AI Model Comparison Table
| Model ↕ | Provider ↕ | Context ↕ | Max Output ↕ | Input $/1M ↕ | Output $/1M ↕ | MMLU ↕ | HumanEval ↕ | Released ↓ |
|---|---|---|---|---|---|---|---|---|
| GPT-5.3-Codex | OpenAI | 400K | 128K | $1.75 | $14.00 | — | — | 2026-02 |
| Claude Opus 4.6 | Anthropic | 200K | 128K | $5.00 | $25.00 | — | — | 2026-02 |
| GPT-5.2 | OpenAI | 400K | 128K | $1.75 | $14.00 | — | — | 2025-12 |
| Mistral Large 3 | Mistral | 262K | 33K | $0.50 | $1.50 | — | — | 2025-12 |
| Claude Haiku 4.5 | Anthropic | 200K | 64K | $1.00 | $5.00 | — | 88.1 | 2025-10 |
| Claude Sonnet 4.5 | Anthropic | 200K | 64K | $3.00 | $15.00 | — | 93.0 | 2025-09 |
| Gemini 2.5 Flash | 1.0M | 66K | $0.30 | $2.50 | — | — | 2025-09 | |
| Grok 4 | xAI | 262K | 33K | $3.00 | $15.00 | — | — | 2025-09 |
| Grok 4 Fast | xAI | 2.0M | 33K | $0.20 | $0.50 | — | — | 2025-09 |
| o4-mini | OpenAI | 200K | 100K | $1.10 | $4.40 | — | — | 2025-07 |
| o3 | OpenAI | 200K | 100K | $2.00 | $8.00 | — | — | 2025-06 |
| GPT-4.1 | OpenAI | 1.0M | 33K | $2.00 | $8.00 | — | — | 2025-04 |
| GPT-4.1-mini | OpenAI | 1.0M | 33K | $0.40 | $1.60 | — | — | 2025-04 |
| GPT-4.1-nano | OpenAI | 1.0M | 33K | $0.10 | $0.40 | — | — | 2025-04 |
| Llama 4 Maverick (Groq) | Meta/Groq | 524K | 8K | $0.50 | $0.77 | — | — | 2025-04 |
| Llama 4 Scout (Groq) | Meta/Groq | 10.0M | 8K | $0.11 | $0.34 | — | — | 2025-04 |
| Gemini 2.5 Pro | 1.0M | 66K | $1.25 | $10.00 | — | — | 2025-03 | |
| Mistral Small 3.1 | Mistral | 128K | 8K | $0.03 | $0.11 | — | — | 2025-03 |
| Gemini 2.0 Flash | 1.0M | 8K | $0.10 | $0.40 | — | — | 2025-02 | |
| o3-mini | OpenAI | 200K | 100K | $1.10 | $4.40 | — | — | 2025-01 |
| DeepSeek R1 | DeepSeek | 128K | 33K | $0.55 | $2.19 | 90.8 | — | 2025-01 |
| DeepSeek V3 | DeepSeek | 128K | 8K | $0.27 | $1.10 | 88.5 | — | 2024-12 |
Sort by:
GPT-5.3-Codex
OpenAIContext
400K
Max Output
128K
Input $/1M
$1.75
Output $/1M
$14.00
MMLU
—
HumanEval
—
Claude Opus 4.6
AnthropicContext
200K
Max Output
128K
Input $/1M
$5.00
Output $/1M
$25.00
MMLU
—
HumanEval
—
GPT-5.2
OpenAIContext
400K
Max Output
128K
Input $/1M
$1.75
Output $/1M
$14.00
MMLU
—
HumanEval
—
Mistral Large 3
MistralContext
262K
Max Output
33K
Input $/1M
$0.50
Output $/1M
$1.50
MMLU
—
HumanEval
—
Claude Haiku 4.5
AnthropicContext
200K
Max Output
64K
Input $/1M
$1.00
Output $/1M
$5.00
MMLU
—
HumanEval
88.1
Claude Sonnet 4.5
AnthropicContext
200K
Max Output
64K
Input $/1M
$3.00
Output $/1M
$15.00
MMLU
—
HumanEval
93.0
Gemini 2.5 Flash
GoogleContext
1.0M
Max Output
66K
Input $/1M
$0.30
Output $/1M
$2.50
MMLU
—
HumanEval
—
Grok 4
xAIContext
262K
Max Output
33K
Input $/1M
$3.00
Output $/1M
$15.00
MMLU
—
HumanEval
—
Grok 4 Fast
xAIContext
2.0M
Max Output
33K
Input $/1M
$0.20
Output $/1M
$0.50
MMLU
—
HumanEval
—
o4-mini
OpenAIContext
200K
Max Output
100K
Input $/1M
$1.10
Output $/1M
$4.40
MMLU
—
HumanEval
—
o3
OpenAIContext
200K
Max Output
100K
Input $/1M
$2.00
Output $/1M
$8.00
MMLU
—
HumanEval
—
GPT-4.1
OpenAIContext
1.0M
Max Output
33K
Input $/1M
$2.00
Output $/1M
$8.00
MMLU
—
HumanEval
—
GPT-4.1-mini
OpenAIContext
1.0M
Max Output
33K
Input $/1M
$0.40
Output $/1M
$1.60
MMLU
—
HumanEval
—
GPT-4.1-nano
OpenAIContext
1.0M
Max Output
33K
Input $/1M
$0.10
Output $/1M
$0.40
MMLU
—
HumanEval
—
Llama 4 Maverick (Groq)
Meta/GroqContext
524K
Max Output
8K
Input $/1M
$0.50
Output $/1M
$0.77
MMLU
—
HumanEval
—
Llama 4 Scout (Groq)
Meta/GroqContext
10.0M
Max Output
8K
Input $/1M
$0.11
Output $/1M
$0.34
MMLU
—
HumanEval
—
Gemini 2.5 Pro
GoogleContext
1.0M
Max Output
66K
Input $/1M
$1.25
Output $/1M
$10.00
MMLU
—
HumanEval
—
Mistral Small 3.1
MistralContext
128K
Max Output
8K
Input $/1M
$0.03
Output $/1M
$0.11
MMLU
—
HumanEval
—
Gemini 2.0 Flash
GoogleContext
1.0M
Max Output
8K
Input $/1M
$0.10
Output $/1M
$0.40
MMLU
—
HumanEval
—
o3-mini
OpenAIContext
200K
Max Output
100K
Input $/1M
$1.10
Output $/1M
$4.40
MMLU
—
HumanEval
—
DeepSeek R1
DeepSeekContext
128K
Max Output
33K
Input $/1M
$0.55
Output $/1M
$2.19
MMLU
90.8
HumanEval
—
DeepSeek V3
DeepSeekContext
128K
Max Output
8K
Input $/1M
$0.27
Output $/1M
$1.10
MMLU
88.5
HumanEval
—
Showing 22 of 26 models (4 legacy hidden)Last updated: February 2026
This tool is provided as-is for convenience. Output should be verified before use in any production or critical context.