-large-3-675b-instruct bedrock_converse | In $0.5000 / 1M tokens Out $1.5000 / 1M tokens | text image
Output: text | Function callingSystem messages | 8.2K | Text covered Overall 54% |
| mistral.ministral-3-14b-instruct bedrock_converse | In $0.2000 / 1M tokens Out $0.2000 / 1M tokens | text image
Output: text | Function callingSystem messages | 8.2K | Text covered Overall 53% |
| gpt-4.1-nano replicate | In $0.1000 / 1M tokens Out $0.4000 / 1M tokens | text image
Output: text | Function callingSystem messages | N/A | Same provider Overall 53% |
| gpt-4-0125-preview Azure | In $10.0000 / 1M tokens Out $30.0000 / 1M tokens | text image
Output: text | Function calling | 4.1K | Text covered Overall 50% |
| gpt-5.5 OpenAI | In $5.0000 / 1M tokens Out $30.0000 / 1M tokens | text imagepdf
Output: text | Function callingSystem messages | 128.0K | Text covered Overall 48% |
| gpt-5.5-2026-04-23 OpenAI | In $5.0000 / 1M tokens Out $30.0000 / 1M tokens | text imagepdf
Output: text | Function callingSystem messages | 128.0K | Text covered Overall 48% |
| gpt-5.5 Azure | In $5.0000 / 1M tokens Out $30.0000 / 1M tokens | text pdf
Output: text | Function callingSystem messages | 128.0K | Partial I/O overlap Overall 36% Missing text |
| gpt-5.5-2026-04-23 Azure | In $5.0000 / 1M tokens Out $30.0000 / 1M tokens | text pdf
Output: text | Function callingSystem messages | 128.0K | Partial I/O overlap Overall 36% Missing text |
No models match this filter.