Fastest, most cost-effective GPT-4.1 model
tokens
tokens
Last Update
Overall Rating
| Type | Price | Unit | Context Type |
|---|---|---|---|
Input | $0.100000 | per mtokens | Standard |
Output | $0.400000 | per mtokens | Standard |
Cached Input | $0.025000 | per mtokens | Standard Reduced cost for cached input |
| Type | Price | Unit | Context Type | Savings |
|---|---|---|---|---|
| Input | $0.050000 | per mtokens | Standard | -50% |
| Output |
| Tier | RPM | RPD | TPM | Additional Limits |
|---|---|---|---|---|
| free | 3 | 200 | 40,000 | |
| tier_1 | 500 | 10,000 | 200,000 | Queue:2,000,000 Requests |
| tier_2 | 5,000 | — | 2,000,000 | Queue:20,000,000 Requests |
| tier_3 | 5,000 | — | 4,000,000 | Queue:40,000,000 Requests |
| tier_4 | 10,000 | — | 10,000,000 | Queue:1,000,000,000 Requests |
| tier_5 | 30,000 | — | 150,000,000 | Queue:15,000,000,000 Requests |
| Tier | RPM | TPM | Additional Limits |
|---|---|---|---|
| tier_1 | 200 | 400,000 | Queue:5,000,000 Requests |
| tier_2 | 500 | 1,000,000 | Queue:40,000,000 Requests |
| per mtokens |
| Standard |
| -50% |
| tier_3 | 1,000 | 2,000,000 | Queue:80,000,000 Requests |
| tier_4 | 2,000 | 10,000,000 | Queue:200,000,000 Requests |
| tier_5 | 8,000 | 20,000,000 | Queue:2,000,000,000 Requests |
