Quality
How DeepSeek: DeepSeek V4.1 Flash compares against every tracked model
Composite of GPQA Diamond, Mock AIME 2024–25, MATH Level 5, SWE-bench Verified, LiveBench, Humanity's Last Exam and Terminal-Bench, normalised 0–100. Scores are ingested from their publishers; we do not run these evaluations. This model is not in this ranking: it holds no Known Good Index score.
Quality Breakdown
DeepSeek: DeepSeek V4.1 Flash on each evaluation feeding the index, against the tracked average
Bar = DeepSeek: DeepSeek V4.1 Flash · grey marker = average across tracked models
None of the seven index evaluations have published a score for this model yet.
Arena Elo
Human preference rating from blind pairwise votes
Elo from blind pairwise votes, ingested from Arena
DeepSeek: DeepSeek V4.1 Flash does not currently appear in any arena we ingest.
Price & Cost
Published API pricing by token type
USD per 1M tokens at a 3:1 input:output blend. Live from OpenRouter, cross-checked against models.dev. Lower is better. Ranked against the 504 models priced above zero, which is the population the chart draws; excludes 39 published at no cost (free and promotional tiers).
Flashthis #194/504 · off scale
Context Window
Maximum input tokens accepted
Maximum input context from provider metadata via models.dev and OpenRouter. Higher is better.
Flashthis #110/550
Speed
Mean output throughput across hosting providers, over successful measurements from the last 48 hours
Mean output tokens per second across all tracked providers, over successful measurements from the last 48 hours. Derived from OpenRouter endpoint telemetry. Higher is better.
Flashthis #64/356 · below scale
Latency
Time to first token, mean across providers over successful measurements from the last 48 hours
Seconds to first streamed chunk, mean across tracked providers over successful measurements from the last 48 hours. Derived from OpenRouter endpoint telemetry. Lower is better.
Flashthis #189/366 · off scale
Providers
Hosts serving DeepSeek: DeepSeek V4.1 Flash, with their own price and speed
| Provider | Input $/M | Output $/M | Blended | Speed | TTFT | Context |
|---|---|---|---|---|---|---|
| Together | $0.30 | $1.20 | $0.53 | 263 | 0.3s | 1.05M |
| BaseTen | $0.30 | $1.20 | $0.53 | 255 | 0.4s | 1.05M |
| Fireworks | $0.30 | $1.20 | $0.53 | 242 | 0.3s | 1.05M |
| DigitalOcean | $0.23 | $0.90 | $0.39 | 220 | 0.8s | 1.05M |
| Modal | $0.30 | $1.20 | $0.53 | 212 | 0.6s | 1.05M |
| Makora | $0.27 | $1.15 | $0.49 | 169 | 0.6s | 1.05M |
| DeepSeek · first party | $0.15 | $0.60 | $0.26 | 157 | 1.0s | 1.05M |
| Parasail | $0.30 | $1.20 | $0.53 | 156 | 1.0s | 1.05M |
| Crusoe | $0.29 | $1.20 | $0.52 | 152 | 0.3s | 1.05M |
| CoreWeave | $0.20 | $0.65 | $0.31 | 146 | 0.5s | 1.05M |
| InferenceNet | $0.10 | $0.60 | $0.23 | 132 | 0.7s | 1.04M |
| Baidu · first party | $0.04 | $0.14 | $0.06 | 126 | 1.1s | 1.05M |
| Venice | $0.30 | $1.20 | $0.53 | 122 | 0.8s | 1.00M |
| Novita | $0.20 | $0.78 | $0.34 | 112 | 1.4s | 1.05M |
| AtlasCloud | $0.30 | $1.20 | $0.53 | 110 | 1.2s | 1.05M |
| Relace | $0.02 | $1.20 | $0.31 | 104 | 1.0s | 1.05M |
| Krea | $0.23 | $0.90 | $0.39 | 99 | 1.9s | 1.05M |
| DekaLLM | $0.12 | $1.20 | $0.39 | 91 | 1.5s | 1.05M |
| GMICloud | $0.18 | $0.72 | $0.32 | 90 | 2.5s | 1.05M |
| Phala | $0.21 | $0.84 | $0.37 | 87 | 1.1s | 1.05M |
| Morph | $0.02 | $0.60 | $0.17 | 82 | 0.6s | 1.05M |
| Wafer | $0.04 | $0.40 | $0.13 | 82 | 0.5s | 1.05M |
| Io Net | $0.11 | $0.41 | $0.18 | 80 | 1.4s | 1.05M |
| StreamLake | $0.15 | $0.60 | $0.26 | 75 | 1.5s | 1.02M |
| Ionstream | $0.05 | $1.15 | $0.33 | 74 | 1.2s | 1.05M |
| SiliconFlow | $0.30 | $1.20 | $0.53 | 73 | 2.8s | 1.05M |
| DeepInfra | $0.14 | $0.42 | $0.21 | 62 | 1.0s | 1.05M |
| Decart | $0.09 | $0.18 | $0.11 | 55 | 0.9s | 1.05M |
| NextBit | $0.21 | $0.84 | $0.37 | 53 | 2.4s | 1.05M |
| Reka · first party | $0.10 | $0.84 | $0.29 | 46 | 0.6s | 1.05M |
| Sail Research | $0.08 | $0.40 | $0.16 | 43 | 1.4s | 1.05M |
| Alibaba · first party | $0.15 | $0.60 | $0.26 | 31 | 7.0s | 1.00M |
| OpenInference | $0.20 | $1.00 | $0.40 | 27 | 3.9s | 1.05M |
Per-host pricing and telemetry from OpenRouter. Speed is output tokens per second; TTFT is time to first token.
History
How price and quality have moved since we began tracking this model
Since 10 Sep 2026
| Known Good Index | — |
| Blended price | $0.53 per 1M · observed 8 Oct 2026 |
| Output speed | 111 tok/s · observed 8 Oct 2026 |
| Time to first token | 1.4s |
Comparisons
Head-to-head pages pairing DeepSeek: DeepSeek V4.1 Flash with other tracked models
Head-to-head pages are generated for the top 50 models by Known Good Index, which DeepSeek: DeepSeek V4.1 Flash is not currently in. Its nearest tracked models by index are below.