Model prices
Compare the prices for capabilities currently enabled on your plan. Chat is priced per million tokens; request-priced capabilities appear per job when enabled. All prices are in credits and include the displayed provider’s multiplier. One credit is $0.0001.
“Up to” is the amount reserved for a request-priced job; the actual charge may be lower. Reference list prices appear where available and use the same credit units. Unpublished prices are not shown as zero.
Showing 1–5 of 240 models
| Model | Type | Cache / 1M | Vendor | Status | Context | Endpoints | |||
|---|---|---|---|---|---|---|---|---|---|
gpt-5.6-luna Provider B · ×2 | Chatper 1M tokens | 1,120 | 6,720 | 112 | — | other | Active | Unknown | Unspecified |
deepseek-v4.1-flash Provider B · ×2 Pricing detailsPrices include the platform markup. One credit is $0.0001. Each completed call rounds up to a whole credit. standard: 2,400 input / 9,500 output / 50 cache read credits per million tokens. Rates synced 2026-09-24. Choose the matching provider alias under Routing to use these prices for a model offered by multiple sources. | Chatper 1M tokens | 2,400 | 9,500 | 50 | — | deepseek | Active | Unknown | Unspecified |
deepseek-v4-flash Provider A · ×25 Pricing detailsPrices include the platform markup. One credit is $0.0001. Each completed call rounds up to a whole credit. Peak rates: 01:00–04:00 and 06:00–10:00 UTC. The request's start time selects its rate. peak: 3,750 input / 15,000 output / 75 cache read credits per million tokens. off peak: 1,875 input / 7,500 output / 38 cache read credits per million tokens. Rates synced 2026-09-21. Choose the matching provider alias under Routing to use these prices for a model offered by multiple sources. | Chatper 1M tokens | 3,750 | 15,000 | 75 | — | deepseek | Active | 1,000,000 | openai |
deepseek-v4-flash-0731 Provider A · ×25 Pricing detailsPrices include the platform markup. One credit is $0.0001. Each completed call rounds up to a whole credit. Peak rates: 01:00–04:00 and 06:00–10:00 UTC. The request's start time selects its rate. peak: 3,750 input / 15,000 output / 75 cache read credits per million tokens. off peak: 1,875 input / 7,500 output / 38 cache read credits per million tokens. Rates synced 2026-09-21. Choose the matching provider alias under Routing to use these prices for a model offered by multiple sources. | Chatper 1M tokens | 3,750 | 15,000 | 75 | — | deepseek | Active | 1,000,000 | openai |
deepseek-v4-flash Qoder Pro · ×3 | Chatper 1M tokens | 4,200 | 8,400 | 84 | — | qoder | Active | Unknown | Unspecified |