Claude Sonnet 3.7 – 200 K context, extended-thinking, text & vision.
tokens
tokens
Last Update
Overall Rating
| Type | Price | Unit | Context Type |
|---|---|---|---|
Input | $3.000000 | per mtokens | Standard |
Output | $15.000000 | per mtokens | Standard |
Cache Write (5 min) | $3.750000 | per mtokens | Standard Cache storage for 5 minutes |
Cache Write (1 hour) | $6.000000 | per mtokens | Standard Cache storage for 1 hour |
Cache Hit | $0.300000 | per mtokens | Standard Accessing cached content |
| Type | Price | Unit | Context Type | Savings |
|---|---|---|---|---|
| Input | $1.500000 | per mtokens | Standard | |
| Output | $7.500000 | per mtokens | Standard |
Batch processing allows for delayed, cost-efficient bulk operations
| Tier | RPM | TPM | Additional Limits |
|---|---|---|---|
| tier_1 | 50 | — | Queue:100,000 requests Per Batch:100,000 requests |
| tier_2 | 1,000 | — | Queue:200,000 requests Per Batch:100,000 requests |
| tier_3 | 2,000 | — | Queue:300,000 requests Per Batch:100,000 requests |
| tier_4 | 4,000 | — | Queue:500,000 requests Per Batch:100,000 requests |
| Tier | RPM | TPM | IPM |
|---|---|---|---|
| tier_1 | 50 | 20000 | 8,000 |
| tier_2 | 1,000 | 40000 | 16,000 |
| tier_3 | 2,000 | 80000 | 32,000 |
| tier_4 |
| 4,000 |
| 200000 |
| 80,000 |
