ModelBench
DeepSeek logo
Models/DeepSeek

DeepSeek: DeepSeek: DeepSeek V4.1 Flash (batch)

DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...

Source-linked Weight access not listed
API record Report
InputT
OutputT
Input price$0.112/M
Output price$0.336/M
Context1.04858M
Max output131.072K
Providers0
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
No inference providers are listed

The model record exists, but no source-linked provider offer is available yet.

Submit a source
Specification

Capabilities

Recorded from the source catalog and provider listings.

? Reasoning Unknown
? Tool calling Unknown
? Structured output Unknown
? Attachments Unknown
✓ Vision input Yes
? Open weights Unknown
Creator
DeepSeek
Model family
Not documented
Knowledge cutoff
Not documented
License
Not documented
Release date
Not documented
Model ID
deepseek/deepseek-v4.1-flash:batch
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 #44 of 205

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 Anthropic: Claude Opus 5.5 — $4/M, score 57.6 SpaceXAI: Grok 4.7 — $1.6/M, score 46.4 GPT-5.6 Sol — $4/M, score 47.0 Anthropic: Claude Opus 4.8 (batch) — $2.5/M, score 41.8 Inkling Small — $0.45/M, score 26.1 Mistral: Mistral Large 3 2512 — $0.55/M, score 9.7 GPT-5.5 — $5/M, score 38.4 GPT-5.4 — $2.5/M, score 53.1 OpenAI: gpt-oss-20b (batch) — $0.024/M, score 9.0 OpenAI: o3 Mini High (batch) — $0.55/M, score 15.7 Trinity Large Thinking — $0.25/M, score 10.8 SpaceXAI: Grok 4.5 — $2/M, score 38.8 Claude Sonnet 5 — $2/M, score 38.2 Gemma 4 26B A4B IT — $0.042/M, score 26.1 DeepSeek V4 Flash — $0.15/M, score 24.2 inclusionAI: Ling 3.0 Flash VL — $0.06/M, score 24.6 Mistral: Devstral 2 2512 — $0.4/M, score 8.6 Thinking Machines: Inkling (batch) — $1/M, score 25.0 Google: Gemma 4 31B (batch) — $0.39/M, score 15.4 Kimi K3 — $3/M, score 43.6 Anthropic: Claude Opus 4.7 (batch) — $2.5/M, score 55.0 Gemini 3.5 Flash Lite — $0.3/M, score 22.2 LongCat-2.0 — $0.3/M, score 19.1 Nemotron 3 Super 120B A12B — $0.2/M, score 12.8 Z.ai: GLM 5.2 (batch) — $0.7/M, score 33.7 GPT OSS 20B — $0.018/M, score 9.0 OpenAI: GPT-6 Sol (batch) — $1/M, score 47.5 GPT-5.6 Luna — $0.2/M, score 37.3 Muse Spark 1.2 — $1.25/M, score 39.6 OpenAI: GPT-5.4 Nano (batch) — $0.1/M, score 20.7 Mistral: Mistral Small 4 (batch) — $0.075/M, score 11.3 OpenAI: GPT-6 Luna (batch) — $0.05/M, score 37.3 GPT-6 Sol — $2/M, score 47.5 Anthropic: Claude Opus 5.5 (batch) — $2/M, score 57.6 Google: Gemini 3.8 Flash (batch) — $0.375/M, score 40.9 Anthropic: Claude Fable 5.1 — $10/M, score 53.4 MoonshotAI: Kimi K2.7 Code (batch) — $0.95/M, score 43.0 Nemotron 3 Ultra 550B A55B — $0.5/M, score 22.9 SpaceXAI: Grok 4.3 — $1.25/M, score 24.9 Qwen: Qwen3 Next 80B A3B Thinking — $0.15/M, score 16.9 Claude Fable 5 — $10/M, score 49.6 GPT-5 Mini — $0.25/M, score 16.8 OpenAI: GPT-5.4 (batch) — $1.25/M, score 53.1 Kimi K2 Thinking — $0.4/M, score 17.2 DeepSeek V4 Flash 0731 — $0.035/M, score 34.3 Qwen: Qwen3.8 2.4T A95B (batch) — $2/M, score 39.9 Gemma 4 31B IT — $0.09/M, score 15.4 MiMo-V2.5 — $0.14/M, score 22.3 Qwen: Qwen3.8 Max (0803) — $2/M, score 53.4 Anthropic: Claude Sonnet 4.5 — $3/M, score 20.7 Gemini 3.7 Flash — $0.75/M, score 39.1 inclusionAI: Ling 3.0 Flash — $0.021/M, score 20.6 OpenAI: GPT-5.6 Terra (batch) — $1/M, score 42.1 Claude Opus 5 — $5/M, score 50.8 DeepSeek-R1 — $0.696/M, score 11.4 Mistral: Ministral 3 8B 2512 — $0.15/M, score 5.5 Gemini 3.1 Pro Preview — $2/M, score 29.7 Muse Spark 1.1 — $1.25/M, score 33.7 Gemini 3.6 Flash — $0.75/M, score 34.0 Gemma 3 12B IT — $0.05/M, score 3.8 Gemini 2.5 Pro — $1.25/M, score 16.1 Gemini 3.8 Flash — $0.75/M, score 40.9 MiniMax: MiniMax M3 (batch) — $0.3/M, score 29.2 DeepSeek: DeepSeek V4.1 Flash (batch) — $0.112/M, score 39.5 Anthropic: Claude Sonnet 5 (batch) — $1/M, score 38.2 Anthropic: Claude Sonnet 4.6 (batch) — $1.5/M, score 30.1 Z.ai: GLM 5.3 — $0.84/M, score 44.8 Ling 3.0 Flash Fin — $0.06/M, score 22.6 Kimi K2.5 — $0.3/M, score 36.0 Nemotron 3.5 Lightning 30B A3B — $0.05/M, score 12.9 Thinking Machines: Inkling Small (batch) — $0.5/M, score 26.1 Google: Gemini 2.5 Pro (batch) — $0.625/M, score 16.1 GPT-5.6 Terra — $2/M, score 42.1 GPT-5.1 — $1.25/M, score 37.5 Z.ai: GLM 5.3 Flash (batch) — $0.06/M, score 41.8 NVIDIA: Nemotron 3 Ultra (batch) — $0.6/M, score 38.3 OpenAI: GPT-6 Astra (batch) — $5/M, score 52.7 Qwen: Qwen3.6 Plus — $0.325/M, score 40.5 Inkling — $1.87/M, score 25.0 Google: Gemini 3.1 Pro Preview (batch) — $1/M, score 29.7 GPT-4.1 mini — $0.4/M, score 14.8 SpaceXAI: Grok 4.3 (batch) — $1/M, score 24.9 Qwen: Qwen3.8 2.4T A95B — $2/M, score 39.9 Google: Gemini 3.6 Flash (batch) — $0.375/M, score 34.0 MoonshotAI: Kimi K3 (batch) — $2.28/M, score 43.6 DeepSeek V4 Pro — $0.435/M, score 30.4 OpenAI: gpt-oss-120b (batch) — $0.15/M, score 11.6 DeepSeek: DeepSeek V4 Pro 0813 (batch) — $0.66/M, score 36.0 DeepSeek V3.2 — $0.18/M, score 32.6 Anthropic: Claude Fable 5.1 (batch) — $5/M, score 53.4 Anthropic: Claude Fable 5 (batch) — $5/M, score 49.6 OpenAI: GPT-5.4 Mini (batch) — $0.375/M, score 24.1 OpenAI: GPT-5 (batch) — $0.625/M, score 35.3 OpenAI: GPT-5 Mini (batch) — $0.125/M, score 16.8 GPT-6 Astra — $10/M, score 52.7 Google: Gemini 3.5 Flash Lite (batch) — $0.15/M, score 22.2 Qwen: Qwen3 235B A22B Thinking 2507 — $0.23/M, score 12.7 Gemini 3.5 Flash — $1.5/M, score 32.6 Qwen: Qwen3.7 Plus — $0.32/M, score 25.2 OpenAI: GPT-4.1 Nano (batch) — $0.05/M, score 9.6 Qwen: Qwen3.5-9B (batch) — $0.17/M, score 21.8 Google: Gemini 3.5 Flash (batch) — $0.75/M, score 32.6 GPT-4.1 nano — $0.1/M, score 9.6 DeepSeek: DeepSeek V4 Flash 0731 (batch) — $0.11/M, score 34.3 Z.ai: GLM 5.1 — $0.966/M, score 26.1 Z.ai: GLM 5.3 Flash — $0.15/M, score 41.8 OpenAI: GPT-5.6 Sol (batch) — $1/M, score 47.0 Nemotron 3 Nano 30B A3B — $0.05/M, score 8.9 OpenAI: GPT-5.1 (batch) — $0.625/M, score 37.5 Anthropic: Claude Haiku 4.5 (batch) — $0.5/M, score 16.9 Z.ai: GLM 4.6 — $0.43/M, score 29.3 DeepSeek: DeepSeek V3.1 Terminus — $0.27/M, score 14.8 Qwen: Qwen3.8 27B — $0.42/M, score 33.7 Mistral: Mistral Medium 3.1 — $0.4/M, score 9.2 MiMo-V2.5-Pro — $0.435/M, score 26.0 Mistral: Mistral Medium 3.5 (batch) — $0.75/M, score 14.2 Solar Pro 4 — $0.3/M, score 41.6 OpenAI: GPT-4.1 Mini (batch) — $0.2/M, score 14.8 Google: Gemini 3.7 Flash (batch) — $0.375/M, score 39.1 IBM: Granite 4.2 8B — $0.06/M, score 11.1 MiniMax: MiniMax M2.7 — $0.3/M, score 22.8 MiMo-V2.6-Pro — $0.435/M, score 46.3 Anthropic: Claude Opus 4.7 — $5/M, score 55.0 Anthropic: Claude Sonnet 4.6 — $3/M, score 30.1 OpenAI: GPT-5.6 Luna (batch) — $0.1/M, score 37.3 GPT-5.4 mini — $0.75/M, score 24.1 GPT-5 — $1.25/M, score 35.3 Anthropic: Claude Opus 4.8 — $5/M, score 41.8 Hy3 preview — $0.172/M, score 25.3 DeepSeek V4 Pro 0813 — $0.442/M, score 36.0 Qwen: Qwen3.8 Max (0902) — $2/M, score 45.4 Z.ai: GLM 5.3 (batch) — $0.72/M, score 44.8 MiniMax: MiniMax M3 — $0.3/M, score 29.2 OpenAI: GPT-5.5 (batch) — $2.5/M, score 38.4 Inception: Mercury 2 — $0.25/M, score 11.5 Anthropic: Claude Sonnet 4.5 (batch) — $1.5/M, score 20.7 Mistral: Mistral Medium 3.1 (batch) — $0.2/M, score 9.2 Anthropic: Claude Sonnet 4 — $3/M, score 29.8 Qwen: Qwen3 14B — $0.12/M, score 6.4 GPT-6 Luna — $0.1/M, score 37.3 GPT-5.4 nano — $0.2/M, score 20.7 Kimi K2.6 — $0.95/M, score 27.0 SpaceXAI: Grok 4.6 — $2/M, score 44.3 DeepSeek V4.1 Flash — $0.15/M, score 39.5 Anthropic: Claude Opus 5 (batch) — $2.5/M, score 50.8 Gemini 3.1 Flash Lite Preview — $0.25/M, score 15.6 Mistral: Ministral 3 8B 2512 (batch) — $0.075/M, score 5.5 Mistral: Mistral Large 3 2512 (batch) — $0.25/M, score 9.3 Gemma 3 27B IT — $0.08/M, score 4.9 GPT OSS 120B — $0.03/M, score 11.6 Kimi K2.7 Code — $0.95/M, score 25.8 Qwen: Qwen3 30B A3B Thinking 2507 — $0.2/M, score 9.8 Z.ai: GLM 5.2 — $0.65/M, score 33.7 Qwen: Qwen3.7 Max — $1.475/M, score 29.5 SpaceXAI: Grok Build 0.1 — $1/M, score 40.7 Qwen: Qwen3.6 35B A3B — $0.15/M, score 18.2 Qwen: Qwen3.6 27B — $0.32/M, score 21.4 inclusionAI: Ling-2.6-flash — $0.01/M, score 14.2 Mistral: Mistral Small 4 — $0.15/M, score 11.3 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 15.6 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 — $0.188/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-N2-Pro — $0.5/M, score 41.7 Mistral: Mistral Medium 3.5 — $1.5/M, score 14.2 inclusionAI: Ring-2.6-1T — $0.075/M, score 31.7 Qwen: Qwen3.5 397B A17B — $0.55/M, score 18.4 Qwen: Qwen3 Coder Next — $0.12/M, score 9.2 Mistral: Ministral 3 14B 2512 — $0.2/M, score 6.0 Anthropic: Claude Haiku 4.5 — $1/M, score 16.9 Qwen: Qwen3 8B — $0.117/M, score 5.2 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 13.1 Step 3.7 Flash — $0.185/M, score 30.9 DeepSeek: DeepSeek V4.1 Flash (batch) 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
No changes recorded

This record has not changed within the retained import history.

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:batch
curl
curl "https://model.kyssta.lol/api/v1/models/deepseek/deepseek-v4.1-flash:batch"
Common questions

Frequently asked questions

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

What is DeepSeek: DeepSeek V4.1 Flash (batch)?

DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on. It is published by DeepSeek and catalogued here from OpenRouter.

What is the context length of DeepSeek: DeepSeek V4.1 Flash (batch)?

DeepSeek: DeepSeek V4.1 Flash (batch) accepts up to 1.04858M tokens of context and returns up to 131.072K output tokens.

Does DeepSeek: DeepSeek V4.1 Flash (batch) support tool calling and structured output?

Provider catalogs list support for image input.

More models from DeepSeek

View all →
DeepSeek: DeepSeek V3.1

DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context...

163.84K ctx $0.25/M in DeepSeek: R1 Distill Llama 70B

DeepSeek R1 Distill Llama 70B is a distilled large language model based on [Llama-3.3-70B-Instruct](/meta-llama/llama-3.3-70b-instruct), using outputs from [DeepSeek R1](/deepseek/deepseek-r1). The model combines advanced distillation techniques to achieve high performance across...

8.192K ctx $0.8/M in DeepSeek: R1 0528

May 28th update to the [original DeepSeek R1](/deepseek/deepseek-r1) Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active...

163.84K ctx $0.5/M in DeepSeek: DeepSeek V3 0324

DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team. It succeeds the [DeepSeek V3](/deepseek/deepseek-chat-v3) model and performs really well...

163.84K ctx $0.25/M in