Overview
Microsoft
Models
7
Cheapest Input
$0.05
Max Context
131K
Top Intelligence
33.1
Xai
Models
9
Cheapest Input
$0.20
Max Context
2.0M
Top Intelligence
41.5
Flagship Model Comparison
WizardLM-2 8x22BvsGrok 4
| Metric | WizardLM-2 8x22B | Grok 4 |
|---|---|---|
| Input $/1M tokens | $0.62 | $3.00 |
| Output $/1M tokens | $0.62 | $15.00 |
| Context Window | 66K | 256K |
| Intelligence | 33.1 | 41.5 |
| Coding | N/A | 40.5 |
| Math | N/A | 92.7 |
All Models Pricing
Microsoft Models
| Model | Input/1M | Output/1M | Context |
|---|---|---|---|
| WizardLM-2 8x22B | $0.62 | $0.62 | 66K |
| Phi-3 Medium 128K Instruct | $1.00 | $1.00 | 128K |
| Phi-3 Mini 128K Instruct | $0.10 | $0.10 | 128K |
| Phi 4 | $0.06 | $0.14 | 16K |
| Phi 4 Multimodal Instruct | $0.05 | $0.10 | 131K |
| Phi 4 Reasoning Plus | $0.07 | $0.35 | 32K |
| Phi-3.5 Mini 128K Instruct | $0.10 | $0.10 | 128K |
Xai Models
| Model | Input/1M | Output/1M | Context |
|---|---|---|---|
| Grok 4 | $3.00 | $15.00 | 256K |
| Grok 3 Mini | $0.25 | $0.50 | 131K |
| Grok Code Fast 1 | $0.20 | $1.50 | 256K |
| Grok 4.1 Fast | $0.20 | $0.50 | 2.0M |
| Grok 4 Fast | $0.20 | $0.50 | 2.0M |
| Grok 3 | $3.00 | $15.00 | 131K |
| Grok 3 Mini Beta | $0.30 | $0.50 | 131K |
| Grok 3 Beta | $3.00 | $15.00 | 131K |
| Grok 3 Fast | $5.00 | $25.00 | 131K |
Benchmark Comparison
Best Scores by Provider
| Benchmark | Microsoft | Xai |
|---|---|---|
| Intelligence | 33.1 WizardLM-2 8x22B | 41.5 Grok 4 |
| Coding | 11.2 Phi 4 | 40.5 Grok 4 |
| Math | 18.0 Phi 4 | 92.7 Grok 4 |
| MMLU Pro | 71.4 Phi 4 | 86.6 Grok 4 |
| GPQA | 57.5 Phi 4 | 87.7 Grok 4 |
| LiveCodeBench | 23.1 Phi 4 | 81.9 Grok 4 |
| Aider | 44.4 WizardLM-2 8x22B | 79.6 Grok 4 |
| AIME | 14.3 Phi 4 | 94.3 Grok 4 |
| BBH | 48.6 WizardLM-2 8x22B | N/A |
Capabilities
| Capability | Microsoft | Xai |
|---|---|---|
| Vision | ✓ | ✓ (3 models) |
| Tool Calls | ✓ (7 models) | ✓ (9 models) |
| Reasoning | ✓ (2 models) | ✓ (6 models) |
| Audio Input | — | — |
| Audio Output | — | — |
| PDF Input | — | — |
| Web Search | — | ✓ (8 models) |
| Prompt Caching | — | ✓ (8 models) |
| Open Source Models | ✓ (7 models) | — |
Model-Level Comparisons
Compare specific models head-to-head:
WizardLM-2 8x22BvsGrok 4
WizardLM-2 8x22BvsGrok 3 Mini
WizardLM-2 8x22BvsGrok Code Fast 1
Phi-3 Medium 128K InstructvsGrok 4
Phi-3 Medium 128K InstructvsGrok 3 Mini
Phi-3 Medium 128K InstructvsGrok Code Fast 1
Phi-3 Mini 128K InstructvsGrok 4
Phi-3 Mini 128K InstructvsGrok 3 Mini
Phi-3 Mini 128K InstructvsGrok Code Fast 1