ModelBench
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$0.15/M
Output price$0.6/M
Context1M
Max output384K
Providers18
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
Merge Gateway deepseek/deepseek-v4.1-flash 1M 384K $0.15 $0.6 $0.003 ReasoningToolsJSON Docs ↗
OpenCode Go deepseek-v4.1-flash 1M 384K $0.15 $0.6 $0.003 ReasoningToolsJSON Docs ↗
OpenRouter deepseek/deepseek-v4.1-flash 1.04858M 384K $0.15 $0.6 $0.003 ReasoningToolsJSON Docs ↗
DeepSeek deepseek-flash 1M 384K $0.15 $0.6 $0.003 ReasoningToolsJSON Docs ↗
OpenCode Go deepseek-flash 1M 384K $0.15 $0.6 $0.003 ReasoningToolsJSON Docs ↗
NanoGPT deepseek/deepseek-v4.1-flash 1M 384K $0.15 $0.6 $0.003 ReasoningToolsJSON Docs ↗
LLM Gateway deepseek/deepseek-v4.1-flash 1.05M 393.216K $0.15 $0.6 $0.003 ReasoningTools Docs ↗
DevPass (LLM Gateway) deepseek-v4.1-flash 1.05M 384K $0.15 $0.6 $0.003 ReasoningToolsJSON Docs ↗
Deep Infra deepseek-ai/DeepSeek-V4.1-Flash 1.04858M 384K $0.2 $0.6 $0.006 ReasoningToolsJSON Docs ↗
Requesty deepseek-v4.1-flash 1.04858M 393.216K $0.22 $0.66 $0.007 ReasoningToolsJSON Docs ↗
Fireworks AI accounts/fireworks/models/deepseek-v4p1-flash 1M 384K $0.22 $0.66 $0.007 ReasoningToolsJSON Docs ↗
CrossModel deepseek/deepseek-v4.1-flash 1M 384K $0.27 $1.08 $0.005 ReasoningToolsJSON Docs ↗
Vercel AI Gateway deepseek/deepseek-v4.1-flash 1.04858M 393.216K $0.3 $1.2 $0.006 ReasoningToolsJSON Docs ↗
Ofox deepseek/deepseek-v4.1-flash 1M 384K $0.3 $1.2 $0.006 ReasoningToolsJSON Docs ↗
Hugging Face deepseek-ai/DeepSeek-V4.1-Flash 1.04858M 384K $0.3 $1.2 — ReasoningToolsJSON Docs ↗
Kilo Gateway deepseek/deepseek-v4.1-flash 1.04858M 384K $0.3 $1.2 $0.006 ReasoningToolsJSON Docs ↗
Charm Hyper deepseek-v4.1-flash 1.04858M 26.214K $0.3 $1.2 $0.03 ReasoningToolsJSON Docs ↗
Venice AI deepseek-v4-1-flash 1M 131.072K $0.375 $1.5 $0.007 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 $0.15/M

Across 18 priced providers

Median input $0.21/M

Midpoint of listed rates

Highest input $0.375/M

2.5× the lowest listed rate

Output range $0.6 – $1.5

Per million output tokens

Merge Gateway $0.15/M
OpenCode Go $0.15/M
OpenRouter $0.15/M
DeepSeek $0.15/M
OpenCode Go $0.15/M
NanoGPT $0.15/M
LLM Gateway $0.15/M
DevPass (LLM Gateway) $0.15/M
Deep Infra $0.2/M
Requesty $0.22/M
Fireworks AI $0.22/M
CrossModel $0.27/M
Vercel AI Gateway $0.3/M
Ofox $0.3/M
Hugging Face $0.3/M
Kilo Gateway $0.3/M
Charm Hyper $0.3/M
Venice AI $0.375/M
Cost calculator

Estimate a workload

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

8 providers list the identical $0.15 input rate, so price alone will not separate them — compare context limits, max output, and capabilities above.

Context limits also differ by provider, from 1M 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
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
Intelligence Index index Source ↗
Intelligence Index #42 of 191

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 29 58 $0.01 $0.1 $1 $10 Anthropic: Claude Fable 5.1 (batch) — $5/M, score 53.4 Claude Opus 5 — $5/M, score 50.7 Mistral: Ministral 3 8B 2512 (batch) — $0.075/M, score 5.5 Anthropic: Claude Opus 4.7 — $5/M, score 55.0 OpenAI: GPT-5.4 Nano (batch) — $0.1/M, score 21.2 Inception: Mercury 2 — $0.25/M, score 11.5 Gemini 3.1 Flash Lite Preview — $0.25/M, score 16.0 Gemini 3.5 Flash Lite — $0.3/M, score 22.7 Gemma 3 12B IT — $0.05/M, score 3.8 Mistral: Mistral Large 3 2512 (batch) — $0.25/M, score 9.7 Anthropic: Claude Sonnet 4.5 — $3/M, score 21.2 OpenAI: o3 Mini High (batch) — $0.55/M, score 15.7 Qwen: Qwen3.8 Max (0902) — $2/M, score 40.3 Gemini 3.5 Flash — $1.5/M, score 33.0 Z.ai: GLM 5.3 Flash (batch) — $0.075/M, score 41.9 DeepSeek V4 Flash — $0.15/M, score 24.8 DeepSeek-R1 — $0.7/M, score 11.4 DeepSeek V4 Pro — $0.435/M, score 30.9 GPT-5.6 Luna — $0.2/M, score 37.5 GPT-4.1 mini — $0.4/M, score 14.8 GPT OSS 120B — $0.03/M, score 12.3 GPT-5 — $1.25/M, score 35.3 Claude Sonnet 5 — $2/M, score 38.4 Mistral: Ministral 3 8B 2512 — $0.15/M, score 5.5 Z.ai: GLM 5.3 (batch) — $0.7/M, score 44.9 Z.ai: GLM 5.1 — $0.966/M, score 26.4 Gemini 3.7 Flash — $0.75/M, score 39.4 Z.ai: GLM 5.3 — $1.4/M, score 44.9 Google: Gemini 3.1 Pro Preview (batch) — $1/M, score 30.4 LongCat-2.0 — $0.3/M, score 19.7 Google: Gemini 2.5 Pro (batch) — $0.625/M, score 16.7 OpenAI: GPT-5.5 (batch) — $2.5/M, score 38.6 GPT-6 Astra — $10/M, score 52.8 Gemini 3.6 Flash — $0.75/M, score 34.3 Qwen: Qwen3.5-9B (batch) — $0.17/M, score 21.8 GPT-5.4 mini — $0.75/M, score 24.6 Gemma 4 26B A4B IT — $0.042/M, score 26.1 Claude Fable 5 — $10/M, score 49.7 Mistral: Mistral Small 4 (batch) — $0.075/M, score 11.5 Z.ai: GLM 5.3 Flash — $0.15/M, score 41.9 MiniMax: MiniMax M3 — $0.3/M, score 29.6 DeepSeek: DeepSeek V4 Pro 0813 (batch) — $0.66/M, score 36.3 Thinking Machines: Inkling Small (batch) — $0.5/M, score 26.1 Anthropic: Claude Fable 5.1 — $10/M, score 53.4 Google: Gemma 4 31B (batch) — $0.39/M, score 15.4 Qwen: Qwen3.8 2.4T A95B (batch) — $2/M, score 40.0 Mistral: Devstral 2 2512 — $0.4/M, score 9.4 MoonshotAI: Kimi K2.7 Code (batch) — $0.95/M, score 43.0 Inkling — $1.87/M, score 25.5 OpenAI: gpt-oss-20b (batch) — $0.05/M, score 9.0 Muse Spark 1.1 — $1.25/M, score 34.3 MiMo-V2.5 — $0.14/M, score 22.3 Google: Gemini 3.5 Flash Lite (batch) — $0.15/M, score 22.7 Kimi K2 Thinking — $0.4/M, score 17.2 Mistral: Mistral Medium 3.5 (batch) — $0.75/M, score 14.9 Qwen: Qwen3.8 Max (0803) — $2/M, score 53.4 Mistral: Mistral Medium 3.1 (batch) — $0.2/M, score 14.7 MiMo-V2.5-Pro — $0.435/M, score 26.4 GPT-5.1 — $1.25/M, score 37.5 Qwen: Qwen3.8 27B — $0.42/M, score 33.9 Gemma 4 31B IT — $0.09/M, score 15.4 Google: Gemini 3.8 Flash (batch) — $0.375/M, score 41.2 OpenAI: GPT-5 Mini (batch) — $0.125/M, score 17.4 Gemini 2.5 Pro — $1.25/M, score 16.7 GPT-5.5 — $5/M, score 38.6 MoonshotAI: Kimi K3 (batch) — $3/M, score 43.8 Inkling Small — $0.45/M, score 26.1 Anthropic: Claude Sonnet 5 (batch) — $1/M, score 38.4 DeepSeek V3.2 — $0.18/M, score 32.6 Anthropic: Claude Fable 5 (batch) — $5/M, score 49.7 Nemotron 3 Super 120B A12B — $0.2/M, score 13.6 IBM: Granite 4.2 8B — $0.06/M, score 11.8 Anthropic: Claude Opus 4.8 — $5/M, score 42.0 Thinking Machines: Inkling (batch) — $1/M, score 25.5 SpaceXAI: Grok 4.6 — $2/M, score 44.4 DeepSeek: DeepSeek V3.1 Terminus — $0.27/M, score 15.4 GPT-5 Mini — $0.25/M, score 17.4 Claude Opus 5 (batch) — $2.5/M, score 50.7 Anthropic: Claude Opus 4.8 (batch) — $2.5/M, score 42.0 SpaceXAI: Grok 4.3 — $1.25/M, score 25.4 OpenAI: GPT-6 Astra (batch) — $5/M, score 52.8 Google: Gemini 3.5 Flash (batch) — $0.75/M, score 33.0 OpenAI: GPT-5.6 Terra (batch) — $1/M, score 42.3 OpenAI: GPT-5.4 (batch) — $1.25/M, score 53.1 Mistral: Mistral Large 3 2512 — $0.5/M, score 9.7 DeepSeek V4 Pro 0813 — $0.442/M, score 36.3 Z.ai: GLM 5.2 (batch) — $0.7/M, score 52.6 Google: Gemini 3.6 Flash (batch) — $0.375/M, score 34.3 Nemotron 3 Nano 30B A3B — $0.05/M, score 8.9 GPT-5.6 Terra — $2/M, score 42.3 MiniMax: MiniMax M3 (batch) — $0.3/M, score 29.6 DeepSeek V4.1 Flash — $0.15/M, score 39.5 Gemini 3.8 Flash — $0.75/M, score 41.2 NVIDIA: Nemotron 3 Ultra (batch) — $0.6/M, score 38.3 MiniMax: MiniMax M2.7 — $0.3/M, score 23.2 SpaceXAI: Grok 4.5 — $2/M, score 39.1 Mistral: Mistral Medium 3.1 — $0.4/M, score 14.7 OpenAI: gpt-oss-120b (batch) — $0.15/M, score 12.3 OpenAI: GPT-4.1 Mini (batch) — $0.2/M, score 14.8 Gemma 3 27B IT — $0.08/M, score 4.9 Solar Pro 4 — $0.3/M, score 41.6 Gemini 3.1 Pro Preview — $2/M, score 30.4 Anthropic: Claude Opus 4.7 (batch) — $2.5/M, score 55.0 GPT-5.6 Sol — $4/M, score 47.1 OpenAI: GPT-4.1 Nano (batch) — $0.05/M, score 9.6 OpenAI: GPT-5.1 (batch) — $0.625/M, score 37.5 Kimi K2.7 Code — $0.95/M, score 26.3 Kimi K3 — $3/M, score 43.8 GPT-5.4 — $2.5/M, score 53.1 Anthropic: Claude Sonnet 4.6 — $3/M, score 30.5 Anthropic: Claude Sonnet 4.6 (batch) — $1.5/M, score 30.5 Google: Gemini 3.7 Flash (batch) — $0.375/M, score 39.4 Muse Spark 1.2 — $1.25/M, score 39.8 DeepSeek: DeepSeek V4 Flash 0731 (batch) — $0.11/M, score 34.5 inclusionAI: Ling 3.0 Flash — $0.021/M, score 27.4 Qwen: Qwen3.7 Plus — $0.32/M, score 25.8 SpaceXAI: Grok 4.3 (batch) — $1/M, score 25.4 Kimi K2.6 — $0.95/M, score 45.1 Nemotron 3 Ultra 550B A55B — $0.5/M, score 23.4 Anthropic: Claude Sonnet 4 — $3/M, score 29.8 OpenAI: GPT-5.6 Luna (batch) — $0.1/M, score 37.5 OpenAI: GPT-5.4 Mini (batch) — $0.375/M, score 24.6 GPT-5.4 nano — $0.2/M, score 21.2 Qwen: Qwen3.8 2.4T A95B — $2/M, score 40.0 OpenAI: GPT-5.6 Sol (batch) — $1/M, score 47.1 Qwen: Qwen3.6 Plus — $0.325/M, score 40.5 Anthropic: Claude Haiku 4.5 (batch) — $0.5/M, score 17.6 Z.ai: GLM 4.6 — $0.43/M, score 29.3 Anthropic: Claude Sonnet 4.5 (batch) — $1.5/M, score 21.2 OpenAI: GPT-5 (batch) — $0.625/M, score 35.3 Qwen: Qwen3 Next 80B A3B Thinking — $0.15/M, score 16.9 DeepSeek V4 Flash 0731 — $0.05/M, score 34.5 Nemotron 3.5 Lightning 30B A3B — $0.05/M, score 13.6 Hy3 preview — $0.066/M, score 25.8 GPT-4.1 nano — $0.1/M, score 9.6 GPT OSS 20B — $0.02/M, score 9.0 Kimi K2.5 — $0.3/M, score 36.0 Trinity Large Thinking — $0.25/M, score 10.9 Qwen: Qwen3 30B A3B Thinking 2507 — $0.2/M, score 9.8 Z.ai: GLM 5.2 — $0.966/M, score 52.6 Qwen: Qwen3.7 Max — $1.475/M, score 29.9 SpaceXAI: Grok Build 0.1 — $1/M, score 40.7 Qwen: Qwen3.6 35B A3B — $0.1/M, score 18.8 Qwen: Qwen3.6 27B — $0.3/M, score 21.9 inclusionAI: Ling-2.6-flash — $0.01/M, score 14.2 Mistral: Mistral Small 4 — $0.15/M, score 11.5 Kwaipilot: KAT-Coder-Pro V2 — $0.3/M, score 33.7 Qwen: Qwen3.5-9B — $0.1/M, score 21.8 Qwen: Qwen3.5-35B-A3B — $0.312/M, score 24.3 Qwen: Qwen3.5-122B-A10B — $0.26/M, score 16.2 Upstage: Solar Pro 3 — $0.15/M, score 7.8 Z.ai: GLM 4.7 — $0.4/M, score 34.5 Amazon: Nova 2 Lite — $0.3/M, score 18.4 Mistral: Ministral 3 3B 2512 — $0.1/M, score 4.8 Meta: Llama 4 Maverick — $0.2/M, score 9.3 OpenAI: o3 Mini High — $1.1/M, score 11.0 Meta: Llama 3.3 70B Instruct — $0.1/M, score 9.3 Meta: Llama 3.1 8B Instruct — $0.05/M, score 7.8 Nex AGI: Nex-N2-Pro — $0.25/M, score 41.7 Mistral: Mistral Medium 3.5 — $1.5/M, score 14.9 inclusionAI: Ring-2.6-1T — $0.075/M, score 31.7 Qwen: Qwen3.5 397B A17B — $0.55/M, score 19.1 Qwen: Qwen3 Coder Next — $0.12/M, score 10.1 Mistral: Ministral 3 14B 2512 — $0.2/M, score 6.0 Anthropic: Claude Haiku 4.5 — $1/M, score 17.6 Qwen: Qwen3 235B A22B Thinking 2507 — $0.23/M, score 12.7 Qwen: Qwen3 8B — $0.117/M, score 5.2 Qwen: Qwen3 14B — $0.227/M, score 6.4 Qwen: Qwen3 32B — $0.08/M, score 7.2 Meta: Llama 4 Scout — $0.1/M, score 6.5 DeepSeek: DeepSeek V3 0324 — $0.25/M, score 9.7 Cohere: Command A — $2.5/M, score 13.9 Step 3.7 Flash — $0.185/M, score 30.9 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
Context Length1048576 → 1000000
Context Length1000000 → 1048576
Context Length1048576 → 1000000
Context Length1000000 → 1048576
Context Length1048576 → 1000000
Context Length1000000 → 1048576
Context Length1048576 → 1000000
Context Length1000000 → 1048576
Context Length1048576 → 1000000
Context Length1000000 → 1048576
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 ↗Merge Gateway documentationprovider documentation ↗OpenCode Go documentationprovider documentation ↗OpenRouter documentationprovider documentation ↗DeepSeek documentationprovider documentation ↗NanoGPT documentationprovider documentation ↗DevPass (LLM Gateway) documentationprovider documentation ↗Deep Infra documentationprovider documentation ↗Requesty documentationprovider documentation ↗Fireworks AI documentationprovider documentation ↗CrossModel 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-v4.1-flash
curl
curl "https://model.kyssta.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 $0.15 per million tokens from Merge Gateway, rising to $0.375 across 18 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?

17 providers list this model: Merge Gateway, OpenCode Go, OpenRouter, DeepSeek, NanoGPT, LLM Gateway and 11 more.

Are the weights for DeepSeek V4.1 Flash open?

Yes. The weights are published under the MIT license.

When was DeepSeek V4.1 Flash released?

The catalog records a release date of 2026-09-10, last verified Sep 11, 2026.

More models from DeepSeek

View all →
DeepSeek V4 Pro 0423

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

1M ctx $1.32/M in DeepSeek OCR 2

High-accuracy OCR model for extracting text from documents, screenshots, receipts, and natural scenes

8.192K ctx $0.03/M in DeepSeek-V3.1

Hybrid-reasoning DeepSeek model with thinking and non-thinking modes

131.072K ctx $0.19/M in deepseek-ai/ESFT-gate-law-lite

No provider description available.

Not documented ctx