RedRouterDeepSeek V4.1 Flash (undated derivative)
Updated Trailing 72 hours
Provider comparison
DeepSeek V4.1 Flash 1017- DeepSeek V4.1 Flash (undated derivative)
GLM 5.3 Flash- GLM 5.3
 abliteration.aivia Abliterated Large Flash |
DeepSeek V4.1 Flash (undated derivative) | abliterated | Unknown | 1,048,576 | $1.250 | $1.000 | $2.000 | 350.1 | 1.1 | 2.7 | 100.0%32 / 32 requests | ok | 07 Nov 2026, 18:10 UTC |
 NanoGPT → abliteration.ai |
DeepSeek V4.1 Flash (undated derivative) | abliterated | FP8 | 1,000,000 | $1.312 | $1.050 | $2.100 | 300.8 | 2.3 | 4.0 | 100.0%32 / 32 requests | ok | 07 Nov 2026, 18:14 UTC |
| NanoGPT → Venice |
DeepSeek V4.1 Flash (undated derivative) | uncensored | FP8 | 524,288 | $0.608 | $0.347 | $1.390 | 181.4 | 1.8 | 4.5 | 75.0%24 / 32 requests | failing | 07 Nov 2026, 18:13 UTC |
 Refuseless |
DeepSeek V4.1 Flash (undated derivative) | abliterated | FP8 | 1,048,576 | $0.203 | $0.120 | $0.450 | 140.3 | 1.7 | 5.3 | 100.0%32 / 32 requests | ok | 07 Nov 2026, 18:11 UTC |
 Yeta Labs |
DeepSeek V4.1 Flash (undated derivative) | uncensored | FP8 | 1,000,000 | $0.147 | $0.080 | $0.350 | 140.8 | 1.7 | 5.1 | 100.0%32 / 32 requests | ok | 07 Nov 2026, 18:04 UTC |
p50 = median. Missing speed or latency values mean fewer than 8 usable successes. Success rate includes failed requests. Status and last success describe the route across all regions. Precision and context are provider declarations; different modifications are different products. Measurement details →
Output speed
tok/s · Higher is better · p50
Reported completion tokens after the first chunk, divided by streaming time. Samples without reported usage are excluded. Methodology ↗
Time to first token
s · Lower is better · p50
Request sent to first non-empty content, reasoning or tool-argument delta. Includes network time from the selected region. Methodology ↗
Time to 500 tokens
s · Lower is better · p50
Per request: TTFT + 500 ÷ output tok/s. Percentiles are computed after this calculation; this is a derived response time. Methodology ↗
Blended price
$ / 1M tokens · Lower is better
Declared price: (3 × input + output) ÷ 4. Excludes cache discounts. Prices are not measured billing receipts. Methodology ↗
Output speed vs. price
Median output speed and declared blended price
- abliteration.ai · Abliterated Large Flash
- NanoGPT → abliteration.ai
- NanoGPT → Venice
- Refuseless
- Yeta Labs
Each point is one route. Shading divides the displayed axes at their midpoints; it is not a quality rating. Blended price uses a 3:1 input/output mix. Routes without usable speed samples are omitted. Methodology ↗
Performance over time
8-hour buckets · UTC
Output speed
7 days · tok/s · p50
Per-bucket median of successful, usable samples. Gaps remain unconnected. All regions shows separate regional series: solid US East, dashed US West. Medians are never averaged. Methodology ↗
Time to first token
7 days · seconds · p50
Per-bucket median of successful, usable samples. Gaps remain unconnected. All regions shows separate regional series: solid US East, dashed US West. Medians are never averaged. Methodology ↗
Success rate
7 days · %
Successful requests ÷ all requests in each bucket. Gaps remain unconnected. All regions shows separate regional series: solid US East, dashed US West. Medians are never averaged. Methodology ↗
Output speed
14 days · tok/s · p50
Per-bucket median of successful, usable samples. Gaps remain unconnected. All regions shows separate regional series: solid US East, dashed US West. Medians are never averaged. Methodology ↗
Time to first token
14 days · seconds · p50
Per-bucket median of successful, usable samples. Gaps remain unconnected. All regions shows separate regional series: solid US East, dashed US West. Medians are never averaged. Methodology ↗
Success rate
14 days · %
Successful requests ÷ all requests in each bucket. Gaps remain unconnected. All regions shows separate regional series: solid US East, dashed US West. Medians are never averaged. Methodology ↗
- abliteration.ai · Abliterated Large Flash
- NanoGPT → abliteration.ai
- NanoGPT → Venice
- Refuseless
- Yeta Labs
| abliteration.aivia Abliterated Large Flash |
DeepSeek V4.1 Flash (undated derivative) | abliterated | Unknown | 1,048,576 | $1.250 | $1.000 | $2.000 | 306.5 | 1.0 | 2.9 | 100.0%16 / 16 requests | ok | 07 Nov 2026, 18:10 UTC |
| NanoGPT → abliteration.ai |
DeepSeek V4.1 Flash (undated derivative) | abliterated | FP8 | 1,000,000 | $1.312 | $1.050 | $2.100 | 283.9 | 2.2 | 3.8 | 100.0%16 / 16 requests | ok | 07 Nov 2026, 18:14 UTC |
| NanoGPT → Venice |
DeepSeek V4.1 Flash (undated derivative) | uncensored | FP8 | 524,288 | $0.608 | $0.347 | $1.390 | 164.8 | 1.7 | 4.7 | 75.0%12 / 16 requests | failing | 07 Nov 2026, 18:13 UTC |
| Refuseless |
DeepSeek V4.1 Flash (undated derivative) | abliterated | FP8 | 1,048,576 | $0.203 | $0.120 | $0.450 | 128.4 | 1.7 | 5.9 | 100.0%16 / 16 requests | ok | 07 Nov 2026, 18:11 UTC |
| Yeta Labs |
DeepSeek V4.1 Flash (undated derivative) | uncensored | FP8 | 1,000,000 | $0.147 | $0.080 | $0.350 | 141.8 | 1.7 | 5.2 | 100.0%16 / 16 requests | ok | 07 Nov 2026, 18:04 UTC |
p50 = median. Missing speed or latency values mean fewer than 8 usable successes. Success rate includes failed requests. Status and last success describe the route across all regions. Precision and context are provider declarations; different modifications are different products. Measurement details →
Output speed
tok/s · Higher is better · p50
Reported completion tokens after the first chunk, divided by streaming time. Samples without reported usage are excluded. Methodology ↗
Time to first token
s · Lower is better · p50
Request sent to first non-empty content, reasoning or tool-argument delta. Includes network time from the selected region. Methodology ↗
Time to 500 tokens
s · Lower is better · p50
Per request: TTFT + 500 ÷ output tok/s. Percentiles are computed after this calculation; this is a derived response time. Methodology ↗
Blended price
$ / 1M tokens · Lower is better
Declared price: (3 × input + output) ÷ 4. Excludes cache discounts. Prices are not measured billing receipts. Methodology ↗
Output speed vs. price
Median output speed and declared blended price
- abliteration.ai · Abliterated Large Flash
- NanoGPT → abliteration.ai
- NanoGPT → Venice
- Refuseless
- Yeta Labs
Each point is one route. Shading divides the displayed axes at their midpoints; it is not a quality rating. Blended price uses a 3:1 input/output mix. Routes without usable speed samples are omitted. Methodology ↗
Performance over time
8-hour buckets · UTC
Output speed
7 days · tok/s · p50
Per-bucket median of successful, usable samples. Gaps remain unconnected. All regions shows separate regional series: solid US East, dashed US West. Medians are never averaged. Methodology ↗
Time to first token
7 days · seconds · p50
Per-bucket median of successful, usable samples. Gaps remain unconnected. All regions shows separate regional series: solid US East, dashed US West. Medians are never averaged. Methodology ↗
Success rate
7 days · %
Successful requests ÷ all requests in each bucket. Gaps remain unconnected. All regions shows separate regional series: solid US East, dashed US West. Medians are never averaged. Methodology ↗
Output speed
14 days · tok/s · p50
Per-bucket median of successful, usable samples. Gaps remain unconnected. All regions shows separate regional series: solid US East, dashed US West. Medians are never averaged. Methodology ↗
Time to first token
14 days · seconds · p50
Per-bucket median of successful, usable samples. Gaps remain unconnected. All regions shows separate regional series: solid US East, dashed US West. Medians are never averaged. Methodology ↗
Success rate
14 days · %
Successful requests ÷ all requests in each bucket. Gaps remain unconnected. All regions shows separate regional series: solid US East, dashed US West. Medians are never averaged. Methodology ↗
- abliteration.ai · Abliterated Large Flash
- NanoGPT → abliteration.ai
- NanoGPT → Venice
- Refuseless
- Yeta Labs
| abliteration.aivia Abliterated Large Flash |
DeepSeek V4.1 Flash (undated derivative) | abliterated | Unknown | 1,048,576 | $1.250 | $1.000 | $2.000 | 390.3 | 1.2 | 2.5 | 100.0%16 / 16 requests | ok | 07 Nov 2026, 18:10 UTC |
| NanoGPT → abliteration.ai |
DeepSeek V4.1 Flash (undated derivative) | abliterated | FP8 | 1,000,000 | $1.312 | $1.050 | $2.100 | 314.8 | 2.5 | 4.0 | 100.0%16 / 16 requests | ok | 07 Nov 2026, 18:14 UTC |
| NanoGPT → Venice |
DeepSeek V4.1 Flash (undated derivative) | uncensored | FP8 | 524,288 | $0.608 | $0.347 | $1.390 | 216.3 | 1.9 | 4.1 | 75.0%12 / 16 requests | failing | 07 Nov 2026, 18:13 UTC |
| Refuseless |
DeepSeek V4.1 Flash (undated derivative) | abliterated | FP8 | 1,048,576 | $0.203 | $0.120 | $0.450 | 148.3 | 2.2 | 5.1 | 100.0%16 / 16 requests | ok | 07 Nov 2026, 18:11 UTC |
| Yeta Labs |
DeepSeek V4.1 Flash (undated derivative) | uncensored | FP8 | 1,000,000 | $0.147 | $0.080 | $0.350 | 140.8 | 1.5 | 4.8 | 100.0%16 / 16 requests | ok | 07 Nov 2026, 18:04 UTC |
p50 = median. Missing speed or latency values mean fewer than 8 usable successes. Success rate includes failed requests. Status and last success describe the route across all regions. Precision and context are provider declarations; different modifications are different products. Measurement details →
Output speed
tok/s · Higher is better · p50
Reported completion tokens after the first chunk, divided by streaming time. Samples without reported usage are excluded. Methodology ↗
Time to first token
s · Lower is better · p50
Request sent to first non-empty content, reasoning or tool-argument delta. Includes network time from the selected region. Methodology ↗
Time to 500 tokens
s · Lower is better · p50
Per request: TTFT + 500 ÷ output tok/s. Percentiles are computed after this calculation; this is a derived response time. Methodology ↗
Blended price
$ / 1M tokens · Lower is better
Declared price: (3 × input + output) ÷ 4. Excludes cache discounts. Prices are not measured billing receipts. Methodology ↗
Output speed vs. price
Median output speed and declared blended price
- abliteration.ai · Abliterated Large Flash
- NanoGPT → abliteration.ai
- NanoGPT → Venice
- Refuseless
- Yeta Labs
Each point is one route. Shading divides the displayed axes at their midpoints; it is not a quality rating. Blended price uses a 3:1 input/output mix. Routes without usable speed samples are omitted. Methodology ↗
Performance over time
8-hour buckets · UTC
Output speed
7 days · tok/s · p50
Per-bucket median of successful, usable samples. Gaps remain unconnected. All regions shows separate regional series: solid US East, dashed US West. Medians are never averaged. Methodology ↗
Time to first token
7 days · seconds · p50
Per-bucket median of successful, usable samples. Gaps remain unconnected. All regions shows separate regional series: solid US East, dashed US West. Medians are never averaged. Methodology ↗
Success rate
7 days · %
Successful requests ÷ all requests in each bucket. Gaps remain unconnected. All regions shows separate regional series: solid US East, dashed US West. Medians are never averaged. Methodology ↗
Output speed
14 days · tok/s · p50
Per-bucket median of successful, usable samples. Gaps remain unconnected. All regions shows separate regional series: solid US East, dashed US West. Medians are never averaged. Methodology ↗
Time to first token
14 days · seconds · p50
Per-bucket median of successful, usable samples. Gaps remain unconnected. All regions shows separate regional series: solid US East, dashed US West. Medians are never averaged. Methodology ↗
Success rate
14 days · %
Successful requests ÷ all requests in each bucket. Gaps remain unconnected. All regions shows separate regional series: solid US East, dashed US West. Medians are never averaged. Methodology ↗
- abliteration.ai · Abliterated Large Flash
- NanoGPT → abliteration.ai
- NanoGPT → Venice
- Refuseless
- Yeta Labs
Published results from other evaluators
These are stock-model results from other evaluators, not RedRouter measurements, and not measurements of the listed hosts or their modified models. Benchmark versions, reasoning settings and agent/scaffold choices can differ. Missing run dates and versions are not reported by the source; model release dates are never substituted.
| Model | Benchmark / version | Score | Evaluator / agent | Run date | Source and attribution |
|---|---|---|---|---|---|
| deepseek-v4.1-flashdeepseek-v4.1-flash_max | Chess PuzzlesVersion: Not reported | 0.4800 fractionBest score (across scorers) | Epoch AIAgent: Not reported Scaffold: Not reported |
2026-10-13 | Source: Epoch AI, CC BY 4.0, accessed 2026-11-07. Adapted by RedRouter. CC BY 4.0 · Original result · Licence evidence |
| deepseek-v4.1-flashdeepseek-v4.1-flash_max | FrontierMath-Tier-4-v2-PrivateVersion: Not reported | 0.2683 fractionBest score (across scorers) | Epoch AIAgent: Not reported Scaffold: Not reported |
2026-10-08 | Source: Epoch AI, CC BY 4.0, accessed 2026-11-07. Adapted by RedRouter. CC BY 4.0 · Original result · Licence evidence |
| deepseek-v4.1-flashdeepseek-v4.1-flash_max | FrontierMath-Tiers-1-3-v2-PrivateVersion: Not reported | 0.6737 fractionBest score (across scorers) | Epoch AIAgent: Not reported Scaffold: Not reported |
2026-10-08 | Source: Epoch AI, CC BY 4.0, accessed 2026-11-07. Adapted by RedRouter. CC BY 4.0 · Original result · Licence evidence |
| deepseek-v4.1-flashdeepseek-v4.1-flash_max | Furniture AssemblyVersion: Not reported | 0.3417 fractionBest score (across scorers) | Epoch AIAgent: Not reported Scaffold: Not reported |
2026-10-08 | Source: Epoch AI, CC BY 4.0, accessed 2026-11-07. Adapted by RedRouter. CC BY 4.0 · Original result · Licence evidence |
| deepseek-v4.1-flashdeepseek-v4.1-flash_max | GPQA diamondVersion: Not reported | 0.8984 fractionBest score (across scorers) | Epoch AIAgent: Not reported Scaffold: Not reported |
2026-10-09 | Source: Epoch AI, CC BY 4.0, accessed 2026-11-07. Adapted by RedRouter. CC BY 4.0 · Original result · Licence evidence |
| deepseek-v4.1-flashdeepseek-v4.1-flash_max | Mystery Game PuzzlesVersion: Not reported | 0.4300 fractionBest score (across scorers) | Epoch AIAgent: Not reported Scaffold: Not reported |
2026-10-08 | Source: Epoch AI, CC BY 4.0, accessed 2026-11-07. Adapted by RedRouter. CC BY 4.0 · Original result · Licence evidence |
| deepseek-v4.1-flashdeepseek-v4.1-flash_max | OTIS Mock AIME 2024-2025Version: Not reported | 0.9833 fractionBest score (across scorers) | Epoch AIAgent: Not reported Scaffold: Not reported |
2026-10-08 | Source: Epoch AI, CC BY 4.0, accessed 2026-11-07. Adapted by RedRouter. CC BY 4.0 · Original result · Licence evidence |
| deepseek-v4.1-flashdeepseek-v4.1-flash_max | SimpleQA VerifiedVersion: Not reported | 0.4290 fractionBest score (across scorers) | Epoch AIAgent: Not reported Scaffold: Not reported |
2026-10-13 | Source: Epoch AI, CC BY 4.0, accessed 2026-11-07. Adapted by RedRouter. CC BY 4.0 · Original result · Licence evidence |
| deepseek-v4.1-flashdeepseek-v4.1-flash_max | WebDev ArenaVersion: Not reported | 1,613.9500 pointsArena Score | Arena (LMArena)Agent: Not reported Scaffold: Not reported |
Not reported | Source: Arena (LMArena), CC BY 4.0, accessed 2026-11-07. Adapted by RedRouter. CC BY 4.0 · Original result · Licence evidenceSource: Epoch AI, CC BY 4.0, accessed 2026-11-07. Adapted by RedRouter. CC BY 4.0 |