DeepSeek V4 Flash 0731 pricing & price history
DeepSeek V4 Flash 0731 by DeepSeek costs $0.04 per 1M input tokens and $0.32 per 1M output tokens, with a 1.3M token context window. The cheapest provider currently charges $0.038 input / $0.16 output.
Price history
| Date | Input | Output |
|---|---|---|
| 2026-09-24 | $0.04 → $0.04 | $0.64 → $0.32 -50% |
Providers serving DeepSeek V4 Flash 0731 (30)
| Provider | Input | Output | Context | Uptime 30m | Uptime 24h |
|---|---|---|---|---|---|
| Sail Research fp4 | $0.038 | $0.55 | 1M | 99.5% | 99.6% |
| Relace fp4 | $0.04 | $0.32 | 1M | 100.0% | 99.8% |
| StreamLake fp8 | $0.0528 | $0.16 | 1M | 99.3% | 99.1% |
| DeepInfra fp8 | $0.06 | $0.18 | 1M | 99.8% | 99.7% |
| Wafer | $0.08 | $0.35 | 1M | 100.0% | 100.0% |
| Reka fp4 | $0.088 | $0.53 | 262K | 99.9% | 99.7% |
| Makora | $0.09 | $0.20 | 1M | 99.5% | 99.1% |
| Inceptron fp4 | $0.0908 | $0.61 | 1M | 99.8% | 99.8% |
| DigitalOcean | $0.12 | $0.24 | 1M | 100.0% | 99.9% |
| BaseTen fp8 | $0.13 | $0.26 | 1M | 99.9% | 100.0% |
| BaseTen fp8 | $0.13 | $0.26 | 1M | 100.0% | 100.0% |
| CoreWeave fp8 | $0.13 | $0.28 | 262K | 100.0% | 100.0% |
| Nebius fp8 | $0.14 | $0.28 | 1M | 92.7% | 70.3% |
| Cohere | $0.14 | $0.28 | 1M | 99.6% | 99.8% |
| Together | $0.14 | $0.28 | 1M | 99.6% | 99.3% |
| Parasail fp8 | $0.14 | $0.28 | 1M | 99.6% | 99.5% |
| OpenInference fp8 | $0.14 | $0.70 | 1M | 100.0% | 97.8% |
| Morph | $0.14 | $0.40 | 1M | 100.0% | 99.0% |
| Venice | $0.17 | $0.35 | 1M | 99.6% | 99.4% |
| Mancer 2 fp8 | $0.20 | $0.60 | 1M | 99.4% | 99.1% |
| Fireworks | $0.22 | $0.66 | 1M | 93.5% | 98.6% |
| SiliconFlow fp8 | $0.22 | $0.66 | 1M | 99.0% | 98.8% |
| GMICloud fp8 | $0.29 | $0.86 | 1M | 100.0% | 100.0% |
| NextBit fp8 | $0.35 | $1.06 | 1M | 99.9% | 98.7% |
| Alibaba | $0.35 | $1.06 | 1M | 100.0% | 100.0% |
| Novita fp8 | $0.41 | $1.23 | 1M | 100.0% | 100.0% |
| Phala | $0.44 | $1.32 | 1M | 100.0% | 99.9% |
| Baidu fp8 | $0.44 | $1.32 | 1M | 100.0% | 99.3% |
| AtlasCloud fp4 | $0.44 | $1.32 | 1M | 99.8% | 99.8% |
| Cloudflare | $0.44 | $1.32 | 1.3M | 100.0% | 93.6% |
Provider availability updated 55m ago.
Cost calculator
Cheaper alternatives to DeepSeek V4 Flash 0731
| Model | Input | Output | Context | Intel. | |
|---|---|---|---|---|---|
I Ling 3.0 Flash VL inclusionAI | $0.06 | $0.18 | 262K | 24.6 | compare |
About DeepSeek V4 Flash 0731
DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows....
FAQ
How much does DeepSeek V4 Flash 0731 cost?
DeepSeek V4 Flash 0731 by DeepSeek costs $0.04 per 1M input tokens and $0.32 per 1M output tokens, with a 1.3M token context window. The cheapest provider currently charges $0.038 input / $0.16 output. A typical request with 2,000 input and 500 output tokens costs about $0.0002.
What is the context window of DeepSeek V4 Flash 0731?
DeepSeek V4 Flash 0731 supports up to 1,310,720 tokens of context and up to 943,718 output tokens per request.
Has DeepSeek V4 Flash 0731’s price changed?
Yes. ModelBank recorded 1 price change; the latest on 2026-09-24.
Is DeepSeek V4 Flash 0731 being deprecated?
No retirement date has been announced for DeepSeek V4 Flash 0731 as of 2026-09-24.
What are cheaper alternatives to DeepSeek V4 Flash 0731?
Cheaper options include Ling 3.0 Flash VL ($0.06/$0.18).