// DeepSeek
DeepSeek-V4-Flash
A DeepSeek model. 19 prices across 11 channels side by side, each with its source and check date – plus specs, licence, speed and benchmarks.
- Official in/out per 1M
- —
- Lowest (DeepInfra)
- $0.06 / $0.18
- Context
- 1.05M
- AA index
- 34.3
Prices checked 2026-10-22Official sources linked on every rowNo estimatesCheapest LLM APIs →
01Specs at a glance
Official values first; gaps filled from OpenRouter’s API where the vendor page is silent.
| Vendor | DeepSeek |
|---|---|
| Context window | 1.05M (1,048,576 tokens) |
| Max output | 944K |
| Input | Text |
| Output | Text |
| Tool calling / JSON | Yes / Yes |
| Weights & licence | Open weights · MIT · Hugging Face |
| Parameters | 304B (from weight files) |
| Released | Apr 24, 2026 |
| Model IDs | deepseek-v4-flash-0731 · deepseek-v4-flash · deepseek/deepseek-v4-flash · deepseek/deepseek-v4-flash-0731 |
02Prices on 11 channels
Per 1M tokens, in the currency each source publishes (1 USD = 6.7 CNY for the blended column). Sorted: official first, then cheapest.
| Channel | Source | Input | Output | Cache hit | Blended $ | Context | Notes |
|---|---|---|---|---|---|---|---|
| DeepInfra Inference platform (own price page) | Platform 10-10 | $0.06 | $0.18 | $0.015 | 0.09 | 1.05M | DeepInfra own pricing page |
| DeepInfra Inference platform (own price page) | Platform 10-10 | $0.09 | $0.18 | $0.018 | 0.113 | 1.05M | DeepInfra own pricing page |
| GMICloud · fp8 Via OpenRouter / provider listed there | OpenRouter 10-22 | $0.091 | $0.182 | $0.018 | 0.114 | 1.05M | GMICloud price as listed on OpenRouter (pass-through; quantization=fp8; discount field=0.35); not checked against GMICloud's own page |
| BaseTen · fp8 Via OpenRouter / provider listed there | OpenRouter 10-22 | $0.13 | $0.26 | $0.028 | 0.163 | 1.05M | BaseTen price as listed on OpenRouter (pass-through; quantization=fp8; discount field=0); not checked against BaseTen's own page |
| SiliconFlow · fp8 Via OpenRouter / provider listed there | OpenRouter 10-22 | $0.13 | $0.28 | $0.028 | 0.168 | 1.05M | SiliconFlow price as listed on OpenRouter (pass-through; quantization=fp8; discount field=0); not checked against SiliconFlow's own page |
| Together Inference platform (own price page) | Platform 10-10 | $0.14 | $0.28 | $0.03 | 0.175 | 1.05M | Together AI own pricing page |
| Parasail · fp8 Via OpenRouter / provider listed there | OpenRouter 10-22 | $0.14 | $0.28 | $0.05 | 0.175 | 1.05M | Parasail price as listed on OpenRouter (pass-through; quantization=fp8; discount field=0); not checked against Parasail's own page |
| AtlasCloud · fp4 Via OpenRouter / provider listed there | OpenRouter 10-22 | $0.14 | $0.28 | $0.028 | 0.175 | 1.05M | AtlasCloud price as listed on OpenRouter (pass-through; quantization=fp4; discount field=0); not checked against AtlasCloud's own page |
| Parasail · fp8 Via OpenRouter / provider listed there | OpenRouter 10-22 | $0.14 | $0.28 | $0.07 | 0.175 | 1.05M | Parasail price as listed on OpenRouter (pass-through; quantization=fp8; discount field=0); not checked against Parasail's own page |
| Alibaba Cloud · fp8 Via OpenRouter / provider listed there | OpenRouter 10-22 | $0.15 | $0.3 | $0.03 | 0.188 | 1M | Alibaba price as listed on OpenRouter (pass-through; quantization=fp8); Alibaba Cloud; promoted from endpoint candidates 2026-10-14; not checked against the provider's own page |
| Azure · unknown Via OpenRouter / provider listed there | OpenRouter 10-22 | $0.21 | $0.56 | $0.031 | 0.297 | 1.05M | Azure price as listed on OpenRouter (pass-through; quantization=unknown); Azure; promoted from endpoint candidates 2026-10-14; not checked against the provider's own page |
| SiliconFlow · fp8 Via OpenRouter / provider listed there | OpenRouter 10-22 | $0.22 | $0.66 | $0.028 | 0.33 | 1.05M | SiliconFlow price as listed on OpenRouter (pass-through; quantization=fp8; discount field=0); not checked against SiliconFlow's own page |
| GMICloud · fp8 Via OpenRouter / provider listed there | OpenRouter 10-22 | $0.286 | $0.858 | $0.0091 | 0.429 | 1.05M | GMICloud price as listed on OpenRouter (pass-through; quantization=fp8; discount field=0.35); not checked against GMICloud's own page |
| Alibaba Cloud · unknown Via OpenRouter / provider listed there | OpenRouter 10-22 | $0.352 | $1.06 | $0.035 | 0.528 | 1M | Alibaba price as listed on OpenRouter (pass-through; quantization=unknown); Alibaba Cloud; promoted from endpoint candidates 2026-10-14; not checked against the provider's own page |
| Novita · fp8 Via OpenRouter / provider listed there | OpenRouter 10-22 | $0.409 | $1.23 | $0.026 | 0.614 | 1.05M | Novita price as listed on OpenRouter (pass-through; quantization=fp8; discount field=0.07); not checked against Novita's own page |
| AtlasCloud · fp4 Via OpenRouter / provider listed there | OpenRouter 10-22 | $0.44 | $1.32 | $0.028 | 0.66 | 1.05M | AtlasCloud price as listed on OpenRouter (pass-through; quantization=fp4; discount field=0); not checked against AtlasCloud's own page |
| Cloudflare · unknown Via OpenRouter / provider listed there | OpenRouter 10-22 | $0.44 | $1.32 | $0.014 | 0.66 | 1.05M | Cloudflare price as listed on OpenRouter (pass-through; quantization=unknown); Cloudflare; promoted from endpoint candidates 2026-10-14; not checked against the provider's own page |
| Cloudflare · unknown Via OpenRouter / provider listed there | OpenRouter 10-22 | $0.44 | $1.32 | $0.014 | 0.66 | 384K | Cloudflare price as listed on OpenRouter (pass-through; quantization=unknown); Cloudflare; promoted from endpoint candidates 2026-10-14; not checked against the provider's own page |
| SiliconFlow Inference platform (own price page) | Platform 10-10 | ¥3 | ¥9 | ¥0.3 | 0.672 | — | 费用发生时段: 2点～8点: 1.5/4.5 SiliconFlow (硅基流动) own pricing page; time-of-day pricing, standard=higher band, off-peak in tiers |
“Official” = vendor pricing page; “Platform” = the platform’s own pricing page; “OpenRouter” = price listed on OpenRouter, not checked on the platform’s site. Click a source tag to open the original page.
03Where you can use it
Derived only from the price sources above. Country restrictions are set by each vendor – check their terms before you sign up.
- Inference platform (own price page)
DeepInfra · Together · SiliconFlow - Via OpenRouter / provider listed there
GMICloud · BaseTen · SiliconFlow · Parasail · AtlasCloud · Alibaba Cloud · Azure · Novita · Cloudflare - Self-host the open weights
GPU / VRAM sizing and build plans→ - Free option
DeepSeek-V4-Flash→ - Free option
DeepSeek-V4-Flash-0731→ - Free option
DeepSeek V4 Flash (AtomCode CodingPlan)→
04Performance
Speed and AA index from Artificial Analysis public leaderboards (not our own tests); benchmark scores from our benchmark library, best result per benchmark.
- AA indexDeepSeek V4 Flash 0731 (Max)
- 34.3
- Output speed (median)
- 217 tok/s
- Time to first token
- 1.29s
- AA index per $ (blended)
- 381.45
| Benchmark | Best score | Source | Date |
|---|---|---|---|
| GPQA Diamond | 91.0% | independent | 2026-08-02 |
| AIME (OTIS Mock AIME 2024–2025) | 94.4% | independent | 2026-08-02 |
05Price changes we recorded
All price changes →From our daily re-checks of the sources above.
- 2026-10-14 · Cloudflare · new listing
- 2026-10-14 · Azure · new listing
- 2026-10-14 · Alibaba Cloud · new listing
- 2026-10-14 · Cloudflare · new listing
- 2026-10-14 · Alibaba Cloud · new listing
06More from DeepSeek
- DeepSeek V4.1 Flash 1017
$0.098 / 0.294 · 1.05M→ - DeepSeek V4.1 Flash
$0.14 / 0.42 · 1M→ - DeepSeek V4 Flash Vision Exp
$0.216 / 0.647 · 1.05M→ - DeepSeek-V4-Pro
$0.957 / 1.91 · 1M→ - DeepSeek V3
$0.209 / 0.31 · 164K→ - DeepSeek V3.2 Exp
$0.27 / 0.41 · 164K→ - DeepSeek V3.1 Terminus
$0.27 / 1 · 164K→ - DeepSeek-V3.1
$0.25 / 0.95 · 164K→
FAQ
How much does the DeepSeek-V4-Flash API cost?
There is no official pay-as-you-go price in our data. The lowest listed price is $0.06 / $0.18 on DeepInfra.
What is the context window of DeepSeek-V4-Flash?
1.05M tokens of context, up to 944K output tokens. Platforms may cap it lower – see the table.
Is DeepSeek-V4-Flash open source?
Yes, the weights are published on Hugging Face (deepseek-ai/DeepSeek-V4-Flash-0731). Licence: MIT.