DeepSeek: DeepSeek Flash Latest
deepseek/deepseek-flash-latestThis model always redirects to the latest model in the DeepSeek Flash family.
Modalities
In / out per 1M$0.01 / $0.06
Context1M
ReleasedSep 14, 2026
Providers
42 providers serve this model upstream.
| Provider | Input /M | Output /M | Cache read /M | Latency P50 | Throughput P50 | Uptime |
|---|---|---|---|---|---|---|
| $0.04 | $0.50 | $0.01 | 0.33s | 163 tps | 100% | |
| $0.04 | $0.50 | $0.01 | 0.66s | 139 tps | 100% | |
| $0.11 | $0.50 | $0.01 | 0.38s | 155 tps | 100% | |
 DigitalOcean | $0.18 | $0.72 | $0.01 | 0.82s | 153 tps | 100% |
| $0.08 | $0.55 | $0.01 | 0.29s | 120 tps | 100% | |
 Cohere | $0.20 | $0.66 | $0.01 | 0.57s | 162 tps | 100% |
| $0.08 | $0.55 | $0.01 | 0.39s | 105 tps | 100% | |
| $0.30 | $1.20 | $0.01 | 0.71s | 195 tps | 100% | |
| $0.30 | $0.90 | $0.01 | 0.59s | 264 tps | 100% | |
| $0.30 | $1.20 | $0.01 | 0.51s | 181 tps | 100% | |
| $0.12 | $0.48 | $0.00 | 1.81s | 105 tps | 100% | |
| $0.20 | $0.78 | $0.00 | 1.79s | 114 tps | 100% | |
| $0.20 | $0.78 | $0.00 | 1.39s | 102 tps | 100% | |
| $0.10 | $0.15 | $0.01 | 0.56s | 58 tps | 100% | |
 DeepInfraus · fp8 | $0.10 | $0.29 | $0.00 | 1.20s | 58 tps | 100% |
| $0.10 | $0.15 | $0.01 | 0.70s | 55 tps | 100% | |
| $0.30 | $1.20 | $0.01 | 0.66s | 118 tps | 100% | |
| $0.20 | $1.20 | $0.01 | 1.92s | 68 tps | 100% | |
 NEAR AI | $0.30 | $1.20 | $0.01 | 0.72s | 31 tps | 100% |
| $0.30 | $1.20 | $0.01 | 0.24s | 252 tps | 100% | |
| DeepInfraus · fp8 | $0.15 | $0.44 | $0.00 | 2.81s | 52 tps | 100% |
 Fireworksus | $0.45 | $1.80 | $0.01 | 0.60s | 191 tps | 100% |
| $0.17 | $0.49 | $0.01 | 0.95s | 127 tps | 99.97% | |
 Baseten | $0.30 | $1.20 | $0.01 | 0.55s | 144 tps | 99.97% |
| $0.29 | $1.20 | $0.01 | 0.63s | 128 tps | 99.97% | |
| $0.10 | $0.60 | $0.00 | 3.16s | 99 tps | 99.97% | |
 SiliconFlowfp8 | $0.30 | $1.20 | $0.01 | 1.35s | 126 tps | 99.97% |
| $0.30 | $1.20 | $0.01 | 1.07s | 133 tps | 99.97% | |
 Particle AI | $0.05 | $0.50 | $0.00 | 0.98s | 113 tps | 99.95% |
| $0.05 | $0.19 | $0.01 | 0.74s | 92 tps | 99.92% | |
| $0.25 | $1.00 | $0.01 | 0.48s | 192 tps | 99.92% | |
| $0.06 | $0.60 | $0.01 | 0.68s | 83 tps | 99.87% | |
| $0.04 | $0.50 | $0.01 | 2.41s | 71 tps | 99.87% | |
 Mistralfp8 | $0.30 | $1.20 | $0.01 | 2.14s | 186 tps | 99.86% |
| $0.28 | $1.13 | $0.01 | 0.72s | 148 tps | 99.84% | |
| $0.15 | $1.20 | $0.01 | 1.41s | 128 tps | 99.59% | |
| DeepInfraus · fp8 | $0.08 | $0.24 | $0.00 | 2.54s | 51 tps | 99.5% |
| $0.30 | $1.20 | $0.01 | 0.97s | 129 tps | 98.54% | |
| $0.17 | $0.66 | $0.02 | 1.08s | 101 tps | 98.51% | |
| Fireworks | $0.30 | $1.20 | $0.01 | 1.25s | 122 tps | 97.52% |
 DeepSeek | $0.15 | $0.60 | $0.00 | 0.87s | 56 tps | 91.22% |
| Fireworks Spot | $0.21 | $0.84 | $0.00 | 1.19s | 111 tps | 86.53% |
Market-wide measurements, refreshed every 15 minutes. They describe who serves DeepSeek Flash Latest in general, not how ProjectCOZY routes your requests.
Pricing
List rates per 1M tokens — what DeepSeek Flash Latest costs pay-as-you-go elsewhere, not what you pay here.
Input
$0.01
per 1M tokens
Output
$0.06
per 1M tokens
Cache read
$0.01
per 1M cached tokens
Included in every pass
DeepSeek Flash Latest is included in every ProjectCOZY pass at no extra cost — one flat rate, no per-token metering. The rates above are there for comparison.
Performance
Time to first token and output speed across every provider, over the last 3 days.
0.0s50.0s100.0s150.0s200.0s
Oct 29, 12 AMOct 29, 8 AMOct 29, 4 PMOct 30, 12 AMOct 30, 8 AMOct 30, 4 PMOct 31, 12 AMOct 31, 8 AMOct 31, 4 PMNov 1, 12 AMNov 1, 8 AM
AtlasCloud Fireworks (us) Modal Fireworks Spot SiliconFlow Makora Open Inference Alibaba Cloud Int. Sail Research Parasail Sail Research (us) Venice Wafer Particle AI DeepInfra (us) Morph (us) Cloudflare DeepInfra (us) inference.net (us) Nebius Token Factory NovitaAI Relace Baidu Qianfan GMICloud DeepSeek DeepInfra (us) Baseten Crusoe Reka AI StreamLake Wafer (us) Phala Cohere Fireworks DigitalOcean inference.net Ionstream Together Prime Intellect Mistral NEAR AI Relace
0 tok/s2000 tok/s4000 tok/s6000 tok/s8000 tok/s
Oct 29, 12 AMOct 29, 8 AMOct 29, 4 PMOct 30, 12 AMOct 30, 8 AMOct 30, 4 PMOct 31, 12 AMOct 31, 8 AMOct 31, 4 PMNov 1, 12 AMNov 1, 8 AM
AtlasCloud Fireworks (us) Modal Fireworks Spot SiliconFlow Makora Open Inference Alibaba Cloud Int. Sail Research Parasail Sail Research (us) Venice Wafer Particle AI DeepInfra (us) Morph (us) Cloudflare DeepInfra (us) inference.net (us) Nebius Token Factory NovitaAI Relace Baidu Qianfan GMICloud DeepSeek DeepInfra (us) Baseten Crusoe Reka AI StreamLake Wafer (us) Phala Cohere Fireworks DigitalOcean inference.net Ionstream Together Prime Intellect Mistral NEAR AI Relace
Uptime
Share of requests that at least one provider served successfully.
Last 3 days
Oct 29, 6:00 PMNow
Availability over the last 24 hours
100% 98% 97% 95%
Oct 31, 6:10 PMNow
Apps
Tools that most often run DeepSeek Flash Latest, by tokens this week.
No apps published
This measurement has not been published for the model yet. It appears as soon as it is.
Activity
Tokens processed market-wide.
No activity published
This measurement has not been published for the model yet. It appears as soon as it is.
FAQ
Which model id do I use for DeepSeek Flash Latest?
~deepseek/deepseek-flash-latest. Send it as the model field from any OpenAI-compatible client, against https://minuykh.app/v1.
How much context does DeepSeek Flash Latest hold?
1,048,576 tokens per request, of which up to 943,718 can be the response.
What can it accept and return?
Input: text, image. Output: text.
What does DeepSeek Flash Latest cost on a pass?
Nothing beyond the pass itself. Pay-as-you-go elsewhere it lists at $0.01 per 1M input tokens and $0.06 per 1M output tokens.
Who built DeepSeek Flash Latest?
DeepSeek, in the DeepSeek family.
Explore
Other models your pass can call.
