DeepSeek
DeepSeek V4 Flash 0731 API prices by provider
deepseek/deepseek-v4-flash-0731
28 inference providers serve this exact model through OpenRouter. Input and output rates are paired per endpoint; route tags may identify a region or sub-endpoint whose eligibility is not yet verified.
- Active endpoints
- 28 / 29
- Lowest at 1M in + 1M out
- $0.24
- DeepInfra · standard tier
- Context up to
- 1.31M
- Latest price change
- None yet
- Rates unchanged since first record 2026-09-29
| Provider · route | Tier | Input / 1M | Output / 1M | Cache read | Cache write | Context | Tools | 1M + 1M | Status | Price since |
|---|---|---|---|---|---|---|---|---|---|---|
StreamLake streamlake/fp8 · fp8 | Promo | $0.044 | $0.132 | $0.0014 | — | 1.02M | Yes | $0.176 | Active | Since |
DeepInfra deepinfra/fp8 · fp8 | Standard | $0.06 | $0.18 | $0.015 | — | 1.05M | Yes | $0.24 | Active | Since |
Makora makora · unknown | Standard | $0.09 | $0.195 | $0.0196 | — | 1M | Yes | $0.285 | Active | Since |
Sail Research sail-research/fp4 · fp4 | Standard | $0.019 | $0.30 | $0.014 | — | 1.05M | Yes | $0.319 | Active | Since |
Relace relace/fp4 · fp4 | Standard | $0.018 | $0.32 | $0.018 | — | 1.05M | Yes | $0.338 | Active | Since |
DigitalOcean digitalocean · unknown | Standard | $0.119 | $0.238 | $0.0238 | — | 1.05M | Yes | $0.357 | Active | Since |
BaseTen baseten/fp8 · fp8 | Standard | $0.13 | $0.26 | $0.028 | — | 1.05M | Yes | $0.39 | Active | Since |
CoreWeave coreweave/fp8 · fp8 | Standard | $0.13 | $0.28 | $0.07 | — | 262K | Yes | $0.41 | Active | Since |
Cohere cohere · unknown | Standard | $0.14 | $0.28 | $0.07 | — | 1.05M | Yes | $0.42 | Active | Since |
Parasail parasail/fp8 · fp8 | Standard | $0.14 | $0.28 | $0.05 | — | 1.05M | Yes | $0.42 | Active | Since |
Together together · unknown | Standard | $0.14 | $0.28 | $0.03 | — | 1.05M | Yes | $0.42 | Active | Since |
Wafer wafer/fast · unknown | Standard | $0.07 | $0.35 | $0.0531 | — | 1.05M | Yes | $0.42 | Active | Since |
Sail Research sail-research/us · fp4 | Standard | $0.019 | $0.42 | $0.012 | — | 1.05M | Yes | $0.439 | Active | Since |
Venice venice · unknown | Standard | $0.175 | $0.35 | $0.035 | — | 1M | Yes | $0.525 | Active | Since |
Morph morph/bf16 · bf16 | Standard | $0.142 | $0.3996 | $0.0359 | — | 1.05M | Yes | $0.5416 | Active | Since |
Reka reka · unknown | Standard | $0.021 | $0.528 | $0.0056 | — | 262K | Yes | $0.549 | Active | Since |
AtlasCloud atlas-cloud/fp4 · fp4 | Standard | $0.1584 | $0.4752 | $0.0101 | — | 1.05M | Yes | $0.6336 | Active | Since |
Alibaba alibaba · unknown | Standard | $0.176 | $0.528 | $0.0176 | — | 1M | Yes | $0.704 | Active | Since |
Inceptron inceptron/fp4 · fp4 | Standard | $0.056 | $0.65 | $0.027 | — | 1.05M | Yes | $0.706 | Active | Since |
Mancer 2 mancer/fp8 · fp8 | Standard | $0.20 | $0.60 | — | — | 1.05M | Yes | $0.80 | Active | Since |
SiliconFlow siliconflow/fp8 · fp8 | Standard | $0.22 | $0.66 | $0.028 | — | 1.05M | Yes | $0.88 | Active | Since |
GMICloud gmicloud/fp8 · fp8 | Promo | $0.286 | $0.858 | $0.0091 | — | 1.05M | Yes | $1.144 | Active | Since |
Phala phala · unknown | Promo | $0.308 | $0.924 | $0.0196 | — | 1.05M | Yes | $1.232 | Active | Since |
OpenInference open-inference/fp8 · fp8 | Standard | $0.012 | $1.25 | $0.01 | — | 1.05M | Yes | $1.262 | Active | Since |
NextBit nextbit/fp8 · fp8 | Standard | $0.352 | $1.056 | $0.012 | — | 1.05M | Yes | $1.408 | Active | Since |
Novita novita/fp8 · fp8 | Promo | $0.4092 | $1.2276 | $0.026 | — | 1.05M | Yes | $1.6368 | Active | Since |
Baidu baidu/fp8 · fp8 | Standard | $0.44 | $1.32 | $0.014 | — | 1.05M | Yes | $1.76 | Active | Since |
Cloudflare cloudflare · unknown | Standard | $0.44 | $1.32 | $0.014 | — | 1.31M | Yes | $1.76 | Active | Since |
Nebius nebius/fp8 · fp8 | Standard | $0.14 | $0.28 | — | — | 1.02M | Yes | $0.42 | Unavailable | Since |
“—” means no rate is published for that endpoint; it is excluded from estimates, not counted as zero. “Since” is the first record with no rate change observed; “Changed” is the latest observed rate or billing change. Per-request fees: not published for any endpoint here. Status is the upstream operational flag, not a measured uptime.