ModelBench
DeepSeek logo
Models/DeepSeek

DeepSeek: DeepSeek V4 Flash 0731

Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding

Source-linked deepseek-flash Open weights MIT Released 2026-07-31
API record Report
InputT
OutputT
Input price$0.05/M
Output price$0.16/M
Context1M
Max output384K
Providers54
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 Flash 0731
ProviderProvider model IDContextMax outputInputOutputCache readCapabilitiesDocs
Alibaba Token Plan deepseek-v4-flash-0731 1M 384K — — — ReasoningToolsJSON Docs ↗
SCNet Token Plan DeepSeek-V4-Flash-0731 1M 384K — — — ReasoningToolsJSON Docs ↗
Hetzner DeepSeek-V4-Flash-0731 512K 384K — — — ReasoningToolsJSON Docs ↗
Alibaba Token Plan (China) deepseek-v4-flash-0731 1M 384K — — — ReasoningToolsJSON Docs ↗
Ollama Cloud deepseek-v4-flash:0731 1.04858M 1.04858M — — — ReasoningToolsJSON Docs ↗
Nvidia deepseek-ai/deepseek-v4-flash-0731 1M 384K — — — ReasoningToolsJSON Docs ↗
Eden AI flexai/deepseek-v4-flash-0731 786.432K 384K $0.03 $0.1 — Reasoning Docs ↗
NanoGPT deepseek/deepseek-v4-flash-0731 1M 131.072K $0.05 $0.16 $0.013 ReasoningToolsJSON Docs ↗
Eden AI deepinfra/deepseek-ai/DeepSeek-V4-Flash-0731 1.04858M 384K $0.06 $0.18 $0.015 ReasoningToolsJSON Docs ↗
Deep Infra deepseek-ai/DeepSeek-V4-Flash-0731 1.04858M 384K $0.06 $0.18 $0.015 ReasoningToolsJSON Docs ↗
OpenRouter deepseek/deepseek-v4-flash-0731 1.31072M 943.718K $0.065 $0.18 $0.016 ReasoningToolsJSON Docs ↗
Vercel AI Gateway deepseek/deepseek-v4-flash-0731 1M 384K $0.076 $0.153 $0.014 ReasoningToolsJSON Docs ↗
DigitalOcean deepseek-v4-flash-0731 1.04858M 1.04858M $0.08 $0.252 $0.025 ReasoningToolsJSON Docs ↗
Eden AI flexai/DeepSeek-V4-Flash-0731 1M 384K $0.08 $0.18 — Reasoning Docs ↗
Ambient deepseek/deepseek-v4-flash-0731 1.04858M 1.04858M $0.08 $0.18 $0.016 ReasoningToolsJSON Docs ↗
Bothub deepseek-v4-flash-0731 1M 384K $0.1 $0.28 — ReasoningToolsJSON Docs ↗
Cortecs deepseek-v4-flash-0731 1.04858M 1.04858M $0.13 $0.28 $0.03 ReasoningTools Docs ↗
Perplexity Agent deepseek/deepseek-v4-flash-0731 1M 384K $0.13 $0.26 $0.028 ReasoningToolsJSON Docs ↗
RunInfra deepseek-ai/DeepSeek-V4-Flash-0731 1.04858M 32.768K $0.13 $0.27 $0.01 ReasoningToolsJSON Docs ↗
Inceptron deepseek-ai/DeepSeek-V4-Flash-0731 1.04858M 1.04858M $0.13 $0.28 $0.03 ReasoningToolsJSON Docs ↗
Baseten deepseek-ai/DeepSeek-V4-Flash-0731 1.04858M 384K $0.13 $0.26 $0.028 ReasoningToolsJSON Docs ↗
OpenReason deepseek-ai/deepseek-v4-flash-0731 1M 384K $0.137 $0.274 — ReasoningToolsJSON Docs ↗
Nebius Token Factory deepseek-ai/DeepSeek-V4-Flash-0731 1.024M 1.024M $0.14 $0.28 $0.14 ReasoningToolsJSON Docs ↗
Eden AI together_ai/deepseek-ai/DeepSeek-V4-Flash-0731 1.04858M 384K $0.14 $0.28 $0.03 ReasoningToolsJSON Docs ↗
Eden AI nebius/deepseek-ai/DeepSeek-V4-Flash-0731 1.024M 384K $0.14 $0.28 $0.14 ReasoningToolsJSON Docs ↗
Hugging Face deepseek-ai/DeepSeek-V4-Flash-0731 1.04858M 384K $0.14 $0.28 — ReasoningToolsJSON Docs ↗
Eden AI databricks/databricks-deepseek-v4-flash-0731 1M 384K $0.14 $0.28 $0.028 ReasoningTools Docs ↗
AMD DeepSeek-V4-Flash 1M 384K $0.14 $0.28 $0.003 ReasoningToolsJSON Docs ↗
OpenCode Zen deepseek-v4-flash 1M 384K $0.14 $0.28 $0.028 ReasoningToolsJSON Docs ↗
Together AI deepseek-ai/DeepSeek-V4-Flash-0731 1M 384K $0.14 $0.28 $0.03 ReasoningToolsJSON Docs ↗
AIHubMix deepseek-v4-flash-0731 1M 384K $0.142 $0.284 $0.028 ReasoningToolsJSON Docs ↗
OrcaRouter deepseek/deepseek-v4-flash-0731 1M 384K $0.147 $0.295 $0.02 ReasoningToolsJSON Docs ↗
GreenPT deepseek-v4-flash-0731 1M 384K $0.16 $0.399 $0.046 ReasoningToolsJSON Docs ↗
Venice AI deepseek-v4-flash-0731 1M 32.768K $0.175 $0.35 $0.035 ReasoningToolsJSON Docs ↗
Eden AI qwen/deepseek-v4-flash-0731 1M 384K $0.176 $0.528 — ReasoningToolsJSON Docs ↗
AKI.IO deepseek-v4-flash-0731-284b 1.04858M 81.92K $0.2 $0.5 $0.1 ReasoningToolsJSON Docs ↗
Alibaba deepseek-v4-flash-0731 1M 384K $0.2 $0.4 $0.04 ReasoningToolsJSON Docs ↗
Fireworks AI accounts/fireworks/models/deepseek-v4-flash-0731 1M 384K $0.22 $0.66 $0.007 ReasoningToolsJSON Docs ↗
Merge Gateway deepseek/deepseek-v4-flash-0731 1M 384K $0.22 $0.66 $0.007 ReasoningToolsJSON Docs ↗
Eden AI fireworks_ai/accounts/fireworks/models/deepseek-v4-flash-0731 1.04858M 384K $0.22 $0.66 $0.007 ReasoningToolsJSON Docs ↗
Eden AI tensorx/deepseek/deepseek-v4-flash-0731 1.04858M 384K $0.25 $0.3 $0.062 ReasoningTools Docs ↗
TensorX deepseek/deepseek-v4-flash-0731 1.04858M 384K $0.25 $0.3 $0.06 ReasoningToolsJSON Docs ↗
Requesty deepseek-v4-flash-0731 1.04858M 131.072K $0.28 $0.56 $0.07 ReasoningToolsJSON Docs ↗
Merge Gateway deepseek/deepseek-v4-flash-0731-fast 1M 384K $0.28 $0.56 $0.07 Reasoning Docs ↗
Tinfoil deepseek-v4-flash 1.04858M 384K $0.3 $0.7 $0.06 ReasoningToolsJSON Docs ↗
EmpirioLabs AI deepseek-v4-flash-0731 1M 393.216K $0.424 $1.272 $0.424 ReasoningToolsJSON Docs ↗
Cloudflare Workers AI @cf/deepseek-ai/deepseek-v4-flash-0731 1.31072M 1.04858M $0.44 $1.32 $0.014 ReasoningToolsJSON Docs ↗
Kilo Gateway deepseek/deepseek-v4-flash-0731 1.04858M 943.718K $0.44 $1.32 $0.028 ReasoningToolsJSON Docs ↗
Charm Hyper deepseek-v4-flash-0731 1M 384K $0.44 $1.32 $0.044 ReasoningToolsJSON Docs ↗
Eden AI cloudflare/@cf/deepseek-ai/deepseek-v4-flash-0731 1.31072M 384K $0.44 $1.32 $0.014 ReasoningToolsJSON Docs ↗
Ofox deepseek/deepseek-v4-flash-0731 1M 384K $0.44 $1.32 $0.014 ReasoningToolsJSON Docs ↗
Volcengine Ark deepseek-v4-flash-ga-260731 1M 384K $0.445 $1.336 $0.015 ReasoningToolsJSON Docs ↗
Eden AI scaleway/deepseek-v4-flash-0731 256K 384K $0.465 $0.93 — ReasoningTools Docs ↗
Scaleway deepseek-v4-flash-0731 256K 16.384K $0.468 $0.936 $0.094 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 $0.03/M

Across 48 priced providers

Median input $0.141/M

Midpoint of listed rates

Highest input $0.468/M

15.6× the lowest listed rate

Output range $0.1 – $1.336

Per million output tokens

Eden AI $0.03/MLowest
NanoGPT $0.05/M
Eden AI $0.06/M
Deep Infra $0.06/M
OpenRouter $0.065/M
Vercel AI Gateway $0.076/M
DigitalOcean $0.08/M
Eden AI $0.08/M
Ambient $0.08/M
Bothub $0.1/M
Cortecs $0.13/M
Perplexity Agent $0.13/M
RunInfra $0.13/M
Inceptron $0.13/M
Baseten $0.13/M
OpenReason $0.137/M
Nebius Token Factory $0.14/M
Eden AI $0.14/M
Eden AI $0.14/M
Hugging Face $0.14/M
Eden AI $0.14/M
AMD $0.14/M
OpenCode Zen $0.14/M
Together AI $0.14/M
AIHubMix $0.142/M
OrcaRouter $0.147/M
GreenPT $0.16/M
Venice AI $0.175/M
Eden AI $0.176/M
AKI.IO $0.2/M
Alibaba $0.2/M
Fireworks AI $0.22/M
Merge Gateway $0.22/M
Eden AI $0.22/M
Eden AI $0.25/M
TensorX $0.25/M
Requesty $0.28/M
Merge Gateway $0.28/M
Tinfoil $0.3/M
EmpirioLabs AI $0.424/M
Cloudflare Workers AI $0.44/M
Kilo Gateway $0.44/M
Charm Hyper $0.44/M
Eden AI $0.44/M
Ofox $0.44/M
Volcengine Ark $0.445/M
Eden AI $0.465/M
Scaleway $0.468/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 1.31072M 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 No
× Vision input No
✓ Open weights Yes
Creator
DeepSeek
Model family
deepseek-flash
Knowledge cutoff
2025-05
License
MIT
Release date
2026-07-31
Model ID
deepseek/deepseek-v4-flash-0731

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
Coding IndexCoding Index Agentic IndexAgentic Index IntelligenceIntelligence Index Design Arena: w…Design Arena: website Design Arena: c…Design Arena: codecategories Design Arena: g…Design Arena: gamedev Design Arena: d…Design Arena: dataviz Design Arena: u…Design Arena: uicomponent This model — Coding Index: 69.1 index (77.5th percentile) This model — Agentic Index: 41.7 index (80.7th percentile) This model — Intelligence Index: 34.5 index (66.8th percentile) This model — Design Arena: website: 1251 elo (64.0th percentile) This model — Design Arena: codecategories: 1245 elo (61.1th percentile) This model — Design Arena: gamedev: 1234 elo (62.3th percentile) This model — Design Arena: dataviz: 1197 elo (48.2th percentile) This model — Design Arena: uicomponent: 1251 elo (61.8th percentile)

Each axis is this model's percentile among the 8 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.

Coding Index index Source ↗
Coding Index #46 of 204
Agentic Index index Source ↗
Agentic Index #37 of 192
Intelligence Index index Source ↗
Intelligence Index #63 of 191
Design Arena: website elo Source ↗
Design Arena: website #63 of 175
Design Arena: codecategories elo Source ↗
Design Arena: codecategories #65 of 167
Design Arena: gamedev elo Source ↗
Design Arena: gamedev #62 of 166
Design Arena: dataviz elo Source ↗
Design Arena: dataviz #85 of 165
Design Arena: uicomponent elo Source ↗
Design Arena: uicomponent #61 of 161
Design Arena: 3d elo Source ↗
Design Arena: 3d #60 of 157
Design Arena: svg elo Source ↗
Design Arena: svg #40 of 116
Design Arena: asciiart elo Source ↗
Design Arena: asciiart #87 of 99
AutomationBench success rate · 2026-07-31 Source ↗
AutomationBench #4 of 5
Agents' Last Exam score · DeepSeek Harness minimal mode · 2026-07-31 Source ↗
25.2 1 model scored — too few for a distribution
CyberGym score · DeepSeek Harness minimal mode · 2026-07-31 Source ↗
76.7 1 model scored — too few for a distribution
DSBench-FullStack score · 2026-07-31 Source ↗
68.7 1 model scored — too few for a distribution
DSBench-Hard score · 2026-07-31 Source ↗
59.6 1 model scored — too few for a distribution
DeepSWE resolve rate · DeepSeek Harness minimal mode · 2026-07-31 Source ↗
54.4 1 model scored — too few for a distribution
NL2Repo resolve rate · DeepSeek Harness minimal mode · 2026-07-31 Source ↗
54.2 1 model scored — too few for a distribution
Terminal-Bench — 2.1 pass@1 Source ↗
82.7 1 model scored — too few for a distribution
Toolathlon-Verified score · DeepSeek Harness minimal mode · 2026-07-31 Source ↗
70.3 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 Coding Index, the benchmark with the widest published coverage that this model appears in.

0 43 86 $0.01 $0.1 $1 $10 Anthropic: Claude Fable 5.1 (batch) — $5/M, score 81.6 Claude Opus 5 — $5/M, score 78.0 Mistral: Ministral 3 8B 2512 (batch) — $0.075/M, score 9.7 GPT-3.5-turbo — $0.5/M, score 10.7 Anthropic: Claude Opus 4.7 — $5/M, score 73.6 OpenAI: GPT-5.4 Nano (batch) — $0.1/M, score 56.1 Inception: Mercury 2 — $0.25/M, score 31.1 Gemini 3.1 Flash Lite Preview — $0.25/M, score 34.7 Gemini 3.5 Flash Lite — $0.3/M, score 49.3 Gemma 3 12B IT — $0.05/M, score 5.8 Mistral: Mistral Large 3 2512 (batch) — $0.25/M, score 20.1 OpenAI: GPT-3.5 Turbo (batch) — $0.25/M, score 10.7 Anthropic: Claude Sonnet 4.5 — $3/M, score 52.1 OpenAI: o3 Mini High (batch) — $0.55/M, score 16.3 Qwen: Qwen3.8 Max (0902) — $2/M, score 71.8 Gemini 3.5 Flash — $1.5/M, score 70.1 Z.ai: GLM 5.3 Flash (batch) — $0.075/M, score 71.5 DeepSeek V4 Flash — $0.15/M, score 52.0 DeepSeek-R1 — $0.7/M, score 24.6 DeepSeek V4 Pro — $0.435/M, score 59.4 GPT-4 Turbo — $10/M, score 21.5 GPT-5.6 Luna — $0.2/M, score 71.4 GPT-4.1 mini — $0.4/M, score 20.2 GPT OSS 120B — $0.03/M, score 30.4 GPT-5 — $1.25/M, score 37.8 Claude Sonnet 5 — $2/M, score 71.5 Mistral: Ministral 3 8B 2512 — $0.15/M, score 9.7 Z.ai: GLM 5.3 (batch) — $0.7/M, score 74.8 OpenAI: o1 (batch) — $7.5/M, score 39.7 Z.ai: GLM 5.1 — $0.966/M, score 55.8 Gemini 3.7 Flash — $0.75/M, score 76.1 Z.ai: GLM 5.3 — $1.4/M, score 74.8 Google: Gemini 3.1 Pro Preview (batch) — $1/M, score 68.8 LongCat-2.0 — $0.3/M, score 45.3 Google: Gemini 2.5 Pro (batch) — $0.625/M, score 33.3 OpenAI: GPT-5.5 (batch) — $2.5/M, score 74.9 GPT-6 Astra — $10/M, score 76.9 Gemini 3.6 Flash — $0.75/M, score 69.2 Qwen: Qwen3.5-9B (batch) — $0.17/M, score 28.7 GPT-5.4 mini — $0.75/M, score 56.1 Gemma 4 26B A4B IT — $0.042/M, score 39.3 Claude Fable 5 — $10/M, score 76.5 Mistral: Mistral Small 4 (batch) — $0.075/M, score 26.6 Z.ai: GLM 5.3 Flash — $0.15/M, score 71.5 MiniMax: MiniMax M3 — $0.3/M, score 58.6 DeepSeek: DeepSeek V4 Pro 0813 (batch) — $0.66/M, score 68.8 Thinking Machines: Inkling Small (batch) — $0.5/M, score 52.9 Anthropic: Claude Fable 5.1 — $10/M, score 81.6 Google: Gemma 4 31B (batch) — $0.39/M, score 43.4 Qwen: Qwen3.8 2.4T A95B (batch) — $2/M, score 71.9 Mistral: Devstral 2 2512 — $0.4/M, score 31.3 MoonshotAI: Kimi K2.7 Code (batch) — $0.95/M, score 60.8 Inkling — $1.87/M, score 52.1 OpenAI: gpt-oss-20b (batch) — $0.05/M, score 20.7 Muse Spark 1.1 — $1.25/M, score 71.3 MiMo-V2.5 — $0.14/M, score 56.8 Google: Gemini 3.5 Flash Lite (batch) — $0.15/M, score 49.3 Kimi K2 Thinking — $0.4/M, score 21.0 Mistral: Mistral Medium 3.5 (batch) — $0.75/M, score 46.9 Qwen: Qwen3.8 Max (0803) — $2/M, score 68.9 Mistral: Mistral Medium 3.1 (batch) — $0.2/M, score 20.5 MiMo-V2.5-Pro — $0.435/M, score 60.2 GPT-5.1 — $1.25/M, score 49.4 Qwen: Qwen3.8 27B — $0.42/M, score 68.1 Gemma 4 31B IT — $0.09/M, score 43.4 Google: Gemini 3.8 Flash (batch) — $0.375/M, score 76.3 OpenAI: GPT-5 Mini (batch) — $0.125/M, score 15.6 Gemini 2.5 Pro — $1.25/M, score 33.3 GPT-5.5 — $5/M, score 74.9 MoonshotAI: Kimi K3 (batch) — $3/M, score 76.2 Inkling Small — $0.45/M, score 52.9 Anthropic: Claude Sonnet 5 (batch) — $1/M, score 71.5 DeepSeek V3.2 — $0.18/M, score 44.2 Anthropic: Claude Fable 5 (batch) — $5/M, score 76.5 Nemotron 3 Super 120B A12B — $0.2/M, score 37.7 IBM: Granite 4.2 8B — $0.06/M, score 22.4 Anthropic: Claude Opus 4.8 — $5/M, score 74.3 Thinking Machines: Inkling (batch) — $1/M, score 52.1 Gemma 3 4B IT — $0.04/M, score 2.7 SpaceXAI: Grok 4.6 — $2/M, score 76.8 DeepSeek: DeepSeek V3.1 Terminus — $0.27/M, score 43.5 GPT-5 Mini — $0.25/M, score 15.6 Claude Opus 5 (batch) — $2.5/M, score 78.0 Anthropic: Claude Opus 4.8 (batch) — $2.5/M, score 74.3 SpaceXAI: Grok 4.3 — $1.25/M, score 42.2 OpenAI: GPT-6 Astra (batch) — $5/M, score 76.9 Google: Gemini 3.5 Flash (batch) — $0.75/M, score 70.1 OpenAI: GPT-5.6 Terra (batch) — $1/M, score 76.7 OpenAI: GPT-5.4 (batch) — $1.25/M, score 71.1 Mistral: Mistral Large 3 2512 — $0.5/M, score 20.1 OpenAI: GPT-4o-mini (batch) — $0.075/M, score 11.4 DeepSeek V4 Pro 0813 — $0.442/M, score 68.8 Z.ai: GLM 5.2 (batch) — $0.7/M, score 68.8 Google: Gemini 3.6 Flash (batch) — $0.375/M, score 69.2 Nemotron 3 Nano 30B A3B — $0.05/M, score 14.4 GPT-5.6 Terra — $2/M, score 76.7 MiniMax: MiniMax M3 (batch) — $0.3/M, score 58.6 Gemini 3.8 Flash — $0.75/M, score 76.3 NVIDIA: Nemotron 3 Ultra (batch) — $0.6/M, score 49.3 MiniMax: MiniMax M2.7 — $0.3/M, score 52.6 SpaceXAI: Grok 4.5 — $2/M, score 72.4 Mistral: Mistral Medium 3.1 — $0.4/M, score 20.5 OpenAI: gpt-oss-120b (batch) — $0.15/M, score 30.4 OpenAI: GPT-4.1 Mini (batch) — $0.2/M, score 20.2 Gemma 3 27B IT — $0.08/M, score 10.1 GPT-4 — $30/M, score 13.1 Solar Pro 4 — $0.3/M, score 52.7 Gemini 3.1 Pro Preview — $2/M, score 68.8 Anthropic: Claude Opus 4.7 (batch) — $2.5/M, score 73.6 GPT-5.6 Sol — $4/M, score 77.4 OpenAI: GPT-4.1 Nano (batch) — $0.05/M, score 11.1 OpenAI: GPT-5.1 (batch) — $0.625/M, score 49.4 Kimi K2.7 Code — $0.95/M, score 60.8 Kimi K3 — $3/M, score 76.2 GPT-5.4 — $2.5/M, score 71.1 Anthropic: Claude Sonnet 4.6 — $3/M, score 63.0 Anthropic: Claude Sonnet 4.6 (batch) — $1.5/M, score 63.0 Google: Gemini 3.7 Flash (batch) — $0.375/M, score 76.1 Muse Spark 1.2 — $1.25/M, score 72.2 DeepSeek: DeepSeek V4 Flash 0731 (batch) — $0.11/M, score 69.1 inclusionAI: Ling 3.0 Flash — $0.021/M, score 50.6 Qwen: Qwen3.7 Plus — $0.32/M, score 55.9 SpaceXAI: Grok 4.3 (batch) — $1/M, score 42.2 Kimi K2.6 — $0.95/M, score 61.8 Nemotron 3 Ultra 550B A55B — $0.5/M, score 49.3 Anthropic: Claude Sonnet 4 — $3/M, score 37.6 OpenAI: GPT-5.6 Luna (batch) — $0.1/M, score 71.4 OpenAI: GPT-5.4 Mini (batch) — $0.375/M, score 56.1 GPT-5.4 nano — $0.2/M, score 56.1 Qwen: Qwen3.8 2.4T A95B — $2/M, score 71.9 OpenAI: GPT-5.6 Sol (batch) — $1/M, score 77.4 Qwen: Qwen3.6 Plus — $0.325/M, score 54.5 Anthropic: Claude Haiku 4.5 (batch) — $0.5/M, score 43.9 Z.ai: GLM 4.6 — $0.43/M, score 45.8 Anthropic: Claude Sonnet 4.5 (batch) — $1.5/M, score 52.1 GPT-4o (2024-05-13) — $5/M, score 24.2 OpenAI: GPT-5 (batch) — $0.625/M, score 37.8 Qwen: Qwen3 Next 80B A3B Thinking — $0.15/M, score 17.4 DeepSeek V4 Flash 0731 — $0.05/M, score 69.1 OpenAI: GPT-4 Turbo (batch) — $5/M, score 21.5 Nemotron 3.5 Lightning 30B A3B — $0.05/M, score 26.8 Hy3 preview — $0.066/M, score 58.8 GPT-4.1 nano — $0.1/M, score 11.1 GPT OSS 20B — $0.02/M, score 20.7 GPT-4o mini — $0.15/M, score 11.4 o1 — $15/M, score 39.7 Kimi K2.5 — $0.3/M, score 46.8 Trinity Large Thinking — $0.25/M, score 25.8 Qwen: Qwen3 30B A3B Thinking 2507 — $0.2/M, score 12.1 Z.ai: GLM 5.2 — $0.966/M, score 68.8 Qwen: Qwen3.7 Max — $1.475/M, score 66.0 SpaceXAI: Grok Build 0.1 — $1/M, score 51.5 Qwen: Qwen3.6 35B A3B — $0.1/M, score 41.9 Qwen: Qwen3.6 27B — $0.3/M, score 53.7 inclusionAI: Ling-2.6-flash — $0.01/M, score 25.3 Mistral: Mistral Small 4 — $0.15/M, score 26.6 Kwaipilot: KAT-Coder-Pro V2 — $0.3/M, score 59.5 Qwen: Qwen3.5-9B — $0.1/M, score 28.7 Qwen: Qwen3.5-35B-A3B — $0.312/M, score 37.0 Qwen: Qwen3.5-122B-A10B — $0.26/M, score 45.7 Upstage: Solar Pro 3 — $0.15/M, score 16.2 Z.ai: GLM 4.7 — $0.4/M, score 45.3 Amazon: Nova 2 Lite — $0.3/M, score 23.0 Mistral: Ministral 3 3B 2512 — $0.1/M, score 4.8 Google: Gemma 3n 4B — $0.06/M, score 3.2 Meta: Llama 4 Maverick — $0.2/M, score 16.3 OpenAI: o3 Mini High — $1.1/M, score 16.3 Meta: Llama 3.3 70B Instruct — $0.1/M, score 11.9 Meta: Llama 3.1 8B Instruct — $0.05/M, score 5.4 Nex AGI: Nex-N2-Pro — $0.25/M, score 59.1 Mistral: Mistral Medium 3.5 — $1.5/M, score 46.9 inclusionAI: Ring-2.6-1T — $0.075/M, score 42.8 IBM: Granite 4.1 8B — $0.05/M, score 9.5 Qwen: Qwen3.5 397B A17B — $0.55/M, score 48.2 Qwen: Qwen3 Coder Next — $0.12/M, score 36.2 Mistral: Ministral 3 14B 2512 — $0.2/M, score 14.4 Anthropic: Claude Haiku 4.5 — $1/M, score 43.9 Qwen: Qwen3 235B A22B Thinking 2507 — $0.23/M, score 22.1 Qwen: Qwen3 8B — $0.117/M, score 9.0 Qwen: Qwen3 14B — $0.227/M, score 13.8 Qwen: Qwen3 32B — $0.08/M, score 15.3 Meta: Llama 4 Scout — $0.1/M, score 8.2 DeepSeek: DeepSeek V3 0324 — $0.25/M, score 21.2 Cohere: Command A — $2.5/M, score 27.8 Step 3.7 Flash — $0.185/M, score 39.6 DeepSeek V4 Flash 0731 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
Price Completion0.18 → 0.16
Price Prompt0.065 → 0.05
Max Output Tokens384000 → 943718
Context Length1000000 → 1048576
Price Completion0.16 → 0.18
Price Prompt0.05 → 0.065
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
Sep 11, 2026
Status
Source-linked
Confidence
Medium
Catalog source
Models.dev
Models.devcatalog ↗Alibaba Token Plan documentationprovider documentation ↗SCNet Token Plan documentationprovider documentation ↗Hetzner documentationprovider documentation ↗Alibaba Token Plan (China) documentationprovider documentation ↗Ollama Cloud documentationprovider documentation ↗Nvidia documentationprovider documentation ↗Eden AI documentationprovider documentation ↗NanoGPT documentationprovider documentation ↗Deep Infra documentationprovider documentation ↗OpenRouter documentationprovider documentation ↗Vercel AI Gateway 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://model.kyssta.lol/api/v1/models/deepseek/deepseek-v4-flash-0731
curl
curl "https://model.kyssta.lol/api/v1/models/deepseek/deepseek-v4-flash-0731"
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 Flash 0731?

Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding. It is published by DeepSeek and catalogued here from Models.dev.

How much does DeepSeek V4 Flash 0731 cost?

Listed input pricing starts at $0.03 per million tokens from Eden AI, rising to $0.468 across 48 listed providers.

What is the context length of DeepSeek V4 Flash 0731?

DeepSeek V4 Flash 0731 accepts up to 1M tokens of context and returns up to 384K output tokens.

Does DeepSeek V4 Flash 0731 support tool calling and structured output?

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

Which providers serve DeepSeek V4 Flash 0731?

43 providers list this model: Alibaba Token Plan, SCNet Token Plan, Hetzner, Alibaba Token Plan (China), Ollama Cloud, Nvidia and 37 more.

Are the weights for DeepSeek V4 Flash 0731 open?

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

When was DeepSeek V4 Flash 0731 released?

The catalog records a release date of 2026-07-31, last verified Sep 11, 2026.

More models from DeepSeek

View all →
DeepSeek: DeepSeek V3.1 Terminus

DeepSeek-V3.1 Terminus is an update to [DeepSeek V3.1](/deepseek/deepseek-chat-v3.1) that maintains the model's original capabilities while addressing issues reported by users, including language consistency and agent capabilities, further optimizing the model's...

131.072K ctx $0.27/M in DeepSeek V4 Pro 0813

DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes

1M ctx $0.442/M in DeepSeek-V3

Open DeepSeek MoE chat model for coding, math, and general reasoning

131.072K ctx $0.27/M in DeepSeek-R1-Distill-Qwen-32B

R1 reasoning distilled into Qwen 2.5 32B for efficient open-weight step-by-step problem solving

131.072K ctx $0.3/M in