ModelBench API
DeepSeek logo
Models/DeepSeek

DeepSeek: DeepSeek V4.1 Flash

DeepSeek V4.1 Flash model for reasoning and agentic coding

Source-linked deepseek-flash Open weights MIT Released 2026-09-10
API record Report
InputT
OutputT
Input price$0.02/M
Output price$1.00/M
Context1M
Max output384K
Providers75
Inference availability

Providers

Provider-specific identifiers, limits, and listed prices per million tokens. Every row links back to the provider's own documentation.

Report a price
Providers offering DeepSeek V4.1 Flash
ProviderProvider model IDContextMax outputInputOutputCache readCapabilitiesDocs
NaN deepseek-v4-flash 1M 384K — — — ReasoningToolsJSON Docs ↗
AMD DeepSeek-V4.1-Flash 1.05M 384K — — — ReasoningToolsJSON Docs ↗
Alibaba Token Plan (China) deepseek-v4.1-flash 1M 384K — — — ReasoningToolsJSON Docs ↗
Alibaba Token Plan deepseek-v4.1-flash 1M 384K — — — ReasoningTools Docs ↗
SCNet Token Plan DeepSeek-V4.1-Flash 1M 384K — — — ReasoningToolsJSON Docs ↗
Umans AI Coding Plan umans-deepseek-v4.1-flash 1.05M 393K — — — ReasoningToolsJSON Docs ↗
Nvidia deepseek-ai/deepseek-v4.1-flash 1M 384K — — — ReasoningToolsJSON Docs ↗
SenseNova (China) deepseek-v4.1-flash 1.05M 65.5K — — — ReasoningToolsJSON Docs ↗
OpenRouter deepseek/deepseek-v4.1-flash 1.05M 944K $0.02 $1.00 $0.01 ReasoningToolsJSON Docs ↗
engy deepseek-v4.1-flash 1.05M 65.5K $0.03 $0.12 $0.006 ReasoningToolsJSON Docs ↗
engy deepseek-v4.1-flash-1017 1.05M 65.5K $0.04 $0.08 $0.008 ReasoningToolsJSON Docs ↗
NanoGPT deepseek/deepseek-v4.1-flash 1M 384K $0.05 $0.21 $0.0011 ReasoningToolsJSON Docs ↗
Vercel AI Gateway deepseek/deepseek-v4.1-flash 1.05M 32.8K $0.07 $0.30 $0.0015 ReasoningToolsJSON Docs ↗
ZenMux deepseek/deepseek-v4.1-flash 1M 384K $0.07 $0.30 $0.0015 ReasoningToolsJSON Docs ↗
DevPass (LLM Gateway) deepseek-v4.1-flash 1.05M 384K $0.10 $0.30 $0.0025 ReasoningToolsJSON Docs ↗
Standard Compute deepseek/deepseek-v4.1-flash 1M 50K $0.14 $0.42 $0.0042 ReasoningToolsJSON Docs ↗
OpenCode Go deepseek-flash 1M 384K $0.15 $0.60 $0.003 ReasoningToolsJSON Docs ↗
LLM Gateway deepseek/deepseek-v4.1-flash 1.05M 393K $0.15 $0.60 $0.003 ReasoningTools Docs ↗
Merge Gateway deepseek/deepseek-v4.1-flash 1M 384K $0.15 $0.60 $0.003 ReasoningToolsJSON Docs ↗
DeepSeek deepseek-flash 1M 393K $0.15 $0.60 $0.003 ReasoningToolsJSON Docs ↗
OpenCode Go deepseek-v4.1-flash 1M 384K $0.15 $0.60 $0.003 ReasoningToolsJSON Docs ↗
Ollama Cloud deepseek-v4.1-flash 1.05M 384K $0.15 $0.60 $0.003 ReasoningTools Docs ↗
ClinePass cline-pass/deepseek-v4.1-flash 1M 384K $0.15 $0.60 $0.003 ReasoningToolsJSON Docs ↗
302.AI deepseek-flash 1M 384K $0.15 $0.60 $0.003 ReasoningToolsJSON Docs ↗
Neuralwatt deepseek-v4.1-flash 1.05M 393K $0.15 $0.60 $0.01 ReasoningToolsJSON Docs ↗
Umans AI umans-deepseek-v4.1-flash 1.05M 393K $0.15 $0.60 $0.03 ReasoningToolsJSON Docs ↗
Tempr Gateway deepseek/deepseek-flash 1M 384K $0.15 $0.60 $0.003 ReasoningToolsJSON Docs ↗
Vultr deepseek-v4.1-flash 1.05M 384K $0.15 $0.60 — ReasoningToolsJSON Docs ↗
CommandCode deepseek/deepseek-v4.1-flash 1M 384K $0.15 $0.60 $0.003 ReasoningToolsJSON Docs ↗
CoreWeave deepseek-ai/DeepSeek-V4.1-Flash 1.05M 1.05M $0.15 $0.65 $0.002 ReasoningToolsJSON Docs ↗
AIHubMix deepseek-v4.1-flash 1M 384K $0.15 $0.62 $0.0031 ReasoningToolsJSON Docs ↗
Kenari deepseek-v4-1-flash 1M 384K $0.16 $0.31 $0.0037 ReasoningToolsJSON Docs ↗
above.dev deepseek-v4-flash 1M 384K $0.17 $0.66 $0.0033 ReasoningToolsJSON Docs ↗
above.dev deepseek-v4.1-flash 1M 384K $0.17 $0.66 $0.0033 ReasoningToolsJSON Docs ↗
IteraCompute deepseek/deepseek-v4.1-flash 1.05M 393K $0.17 $0.70 $0.005 ReasoningToolsJSON Docs ↗
Deep Infra deepseek-ai/DeepSeek-V4.1-Flash 1.05M 384K $0.20 $0.60 $0.006 ReasoningToolsJSON Docs ↗
Boundless deepseek-v4.1-flash 1.05M 384K $0.20 $1.00 $0.01 ReasoningToolsJSON Docs ↗
Cortecs deepseek-v4.1-flash 1.05M 393K $0.20 $0.60 $0.004 ReasoningToolsJSON Docs ↗
Arcee deepseek/deepseek-v4.1-flash 1M 384K $0.22 $0.66 $0.007 ReasoningToolsJSON Docs ↗
Melious deepseek-v4.1-flash 1M 384K $0.23 $1.16 $0.01 ReasoningToolsJSON Docs ↗
Vancine deepseek-flash 1M 384K $0.24 $0.96 $0.0048 ReasoningToolsJSON Docs ↗
Vancine deepseek-v4.1-flash 1M 384K $0.24 $0.96 $0.0048 ReasoningToolsJSON Docs ↗
CoralBricks deepseek-v4.1-flash-fast 1.05M 393K $0.25 $1.20 $0.005 ReasoningToolsJSON Docs ↗
GreenPT deepseek-v4.1-flash 1M 384K $0.26 $1.28 $0.01 ReasoningToolsJSON Docs ↗
AKI.IO deepseek-v4.1-flash-552b 1.05M 81.9K $0.28 $1.12 $0.11 ReasoningToolsJSON Docs ↗
Alibaba (China) deepseek-v4.1-flash 1M 384K $0.30 $1.19 $0.01 ReasoningToolsJSON Docs ↗
CrossModel deepseek/deepseek-v4.1-flash 1M 384K $0.30 $1.20 $0.006 ReasoningToolsJSON Docs ↗
Kilo Gateway deepseek/deepseek-v4.1-flash 1.05M 944K $0.30 $1.20 $0.006 ReasoningToolsJSON Docs ↗
Venice AI deepseek-v4-1-flash 1M 131K $0.30 $1.20 $0.0075 ReasoningToolsJSON Docs ↗
Hugging Face deepseek-ai/DeepSeek-V4.1-Flash 1.05M 384K $0.30 $1.20 — ReasoningToolsJSON Docs ↗
Fireworks AI accounts/fireworks/models/deepseek-v4p1-flash 1M 384K $0.30 $1.20 $0.006 ReasoningToolsJSON Docs ↗
Ofox deepseek/deepseek-v4.1-flash 1M 384K $0.30 $1.20 $0.006 ReasoningToolsJSON Docs ↗
Baseten deepseek-ai/DeepSeek-V4.1-Flash 1.05M 32.8K $0.30 $1.20 $0.007 ReasoningToolsJSON Docs ↗
Together AI deepseek-ai/DeepSeek-V4.1-Flash 1.05M 384K $0.30 $1.20 $0.006 ReasoningToolsJSON Docs ↗
EmpirioLabs AI deepseek-v4-1-flash 1M 393K $0.30 $1.20 $0.30 ReasoningToolsJSON Docs ↗
DigitalOcean deepseek-v4.1-flash 1.05M 1.05M $0.30 $1.20 $0.006 ReasoningToolsJSON Docs ↗
OpenCode deepseek-v4.1-flash 1M 384K $0.30 $1.20 $0.006 ReasoningToolsJSON Docs ↗
Nebius Token Factory deepseek-ai/DeepSeek-V4.1-Flash 1.05M 1.05M $0.30 $1.20 $0.01 ReasoningToolsJSON Docs ↗
ai& deepseek-ai/deepseek-v4.1-flash 1.05M 384K $0.30 $0.60 $0.02 ReasoningToolsJSON Docs ↗
Novita AI deepseek/deepseek-v4.1-flash 1.05M 393K $0.30 $1.20 $0.006 ReasoningToolsJSON Docs ↗
NEAR AI Cloud deepseek/deepseek-v4.1-flash 1M 384K $0.30 $1.20 $0.006 ReasoningToolsJSON Docs ↗
Prime Inference deepseek/deepseek-v4.1-flash 1.05M 131K $0.30 $1.20 $0.006 ReasoningToolsJSON Docs ↗
AI/ML API deepseek/deepseek-v4.1-flash 1.05M 384K $0.30 $1.20 $0.006 ReasoningToolsJSON Docs ↗
Neon deepseek-v4-1-flash 1M 384K $0.30 $1.20 $0.03 ReasoningToolsJSON Docs ↗
Venice AI deepseek-v4-1-flash-1017 1M 131K $0.30 $1.20 $0.0075 ReasoningToolsJSON Docs ↗
Modal deepseek-ai/DeepSeek-V4.1-Flash 1M 384K $0.30 $1.20 $0.03 ReasoningToolsJSON Docs ↗
Vivgrid deepseek-v4.1-flash 1M 384K $0.31 $1.23 $0.01 ReasoningToolsJSON Docs ↗
Charm Hyper deepseek-v4.1-flash 1M 262K $0.33 $1.31 $0.03 ReasoningToolsJSON Docs ↗
Requesty deepseek-v4.1-flash 1.05M 393K $0.50 $1.50 $0.05 ReasoningToolsJSON Docs ↗
TensorX deepseek/deepseek-v4.1-flash 1.05M 384K $0.50 $1.50 $0.13 ReasoningToolsJSON Docs ↗
Inco deepseek-v4.1-flash:fast 1M 384K $0.60 $2.40 $0.01 ReasoningToolsJSON Docs ↗
Synthetic hf:deepseek-ai/DeepSeek-V4.1-Flash 524K 65.5K $0.60 $1.20 $0.03 ReasoningToolsJSON Docs ↗
Thinking Machines deepseek-ai/DeepSeek-V4.1-Flash:peft:262144 262K 262K $0.60 $3.60 $0.12 ReasoningTools Docs ↗
Tinfoil deepseek-v4-1-flash 1.05M 384K $0.65 $1.45 $0.13 ReasoningToolsJSON Docs ↗
Scaleway deepseek-v4.1-flash 256K 32.8K $0.67 $2.02 $0.13 ReasoningToolsJSON Docs ↗

Capability badges appear only where the provider catalog explicitly lists support. A blank cell means the source is silent, not that the feature is absent.

Listed rates

Price across providers

Input price per million tokens as published by each provider. Bars are drawn from listed rates only — no traffic weighting, since the catalog observes no requests.

Lowest input $0.02/M

Across 67 priced providers

Median input $0.24/M

Midpoint of listed rates

Highest input $0.67/M

33.6× the lowest listed rate

Output range $0.08 – $3.60

Per million output tokens

OpenRouter $0.02/MLowest
engy $0.03/M
engy $0.04/M
NanoGPT $0.05/M
Vercel AI Gateway $0.07/M
ZenMux $0.07/M
DevPass (LLM Gateway) $0.10/M
Standard Compute $0.14/M
OpenCode Go $0.15/M
LLM Gateway $0.15/M
Merge Gateway $0.15/M
DeepSeek $0.15/M
OpenCode Go $0.15/M
Ollama Cloud $0.15/M
ClinePass $0.15/M
302.AI $0.15/M
Neuralwatt $0.15/M
Umans AI $0.15/M
Tempr Gateway $0.15/M
Vultr $0.15/M
CommandCode $0.15/M
CoreWeave $0.15/M
AIHubMix $0.15/M
Kenari $0.16/M
above.dev $0.17/M
above.dev $0.17/M
IteraCompute $0.17/M
Deep Infra $0.20/M
Boundless $0.20/M
Cortecs $0.20/M
Arcee $0.22/M
Melious $0.23/M
Vancine $0.24/M
Vancine $0.24/M
CoralBricks $0.25/M
GreenPT $0.26/M
AKI.IO $0.28/M
Alibaba (China) $0.30/M
CrossModel $0.30/M
Kilo Gateway $0.30/M
Venice AI $0.30/M
Hugging Face $0.30/M
Fireworks AI $0.30/M
Ofox $0.30/M
Baseten $0.30/M
Together AI $0.30/M
EmpirioLabs AI $0.30/M
DigitalOcean $0.30/M
OpenCode $0.30/M
Nebius Token Factory $0.30/M
ai& $0.30/M
Novita AI $0.30/M
NEAR AI Cloud $0.30/M
Prime Inference $0.30/M
AI/ML API $0.30/M
Neon $0.30/M
Venice AI $0.30/M
Modal $0.30/M
Vivgrid $0.31/M
Charm Hyper $0.33/M
Requesty $0.50/M
TensorX $0.50/M
Inco $0.60/M
Synthetic $0.60/M
Thinking Machines $0.60/M
Tinfoil $0.65/M
Scaleway $0.67/M
Cost calculator

Estimate a workload

$0.00
Excludes taxes, non-token charges, and tiered discounts.

Context limits also differ by provider, from 256K to 1.05M tokens. Compare the provider table above before choosing on price alone.

Specification

Capabilities

Recorded from the source catalog and provider listings.

✓ Reasoning Yes
✓ Tool calling Yes
✓ Structured output Yes
✓ Attachments Yes
✓ Vision input Yes
✓ Open weights Yes
Creator
DeepSeek
Model family
deepseek-flash
Knowledge cutoff
2025-05
License
MIT
Release date
2026-09-10
Model ID
deepseek/deepseek-v4.1-flash

Weights: Hugging Face ↗

Published evaluations

Benchmarks

Every result stays attached to its source, version, metric and harness. Scores from different versions are never merged, and the profile below plots each benchmark against its own population rather than on a shared scale.

Benchmark registry
Benchmark profile
IntelligenceIntelligence Index Terminal-BenchTerminal-Bench 2.1 AutomationBenchAutomationBench This model — Intelligence Index: 24.7 index (59.9th percentile) This model — Terminal-Bench 2.1: 88 pass@1 (92.9th percentile) This model — AutomationBench: 54.8 pass@1 (90.0th percentile)

Each axis is this model's percentile among the 3 benchmarks it has published results for, measured against every other model with a score on that same benchmark. Percentiles are used because benchmarks do not share a scale — a 60 on one is not a 60 on another. Hover any point for the raw score.

Intelligence Index index Source ↗
Intelligence Index #133 of 334
Terminal-Bench — 2.1 pass@1 · Claude Code Source ↗
Terminal-Bench #1 of 7
AutomationBench pass@1 Source ↗
AutomationBench #1 of 5
Codeforces rating Source ↗
Codeforces #1 of 3
DeepSWE — 1.1 resolved · mini-swe-agent Source ↗
DeepSWE #1 of 3
GPQA Diamond pass@1 Source ↗
GPQA Diamond #1 of 3
Humanity's Last Exam pass@1 Source ↗
Humanity's Last Exam #1 of 3
MathArena Apex pass@1 Source ↗
MathArena Apex #1 of 3
NL2Repo score · DeepSeek Harness minimal mode Source ↗
NL2Repo #1 of 3
Terminal-Bench — 2.1 pass@1 · Codex Source ↗
Terminal-Bench #1 of 3
Agents' Last Exam pass@1 Source ↗
31.8 1 model scored — too few for a distribution
BabyVision pass@1 · Claude Code Source ↗
89.6 1 model scored — too few for a distribution
Chartography pass@1 · Claude Code Source ↗
78.9 1 model scored — too few for a distribution
CyberGym pass@1 Source ↗
88.1 1 model scored — too few for a distribution
DeepSWE — 1.1 resolved · Claude Code Source ↗
69.8 1 model scored — too few for a distribution
DeepSWE — 1.1 resolved · Codex Source ↗
65.6 1 model scored — too few for a distribution
DeepSWE — 1.1 resolved · DeepSeek Harness PTC mode Source ↗
67.6 1 model scored — too few for a distribution
DeepSWE — 1.1 resolved · DeepSeek Harness minimal mode Source ↗
72.6 1 model scored — too few for a distribution
DeepSWE — 1.1 resolved · DeepSeek Harness standard mode Source ↗
70.5 1 model scored — too few for a distribution
DeepSWE — 1.1 resolved · OpenCode Source ↗
65.5 1 model scored — too few for a distribution
DeepSWE — 1.1 resolved · Pi Source ↗
66.2 1 model scored — too few for a distribution
ExploitGym pass@1 Source ↗
15.3 1 model scored — too few for a distribution
ProgramBench almost@1 · DeepSeek Harness minimal mode Source ↗
20.3 1 model scored — too few for a distribution
SEC-Bench Pro pass@1 · Claude Code Source ↗
62.8 1 model scored — too few for a distribution
Terminal-Bench — 2.1 pass@1 · DeepSeek Harness PTC mode Source ↗
85.8 1 model scored — too few for a distribution
Terminal-Bench — 2.1 pass@1 · DeepSeek Harness minimal mode Source ↗
90.6 1 model scored — too few for a distribution
Terminal-Bench — 2.1 pass@1 · DeepSeek Harness standard mode Source ↗
85.8 1 model scored — too few for a distribution
Terminal-Bench — 2.1 pass@1 · OpenCode Source ↗
85.0 1 model scored — too few for a distribution
Terminal-Bench — 2.1 pass@1 · Pi Source ↗
86.1 1 model scored — too few for a distribution
Terminal-Bench — 2.1 pass@1 · mini-swe-agent Source ↗
90.3 1 model scored — too few for a distribution
Terminal-Bench — 3.0 pass@1 · DeepSeek Harness minimal mode Source ↗
30.0 1 model scored — too few for a distribution
Terminal-Bench — 4.0 pass@1 · DeepSeek Harness minimal mode Source ↗
31.2 1 model scored — too few for a distribution
ZeroBench pass@5 · Claude Code Source ↗
49.0 1 model scored — too few for a distribution

Each strip shows every published score for that benchmark, with this model marked. The lighter shape behind the ticks is the density of results, and the dashed line is the median.

Cost against capability

Price and performance

Listed input price plotted against Intelligence Index, the benchmark with the widest published coverage that this model appears in.

0 31 61 $0.01 $0.1 $1 $10 $100 Nova 2 Lite — $0.30/M, score 13.4 Nova Lite 1.0 — $0.06/M, score 6.7 Nova Micro 1.0 — $0.04/M, score 5.9 Amazon: Nova Premier 1.0 — $2.50/M, score 9.2 Nova Pro 1.0 — $0.80/M, score 7.0 Claude Fable 5 — $10.00/M, score 49.6 Anthropic: Claude Fable 5.1 — $10.00/M, score 53.4 Anthropic: Claude Fable 5.1 (batch) — $5.00/M, score 53.4 Anthropic: Claude Fable 5 (batch) — $5.00/M, score 49.6 Anthropic: Claude Haiku 4.5 — $1.00/M, score 16.9 Anthropic: Claude Haiku 4.5 (batch) — $0.50/M, score 16.9 Anthropic: Claude Haiku 5.5 — $0.10/M, score 43.4 Anthropic: Claude Haiku 5.5 (batch) — $0.05/M, score 43.4 Anthropic: Claude Opus 4.1 — $15.00/M, score 22.8 Anthropic: Claude Opus 4.1 (batch) — $7.50/M, score 22.8 Anthropic: Claude Opus 4.5 — $5.00/M, score 29.1 Anthropic: Claude Opus 4.5 (batch) — $2.50/M, score 29.1 Anthropic: Claude Opus 4.6 — $5.00/M, score 31.9 Anthropic: Claude Opus 4.6 (batch) — $2.50/M, score 31.9 Anthropic: Claude Opus 4.7 — $5.00/M, score 40.7 Anthropic: Claude Opus 4.7 (batch) — $2.50/M, score 40.7 Anthropic: Claude Opus 4.8 — $5.00/M, score 41.8 Anthropic: Claude Opus 4.8 (batch) — $2.50/M, score 41.8 Claude Opus 5 — $5.00/M, score 50.8 Anthropic: Claude Opus 5.5 — $4.00/M, score 57.6 Anthropic: Claude Opus 5.5 (batch) — $2.00/M, score 57.6 Anthropic: Claude Opus 5 (batch) — $2.50/M, score 50.8 Anthropic: Claude Sonnet 4 — $3.00/M, score 18.9 Anthropic: Claude Sonnet 4.5 — $3.00/M, score 20.7 Anthropic: Claude Sonnet 4.5 (batch) — $1.50/M, score 20.7 Anthropic: Claude Sonnet 4.6 — $3.00/M, score 30.1 Anthropic: Claude Sonnet 4.6 (batch) — $1.50/M, score 30.1 Claude Sonnet 5 — $2.00/M, score 38.2 Anthropic: Claude Sonnet 5.5 — $2.00/M, score 56.0 Anthropic: Claude Sonnet 5.5 (batch) — $1.00/M, score 56.0 Anthropic: Claude Sonnet 5 (batch) — $1.00/M, score 38.2 Trinity Large Thinking — $0.25/M, score 10.8 Command A — $2.50/M, score 13.1 DeepSeek V3 0324 — $0.29/M, score 9.7 DeepSeek V3.1 — $0.19/M, score 13.7 DeepSeek-R1 — $0.58/M, score 11.4 DeepSeek R1 0528 — $0.20/M, score 13.1 DeepSeek: DeepSeek V3.1 Terminus — $0.27/M, score 14.8 DeepSeek V3.2 — $0.21/M, score 21.5 DeepSeek: DeepSeek V3.2 Exp — $0.27/M, score 16.6 DeepSeek V4 Flash — $0.15/M, score 24.4 DeepSeek V4 Flash 0731 — $0.04/M, score 34.3 DeepSeek: DeepSeek V4 Flash 0731 (batch) — $0.11/M, score 34.3 DeepSeek V4 Flash Vision Exp — $0.15/M, score 34.8 DeepSeek V4 Pro — $0.66/M, score 30.4 DeepSeek V4 Pro 0813 — $0.13/M, score 36.0 DeepSeek: DeepSeek V4 Pro 0813 (batch) — $0.66/M, score 36.0 DeepSeek V4.1 Flash — $0.02/M, score 24.7 DeepSeek V4.1 Flash 1017 — $0.15/M, score 39.5 DeepSeek: DeepSeek V4.1 Flash (batch) — $0.05/M, score 24.7 Gemini 2.5 Flash — $0.30/M, score 15.5 Gemini 2.5 Flash-Lite — $0.10/M, score 10.4 Google: Gemini 2.5 Flash Lite (batch) — $0.05/M, score 10.4 Google: Gemini 2.5 Flash (batch) — $0.15/M, score 15.5 Gemini 2.5 Pro — $1.25/M, score 16.1 Google: Gemini 2.5 Pro (batch) — $0.62/M, score 16.1 Gemini 3 Flash Preview — $0.50/M, score 26.3 Google: Gemini 3 Flash Preview (batch) — $0.25/M, score 26.3 Gemini 3.1 Flash Lite Preview — $0.25/M, score 15.6 Gemini 3.1 Pro Preview — $2.00/M, score 29.7 Google: Gemini 3.1 Pro Preview (batch) — $1.00/M, score 29.7 Gemini 3.5 Flash — $1.50/M, score 33.6 Gemini 3.5 Flash Lite — $0.30/M, score 22.2 Google: Gemini 3.5 Flash Lite (batch) — $0.15/M, score 22.2 Google: Gemini 3.5 Flash (batch) — $0.75/M, score 33.6 Gemini 3.6 Flash — $0.75/M, score 34.0 Google: Gemini 3.6 Flash (batch) — $0.38/M, score 34.0 Gemini 3.7 Flash — $0.75/M, score 39.6 Google: Gemini 3.7 Flash (batch) — $0.38/M, score 39.6 Gemini 3.8 Flash — $0.75/M, score 40.9 Google: Gemini 3.8 Flash (batch) — $0.38/M, score 40.9 Gemini 4 Argon — $2.00/M, score 52.6 Google: Gemini 4 Argon (batch) — $1.00/M, score 52.6 Gemma 3 12B IT — $0.04/M, score 3.8 Gemma 3 27B IT — $0.08/M, score 4.9 Gemma 3 4B IT — $0.04/M, score 4.8 Gemma 4 26B A4B IT — $0.04/M, score 16.7 Gemma 4 31B IT — $0.10/M, score 14.7 Google: Gemma 4 31B (batch) — $0.39/M, score 15.4 IBM: Granite 4.0 Micro — $0.02/M, score 5.1 IBM: Granite 4.2 8B — $0.06/M, score 11.1 Mercury 2 — $0.25/M, score 10.8 Mercury 2.5 — $0.20/M, score 12.3 inclusionAI: Ling-2.6-flash — $0.01/M, score 14.2 Ling 3.0 Flash — $0.02/M, score 20.1 Ling 3.0 Flash Fin — $0.07/M, score 22.6 Ling 3.0 Flash VL — $0.06/M, score 24.6 Ling 3.1 Flash — $0.07/M, score 41.1 inclusionAI: Ring-2.6-1T — $0.07/M, score 31.1 Kwaipilot: KAT-Coder-Pro V2 — $0.30/M, score 33.7 LongCat-2.0 — $0.30/M, score 19.1 Meta: Llama 3.1 70B Instruct — $0.40/M, score 6.6 Meta: Llama 3.1 8B Instruct — $0.05/M, score 6.9 Meta: Llama 3.2 1B Instruct — $0.03/M, score 4.8 Meta: Llama 3.2 3B Instruct — $0.05/M, score 5.7 Meta: Llama 3.3 70B Instruct — $0.10/M, score 7.7 Meta: Llama 4 Maverick — $0.19/M, score 9.3 Meta: Llama 4 Scout — $0.10/M, score 6.5 Muse Glimmer 30B — $0.20/M, score 17.5 Muse Spark 1.1 — $1.25/M, score 33.7 Muse Spark 1.2 — $1.25/M, score 39.6 Muse Spark 1.3 — $1.25/M, score 48.1 Microsoft: Phi 4 — $0.07/M, score 5.9 MiniMax: MiniMax M1 — $0.55/M, score 11.7 MiniMax: MiniMax M2 — $0.26/M, score 18.6 MiniMax: MiniMax M2.1 — $0.30/M, score 20.9 MiniMax: MiniMax M2.5 — $0.30/M, score 22.8 MiniMax: MiniMax M2.7 — $0.30/M, score 22.8 MiniMax: MiniMax M3 — $0.30/M, score 29.2 MiniMax: MiniMax M3.1 Flash — $0.15/M, score 42.7 MiniMax: MiniMax M3 (batch) — $0.30/M, score 29.2 Mistral: Devstral 2 2512 — $0.40/M, score 8.6 Mistral: Ministral 3 14B 2512 — $0.20/M, score 6.0 Mistral: Ministral 3 3B 2512 — $0.10/M, score 4.8 Mistral: Ministral 3 8B 2512 — $0.15/M, score 5.5 Mistral: Ministral 3 8B 2512 (batch) — $0.07/M, score 5.5 Mistral Large — $2.00/M, score 5.8 Mistral Large 2407 — $2.00/M, score 7.6 Mistral: Mistral Large 3 2512 — $0.50/M, score 9.3 Mistral: Mistral Large 3 2512 (batch) — $0.25/M, score 9.3 Mistral: Mistral Large 4 — $1.36/M, score 38.4 Mistral: Mistral Medium 3 — $0.40/M, score 9.0 Mistral: Mistral Medium 3.5 — $1.50/M, score 14.2 Mistral: Mistral Medium 3.5 (batch) — $0.75/M, score 14.2 Mistral: Mistral Medium 3.1 — $0.40/M, score 9.2 Mistral: Mistral Medium 3.1 (batch) — $0.20/M, score 9.2 Mistral: Saba — $0.20/M, score 6.5 Mistral: Mistral Small 3 — $0.05/M, score 6.7 Mistral: Mistral Small 4 — $0.15/M, score 11.3 Mistral: Mistral Small 4 (batch) — $0.07/M, score 11.3 Mistral: Mixtral 8x22B Instruct — $2.00/M, score 5.7 Kimi K2 0711 — $0.40/M, score 12.7 Kimi K2 Instruct 0905 — $0.60/M, score 15.3 Kimi K2 Thinking — $0.40/M, score 22.0 Kimi K2.5 — $0.38/M, score 23.5 Kimi K2.6 — $0.95/M, score 27.0 Kimi K2.7 Code — $0.95/M, score 25.8 MoonshotAI: Kimi K2.7 Code (batch) — $0.47/M, score 43.0 Kimi K3 — $3.00/M, score 43.6 Kimi K3.1 Pro — $2.00/M, score 55.1 MoonshotAI: Kimi K3 (batch) — $2.28/M, score 43.6 Nex-N2-Pro — $0.50/M, score 41.7 Hermes 3 405B Instruct — $1.00/M, score 7.4 Hermes 3 70B Instruct — $0.70/M, score 6.7 Hermes 4 405B — $1.00/M, score 7.5 Nemotron 3 Nano 30B A3B — $0.05/M, score 8.9 Nemotron 3 Super 120B A12B — $0.05/M, score 12.8 Nemotron 3 Ultra 550B A55B — $0.10/M, score 22.9 NVIDIA: Nemotron 3 Ultra (batch) — $0.60/M, score 38.3 Nemotron 3.5 Lightning 30B A3B — $0.03/M, score 12.9 NVIDIA: Nemotron 3.5 Super VL — $0.15/M, score 26.5 GPT-3.5-turbo — $0.50/M, score 5.5 OpenAI: GPT-3.5 Turbo (batch) — $0.25/M, score 5.5 GPT-4 — $30.00/M, score 6.7 GPT-4 Turbo — $10.00/M, score 7.0 OpenAI: GPT-4 Turbo (batch) — $5.00/M, score 7.0 GPT-4.1 — $2.00/M, score 12.7 GPT-4.1 mini — $0.40/M, score 10.2 OpenAI: GPT-4.1 Mini (batch) — $0.20/M, score 10.2 GPT-4.1 nano — $0.10/M, score 7.8 OpenAI: GPT-4.1 Nano (batch) — $0.05/M, score 7.8 OpenAI: GPT-4.1 (batch) — $1.00/M, score 12.7 GPT-4o (2024-05-13) — $5.00/M, score 7.3 GPT-4o (2024-08-06) — $2.50/M, score 7.7 GPT-4o (2024-11-20) — $2.50/M, score 8.4 GPT-4o mini — $0.15/M, score 6.7 OpenAI: GPT-4o-mini (batch) — $0.07/M, score 6.7 GPT-5 — $1.25/M, score 23.0 GPT-5 Mini — $0.25/M, score 20.6 OpenAI: GPT-5 Mini (batch) — $0.12/M, score 20.6 GPT-5 Nano — $0.05/M, score 13.0 OpenAI: GPT-5 Nano (batch) — $0.02/M, score 13.0 GPT-5.1 — $1.25/M, score 24.7 GPT-5.1 Codex — $1.07/M, score 23.7 GPT-5.1 Codex mini — $0.22/M, score 20.4 OpenAI: GPT-5.1 (batch) — $0.62/M, score 24.7 GPT-5.2 — $1.75/M, score 30.4 GPT-5.2 Codex — $0.14/M, score 28.5 OpenAI: GPT-5.2 (batch) — $0.88/M, score 30.4 GPT-5.3 Codex — $1.75/M, score 32.5 GPT-5.4 — $2.50/M, score 39.0 GPT-5.4 mini — $0.75/M, score 24.1 OpenAI: GPT-5.4 Mini (batch) — $0.38/M, score 24.1 GPT-5.4 nano — $0.20/M, score 20.7 OpenAI: GPT-5.4 Nano (batch) — $0.10/M, score 20.7 OpenAI: GPT-5.4 (batch) — $1.25/M, score 39.0 GPT-5.5 — $5.00/M, score 38.4 OpenAI: GPT-5.5 (batch) — $2.50/M, score 38.4 GPT-5.6 Luna — $0.20/M, score 37.3 OpenAI: GPT-5.6 Luna (batch) — $0.10/M, score 37.3 GPT-5.6 Sol — $4.00/M, score 47.0 OpenAI: GPT-5.6 Sol (batch) — $2.00/M, score 47.0 GPT-5.6 Terra — $2.00/M, score 42.1 OpenAI: GPT-5.6 Terra (batch) — $1.00/M, score 42.1 OpenAI: GPT-5 (batch) — $0.62/M, score 23.0 GPT-6 Astra — $10.00/M, score 52.7 OpenAI: GPT-6 Astra (batch) — $5.00/M, score 52.7 GPT-6 Luna — $0.10/M, score 38.1 OpenAI: GPT-6 Luna (batch) — $0.05/M, score 38.1 GPT-6 Sol — $2.00/M, score 47.6 OpenAI: GPT-6 Sol (batch) — $1.00/M, score 47.6 GPT-6.1 Sol — $2.00/M, score 51.8 OpenAI: GPT-6.1 Sol (batch) — $1.00/M, score 51.8 GPT OSS 120B — $0.03/M, score 11.6 OpenAI: gpt-oss-120b (batch) — $0.03/M, score 11.6 GPT OSS 20B — $0.02/M, score 10.0 OpenAI: gpt-oss-20b (batch) — $0.02/M, score 10.0 o1 — $15.00/M, score 15.2 o1-pro — $150.00/M, score 12.4 o3 — $2.00/M, score 20.2 o3-mini — $1.10/M, score 12.5 OpenAI: o3 Mini High — $1.10/M, score 11.0 OpenAI: o3 Mini High (batch) — $0.55/M, score 15.7 OpenAI: o3 Mini (batch) — $0.55/M, score 12.5 o3-pro — $20.00/M, score 21.9 OpenAI: o3 (batch) — $1.00/M, score 20.2 o4-mini — $1.10/M, score 16.7 OpenAI: o4 Mini (batch) — $0.55/M, score 16.7 Sonar — $1.00/M, score 7.7 Sonar Pro — $3.00/M, score 7.6 Sonar Reasoning Pro — $2.00/M, score 11.8 Qwen2.5 72B Instruct — $0.36/M, score 7.7 Qwen2.5 Coder 32B Instruct — $0.66/M, score 6.7 Qwen: Qwen3 14B — $0.12/M, score 6.7 Qwen: Qwen3 235B A22B — $0.45/M, score 9.5 Qwen: Qwen3 235B A22B Instruct 2507 — $0.09/M, score 12.0 Qwen: Qwen3 235B A22B Thinking 2507 — $0.45/M, score 12.7 Qwen: Qwen3 30B A3B — $0.12/M, score 7.6 Qwen: Qwen3 30B A3B Instruct 2507 — $0.09/M, score 7.5 Qwen: Qwen3 30B A3B Thinking 2507 — $0.20/M, score 9.8 Qwen: Qwen3 32B — $0.08/M, score 7.3 Qwen: Qwen3 8B — $0.12/M, score 7.3 Qwen: Qwen3 Coder 480B A35B — $0.30/M, score 11.9 Qwen: Qwen3 Coder 30B A3B Instruct — $0.07/M, score 9.6 Qwen: Qwen3 Coder Next — $0.12/M, score 9.2 Qwen: Qwen3 Max — $0.78/M, score 15.6 Qwen: Qwen3 Max Thinking — $0.78/M, score 21.3 Qwen: Qwen3 Next 80B A3B Instruct — $0.09/M, score 9.6 Qwen: Qwen3 Next 80B A3B Thinking — $0.15/M, score 11.2 Qwen: Qwen3 VL 235B A22B Instruct — $0.21/M, score 9.9 Qwen: Qwen3 VL 235B A22B Thinking — $0.40/M, score 13.4 Qwen: Qwen3 VL 30B A3B Instruct — $0.15/M, score 7.9 Qwen: Qwen3 VL 30B A3B Thinking — $0.29/M, score 9.5 Qwen: Qwen3 VL 32B Instruct — $0.10/M, score 11.9 Qwen: Qwen3 VL 8B Instruct — $0.25/M, score 7.3 Qwen: Qwen3 VL 8B Thinking — $0.18/M, score 8.2 Qwen: Qwen3.5-122B-A10B — $0.40/M, score 17.7 Qwen: Qwen3.5-27B — $0.27/M, score 22.9 Qwen: Qwen3.5-35B-A3B — $0.14/M, score 19.3 Qwen: Qwen3.5 397B A17B — $0.50/M, score 21.4 Qwen: Qwen3.5-9B — $0.17/M, score 13.3 Qwen: Qwen3.5-9B (batch) — $0.17/M, score 21.8 Qwen: Qwen3.6 27B — $0.25/M, score 21.4 Qwen: Qwen3.6 35B A3B — $0.10/M, score 18.2 Qwen: Qwen3.6 Max Preview — $1.03/M, score 28.4 Qwen: Qwen3.6 Plus — $0.33/M, score 27.0 Qwen: Qwen3.7 Max — $1.48/M, score 29.5 Qwen: Qwen3.7 Plus — $0.32/M, score 25.2 Qwen: Qwen3.7 Plus (batch) — $0.23/M, score 25.2 Qwen: Qwen3.8 2.4T A95B — $2.00/M, score 39.9 Qwen: Qwen3.8 2.4T A95B (batch) — $2.00/M, score 39.9 Qwen: Qwen3.8 27B — $0.20/M, score 33.7 Qwen: Qwen3.8 Max — $2.00/M, score 53.4 Qwen: Qwen3.8 Max (0902) — $2.00/M, score 45.4 Reka Flash 3 — $0.10/M, score 6.4 Step 3.5 Flash — $0.10/M, score 17.0 Step 3.7 Flash — $0.20/M, score 19.5 Step 5 Preview — $1.05/M, score 43.7 Hy3 preview — $0.18/M, score 25.3 Inkling — $1.87/M, score 25.0 Inkling Small — $0.30/M, score 25.7 Thinking Machines: Inkling Small (batch) — $0.50/M, score 26.1 Thinking Machines: Inkling (batch) — $1.00/M, score 25.0 Solar Mini 4 — $0.10/M, score 24.1 Upstage: Solar Pro 3 — $0.15/M, score 7.8 Solar Pro 4 — $0.30/M, score 28.2 SpaceXAI: Grok 4.20 — $1.25/M, score 25.7 SpaceXAI: Grok 4.3 — $1.25/M, score 24.9 SpaceXAI: Grok 4.3 (batch) — $1.00/M, score 24.9 SpaceXAI: Grok 4.5 — $2.00/M, score 38.8 SpaceXAI: Grok 4.6 — $2.00/M, score 44.3 SpaceXAI: Grok 4.7 — $2.00/M, score 46.4 SpaceXAI: Grok Build 0.1 — $1.00/M, score 27.2 MiMo-V2.5 — $0.14/M, score 21.8 MiMo-V2.5-Pro — $0.43/M, score 26.0 MiMo-V2.6-Flash — $0.14/M, score 37.9 MiMo-V2.6-Pro — $0.43/M, score 46.3 Z.ai: GLM 4.5 — $0.60/M, score 12.8 Z.ai: GLM 4.5 Air — $0.13/M, score 11.1 Z.ai: GLM 4.5V — $0.60/M, score 7.6 Z.ai: GLM 4.6 — $0.55/M, score 18.5 Z.ai: GLM 4.6V — $0.30/M, score 11.2 Z.ai: GLM 4.7 — $0.54/M, score 22.2 Z.ai: GLM 4.7 Flash — $0.06/M, score 14.9 Z.ai: GLM 5 — $1.00/M, score 27.9 Z.ai: GLM 5 Turbo — $1.20/M, score 26.6 Z.ai: GLM 5.1 — $1.40/M, score 26.1 Z.ai: GLM 5.2 — $0.03/M, score 33.7 Z.ai: GLM 5.2 (batch) — $0.70/M, score 33.7 Z.ai: GLM 5.3 — $0.08/M, score 44.8 Z.ai: GLM 5.3 Flash — $0.15/M, score 41.8 Z.ai: GLM 5.3 Flash (batch) — $0.05/M, score 41.8 Z.ai: GLM 5.3 (batch) — $0.45/M, score 44.8 Z.ai: GLM 5V Turbo — $1.20/M, score 23.5 DeepSeek V4.1 Flash Input price per million tokens (log scale) Index

The stepped line is the efficient frontier: at each price, the best score available for that money or less. A model sitting on it is not being beaten by anything cheaper. Price is log-scaled because listed rates span four orders of magnitude. Only models with both a listed price and a score on this benchmark can appear.

Catalog activity

Change log

Field-level changes detected between successful source imports.

Full change log
Max Output Tokens943718 → 384000
Context Length1048576 → 1000000
Max Output Tokens384000 → 943718
Context Length1000000 → 1048576
Max Output Tokens943718 → 384000
Context Length1048576 → 1000000
Max Output Tokens384000 → 943718
Context Length1000000 → 1048576
Max Output Tokens943718 → 384000
Context Length1048576 → 1000000
Provenance

Sources & verification

Every figure on this page traces back to one of these records.

Methodology
Last verified
Oct 24, 2026
Status
Source-linked
Confidence
Medium
Catalog source
Models.dev
Models.devcatalog ↗NaN documentationprovider documentation ↗AMD documentationprovider documentation ↗Alibaba Token Plan (China) documentationprovider documentation ↗Alibaba Token Plan documentationprovider documentation ↗SCNet Token Plan documentationprovider documentation ↗Umans AI Coding Plan documentationprovider documentation ↗Nvidia documentationprovider documentation ↗SenseNova (China) documentationprovider documentation ↗OpenRouter documentationprovider documentation ↗engy documentationprovider documentation ↗NanoGPT documentationprovider documentation ↗
Public API

Use this record

Fetch the complete source-linked model record. No key, no account, no rate-limited tier.

API documentation
Endpoint
GET https://modelbench.lol/api/v1/models/deepseek/deepseek-v4.1-flash
curl
curl "https://modelbench.lol/api/v1/models/deepseek/deepseek-v4.1-flash"
Common questions

Frequently asked questions

Answered directly from the stored record — nothing here is generated beyond the catalog's own fields.

What is DeepSeek V4.1 Flash?

DeepSeek V4.1 Flash model for reasoning and agentic coding. It is published by DeepSeek and catalogued here from Models.dev.

How much does DeepSeek V4.1 Flash cost?

Listed input pricing starts at $0.02 per million tokens from OpenRouter, rising to $0.67 across 67 listed providers.

What is the context length of DeepSeek V4.1 Flash?

DeepSeek V4.1 Flash accepts up to 1M tokens of context and returns up to 384K output tokens.

Does DeepSeek V4.1 Flash support tool calling and structured output?

Provider catalogs list support for tool calling, structured output, reasoning, and image input.

Which providers serve DeepSeek V4.1 Flash?

70 providers list this model: NaN, AMD, Alibaba Token Plan (China), Alibaba Token Plan, SCNet Token Plan, Umans AI Coding Plan and 64 more.

Are the weights for DeepSeek V4.1 Flash open?

Yes. The weights are published and downloadable from Hugging Face under the MIT license.

When was DeepSeek V4.1 Flash released?

The catalog records a release date of 2026-09-10, last verified Oct 24, 2026.

More models from DeepSeek

View all →
DeepSeek V4 Pro

Open MoE flagship with million-token context for coding and long agent runs

1M ctx $0.66/M in DeepSeek V4 Flash

Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work

1M ctx $0.15/M in DeepSeek V3.2

Hybrid-reasoning DeepSeek model with thinking and non-thinking modes, sparse attention, and tool-use

128K ctx $0.21/M in DeepSeek: DeepSeek V3.2 Exp

DeepSeek-V3.2-Exp is an experimental large language model released by DeepSeek as an intermediate step between V3.1 and future architectures. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...

164K ctx $0.27/M in