tokevenGPT 4
GPT 4 is GPT's most capable model, priced at $30.00/MTok input and $60.00/MTok output with a 8K context window. Alias of gpt-4-0613 (same prices). Added 2026-10-13 for integrations that report the requested model id. Not benchmarked, so never recommended.
Input $/MTok
$30.00
Output $/MTok
$60.00
Context window
8K
Cache read discount
0% off
GPT 4 pricing breakdown
| Rate | Input $/MTok | Output $/MTok |
|---|---|---|
| Standard | $30.00 | $60.00 |
| Cached read (0% off input) | $30.00 | - |
| Cached write (no surcharge) | $30.00 | - |
| Batch (50% off) | $15.00 | $30.00 |
All rates in USD per million tokens. Prices verified against provider documentation.
GPT 4 task benchmarks
Confidence scores (0-100) and cross-provider rank for each task type. Rank 1 is best across all 88 models.
Not benchmarked. The third-party benchmark source used for confidence scores does not cover GPT models yet. Scores will appear here once independent benchmarks are published.
GPT 4 cost by use case
Estimated cost per API call using default token counts for each workload.
| Use case | Input tokens | Output tokens | Cost / call |
|---|---|---|---|
| Code Generation | 2,000 | 4,000 | $0.3000 |
| Unit Test Generation | 3,000 | 5,000 | $0.3900 |
| SQL Generation | 1,500 | 1,000 | $0.1050 |
| API Generation | 3,000 | 6,000 | $0.4500 |
| Code Refactoring | 4,000 | 4,000 | $0.3600 |
| Code Review | 5,000 | 2,000 | $0.2700 |
| PR Review | 8,000 | 3,000 | $0.4200 |
| Security Review | 6,000 | 2,500 | $0.3300 |
| Bug Detection | 5,000 | 2,000 | $0.2700 |
| Document Summarization | 10,000 | 1,000 | $0.3600 |
| PDF Summarization | 15,000 | 1,500 | $0.5400 |
| Meeting Notes | 8,000 | 2,000 | $0.3600 |
Monthly cost projections
Projected monthly spend at different call volumes, using code generation as a representative workload (2,000 input / 4,000 output tokens per call).
| Calls / month | Without caching | With caching (0% read discount) |
|---|---|---|
| 1K | $300 | $300 |
| 10K | $3,000 | $3,000 |
| 100K | $30,000 | $30,000 |
| 500K | $150,000 | $150,000 |
| 1M | $300,000 | $300,000 |
Caching estimate assumes 70% of input tokens are cache reads. Your actual cache hit rate will depend on prompt structure and reuse.
Flagship alternatives to GPT 4
Same-tier models from other providers, sorted by input price.
| Model | Provider | Input $/MTok | Output $/MTok | Input savings |
|---|---|---|---|---|
| MiniMax M3 | MiniMax | $0.30 | $1.20 | 99% cheaper |
| DeepSeek V4 Pro | DeepSeek | $0.66 | $1.98 | 98% cheaper |
| Grok 4.6 | Grok | $2.00 | $6.00 | 93% cheaper |
| Grok 4.5 | Grok | $2.00 | $6.00 | 93% cheaper |
| Grok 4.7 | Grok | $2.00 | $6.00 | 93% cheaper |
| Qwen 3.8 Max | Alibaba (Qwen) | $2.00 | $6.00 | 93% cheaper |
| Kimi K3 | Moonshot (Kimi) | $3.00 | $15.00 | 90% cheaper |
| Claude Opus 5.5 | Claude | $4.00 | $20.00 | 87% cheaper |
| Claude Opus 4.8 | Claude | $5.00 | $25.00 | 83% cheaper |
| Claude Opus 5 | Claude | $5.00 | $25.00 | 83% cheaper |
| Claude Opus 4.7 | Claude | $5.00 | $25.00 | 83% cheaper |
| Claude Opus 4.6 | Claude | $5.00 | $25.00 | 83% cheaper |
| Claude Opus 4.5 | Claude | $5.00 | $25.00 | 83% cheaper |
| Claude Fable 5.1 | Claude | $10.00 | $50.00 | 67% cheaper |
| Claude Fable 5 | Claude | $10.00 | $50.00 | 67% cheaper |
| Claude Mythos 5.1 | Claude | $10.00 | $50.00 | 67% cheaper |
| Claude Mythos 5 | Claude | $10.00 | $50.00 | 67% cheaper |
Other GPT models
GPT 5 Nano
Fast / Budget / $0.05 in / $0.40 out
GPT 4.1 Nano
Fast / Budget / $0.10 in / $0.40 out
GPT 6 Luna
Fast / Budget / $0.10 in / $0.50 out
GPT 4o Mini
Fast / Budget / $0.15 in / $0.60 out
GPT 5.6 Luna
Fast / Budget / $0.20 in / $1.20 out
GPT 5.4 Nano
Fast / Budget / $0.20 in / $1.25 out
GPT 5 Mini
Fast / Budget / $0.25 in / $2.00 out
GPT 4.1 Mini
Fast / Budget / $0.40 in / $1.60 out
GPT 3.5 Turbo
Fast / Budget / $0.50 in / $1.50 out
GPT 3.5 Turbo (0125)
Fast / Budget / $0.50 in / $1.50 out
GPT 5.4 Mini
Fast / Budget / $0.75 in / $4.50 out
o3 Mini
Fast / Budget / $1.10 in / $4.40 out
o4 Mini
Fast / Budget / $1.10 in / $4.40 out
GPT 5
Mid-tier / $1.25 in / $10.00 out
GPT 5.1
Mid-tier / $1.25 in / $10.00 out
GPT 5.2
Mid-tier / $1.75 in / $14.00 out
GPT 5.6 Terra
Mid-tier / $2.00 in / $12.00 out
GPT 4.1
Mid-tier / $2.00 in / $8.00 out
GPT 6 Sol
Flagship / $2.00 in / $10.00 out
o3
Mid-tier / $2.00 in / $8.00 out
GPT 6.1 Sol
Flagship / $2.00 in / $10.00 out
GPT 5.4
Mid-tier / $2.50 in / $15.00 out
GPT 4o
Mid-tier / $2.50 in / $10.00 out
GPT 5.6 Sol
Flagship / $4.00 in / $20.00 out
GPT 5.5
Flagship / $5.00 in / $30.00 out
GPT 4o (2024-05-13)
Flagship / $5.00 in / $15.00 out
GPT 4 Turbo (2024-04-09)
Flagship / $10.00 in / $30.00 out
GPT 4 Turbo
Flagship / $10.00 in / $30.00 out
GPT 6 Astra
Flagship / $10.00 in / $50.00 out
GPT 5 Pro
Flagship / $15.00 in / $120.00 out
o1
Flagship / $15.00 in / $60.00 out
o3 Pro
Flagship / $20.00 in / $80.00 out
GPT 5.2 Pro
Flagship / $21.00 in / $168.00 out
GPT 4 (0613)
Flagship / $30.00 in / $60.00 out
GPT 5.4 Pro
Flagship / $30.00 in / $180.00 out
GPT 5.5 Pro
Flagship / $30.00 in / $180.00 out
o1 Pro
Flagship / $150.00 in / $600.00 out
Track your GPT 4 spend
See exactly how much you spend on GPT 4 and where you can save. Two-line wrapper install, no API keys shared.