DeepSeek V4 Flash 0731 deepseek/deepseek-v4-flash-0731
Served by 18 providers. Cheapest: OpenRouter at $0.075 blended /1M tokens. The most expensive listing costs 10.6× as much for the same model.
| Provider | Type | Input /1M | Output /1M | Cached input | Blended | Context | Notes | Source |
|---|---|---|---|---|---|---|---|---|
| OpenRouter deepseek/deepseek-v4-flash-0731 |
LLM routers | $0.06 | $0.12 | $0.012 | $0.075 | 1.05M | api modality text->text |
✓ src 2026-09-18 |
| DeepInfra deepseek-ai/DeepSeek-V4-Flash-0731 |
Inference hosts | $0.06 | $0.18 | $0.015 | $0.09 | 1.05M | fp8 |
✓ src src2 2026-09-18 |
| Requesty deepinfra/deepseek-v4-flash-0731:flex |
LLM routers | $0.072 | $0.144 | $0.014 | $0.09 | 1.05M | upstream route deepinfra; geo global; 9 other upstream routes listed (input $0.076-$0.46/M); API list price; Requesty's 5% markup on model cost (pricing page) is not included |
✓ src 2026-09-18 |
| DigitalOcean deepseek-v4-flash-0731 |
Inference hosts | $0.08 | $0.252 | $0.025 | $0.123 | 1.05M |
✓ src src2 2026-09-18 |
|
| Baseten | Inference hosts | $0.13 | $0.26 | $0.028 | $0.163 | — | Model API id not shown on pricing page. |
◐ src 2026-09-18 |
| CoreWeave deepseek-ai/DeepSeek-V4-Flash-0731 |
Inference hosts | $0.13 | $0.28 | $0.07 | $0.168 | 262k | Context from docs model table (rounded, e.g. "262k"). |
✓ src src2 2026-09-18 |
| Featherless deepseek-ai/DeepSeek-V4-Flash-0731 |
Inference hosts | $0.14 | $0.28 | — | $0.175 | 262k | Developer-plan per-token rate; model_class deepseek4-284b; effective price differs from class base rate (docs table class rate $0.1385 in/$0.279 out) — niche-model multiplier; also usable flat-rate on $25/mo Chat plan (32K ctx, human chat only) |
✓ src src2 src3 2026-09-18 |
| Together AI deepseek-ai/DeepSeek-V4-Flash-0731 |
Inference hosts | $0.14 | $0.28 | $0.03 | $0.175 | 1.05M | fp4 |
✓ src 2026-09-18 |
| Venice.ai API deepseek-v4-flash-0731 |
Inference hosts | $0.175 | $0.35 | $0.035 | $0.219 | 1M |
✓ src src2 2026-09-18 |
|
| Fireworks AI accounts/fireworks/models/deepseek-v4-flash-0731 |
Inference hosts | $0.22 | $0.66 | $0.007 | $0.33 | — | batch −50% Priority $0.275/$0.00875/$0.825; Reserved Throughput available |
✓ src 2026-09-18 |
| SiliconFlow | Inference hosts | $0.22 | $0.66 | $0.014 | $0.33 | — | context shown on pricing page as "1049K" |
✓ src 2026-09-18 |
| Scaleway deepseek-v4-flash-0731 |
Inference hosts | $0.459 | $0.918 | $0.092 | $0.574 | — | batch −50% list price EUR 0.4/M in, EUR 0.8/M out, EUR 0.08/M cached; Paris region; prices before tax; Batches API -50%; converted at ECB EURUSD 1.1481 2026-09-17 (latest ECB reference rate) |
✓ src 2026-09-18 |
| Atlas Cloud deepseek-ai/deepseek-v4-flash-0731 |
Inference hosts | $0.44 | $1.32 | $0.028 | $0.66 | 1.05M | fp4 |
✓ src 2026-09-18 |
| Chutes deepseek-ai/DeepSeek-V4-Flash-0731-TEE |
Inference hosts | $0.44 | $1.32 | $0.044 | $0.66 | 1.05M | fp8 TEE (confidential compute); upstream weights AtlasCloud/DeepSeek-V4-Flash-0731-FP8-DSpark |
✓ src src2 2026-09-18 |
| Cloudflare Workers AI @cf/deepseek-ai/deepseek-v4-flash-0731 |
Inference hosts | $0.44 | $1.32 | $0.014 | $0.66 | — | Billed in neurons ($0.011/1k neurons); USD per-M-token equivalent as published by Cloudflare; requires Workers Paid or AI Gateway credits |
✓ src 2026-09-18 |
| Microsoft Foundry (Azure AI Foundry / Azure OpenAI) DeepSeek-V4-Flash-0731 |
Hyperscaler AI platforms | $0.44 | $1.32 | $0.014 | $0.66 | — | Global Standard, Azure Retail Prices API meter 'V4 Flash 0731 Inp glbl Tokens' (eastus); API meter is per 1K tokens, multiplied by 1000 (unit conversion only) |
✓ src src2 2026-09-18 |
| Novita AI deepseek/deepseek-v4-flash-0731 |
Inference hosts | $0.44 | $1.32 | $0.028 | $0.66 | 1.05M |
✓ src src2 2026-09-18 |
|
| Inference.net deepseek-v4-flash-0731 |
Inference hosts | $0.53 | $1.58 | $0.017 | $0.792 | 1.05M | https://inference.net/models shows the same figures |
✓ src 2026-09-18 |
✓ from the provider's own pricing page · ◐ partly confirmed there · 2° third-party source. Router prices may exclude the router's own fees; see each router's page.