DeepSeek V4.1 Flash
deepseek/v4-1-flashBy DeepSeek · family: deepseek-flash · released 2026-09-10 · knowledge: 2025-05
Prices in USD per 1M tokens. Unknown means the provider does not publish per-token pricing.
Capabilities
Model fit scores
0–100 · higher is betterThese scores reward declared capabilities, context size, price and provider availability — they are not benchmark results. Use them as a directional signal alongside your own evaluation.
Coding100
- Tool calling40/40
- Structured output20/20
- Reasoning10/10
- Context window (100K → 1M)20/20
- Provider availability10/10
Agents100
- Tool calling35/35
- Structured output25/25
- Reasoning15/15
- Output token limit15/15
- Provider availability10/10
JSON / structured output99
- Structured output / JSON mode50/50
- Tool calling20/20
- Temperature control10/10
- Price-friendly for high-volume19/20
Cost efficiency77
- Headline price (log-scaled)72/95
- Has prompt-cache pricing5/5
Long context91
- Context window (100K → 2M)81/90
- Has published price for full window10/10
Vision100
- Accepts image input50/50
- Context window (10K → 1M)30/30
- Has published price10/10
- Provider availability10/10
Production-readiness96
- Number of independent providers40/40
- Has published per-token price20/20
- Context window ≥ 8K15/15
- No data inconsistencies across providers6/10
- Official model (not derivative)15/15
Cost Efficiency Index
Open full calculator →Estimated cost using the recommended provider's headline rate. Each scenario fixes average input/output tokens — the assumptions are shown in the third column.
| Scenario | Cost | Assumption |
|---|---|---|
RAG answer per 1,000 RAG answers | $0.84 < $0.01 per request | 5K input tokens (query + 4 retrieved chunks of ~1K each) and a 500-token answer. Typical SaaS knowledge-base bot. |
Support ticket triage per 10,000 tickets | $1.68 < $0.01 per request | 1K input tokens (ticket body + system prompt) and a 100-token JSON classification reply. High-volume customer support. |
Data extraction per 1,000 documents | $0.42 < $0.01 per request | 2K input tokens (a single document page) and a 500-token JSON extraction. ETL / invoice / form pipelines. |
Code review per 1,000 PRs | $1.40 < $0.01 per request | 8K input tokens (diff + surrounding files) and a 1K-token review comment. PR-bot workloads. |
Agent step per 1,000 steps | $1.85 < $0.01 per request | 12K input tokens (long-running tool history) and a 600-token tool-call decision. Cost per agent step. |
Pricing detail
Recommended pricing from amd · DeepSeek-V4.1-Flash
Cheapest provider: alibaba-token-plan · Unknown input + Unknown output
Available on 53 providers
| Provider | Provider model id | Input / 1M | Output / 1M | Context | Released |
|---|---|---|---|---|---|
| OpenRouter openrouter | deepseek/deepseek-v4.1-flash | $0.020 | $0.600 | 1.05M | 2026-09-10 |
| Vercel AI Gateway vercel | deepseek/deepseek-v4.1-flash | $0.300 | $1.20 | 1.05M | 2026-09-10 |
| Together AI togetherai | deepseek-ai/DeepSeek-V4.1-Flash | $0.300 | $1.20 | 1.05M | 2026-09-10 |
| Deep Infra deepinfra | deepseek-ai/DeepSeek-V4.1-Flash | $0.200 | $0.600 | 1.05M | 2026-09-10 |
| Hugging Face huggingface | deepseek-ai/DeepSeek-V4.1-Flash | $0.300 | $1.20 | 1.05M | 2026-09-10 |
| EmpirioLabs AI empiriolabs | deepseek-v4-1-flash | $0.300 | $1.20 | 1M | 2026-09-10 |
| Alibaba Token Plan alibaba-token-plan | deepseek-v4.1-flash | Unknown | Unknown | 1M | 2026-09-10 |
| NanoGPT nano-gpt | deepseek/deepseek-v4.1-flash | $0.130 | $0.520 | 1M | 2026-09-10 |
| NanoGPT nano-gpt | TEE/deepseek-v4.1-flash | $0.650 | $1.45 | 1.05M | 2026-09-10 |
| Tinfoil tinfoil | deepseek-v4-1-flash | $0.650 | $1.45 | 1.05M | 2026-09-10 |
| Baseten baseten | deepseek-ai/DeepSeek-V4.1-Flash | $0.300 | $1.20 | 1.05M | 2026-09-10 |
| CoreWeave wandb | deepseek-ai/DeepSeek-V4.1-Flash | $0.200 | $0.650 | 1.05M | 2026-09-10 |
| LLM Gateway llmgateway-providers | consensusprotocol/deepseek-v4.1-flash | $0.200 | $0.600 | 1.05M | 2026-09-10 |
| LLM Gateway llmgateway-providers | deepinfra/deepseek-v4.1-flash | $0.200 | $0.600 | 1.05M | 2026-09-10 |
| LLM Gateway llmgateway-providers | scx-ai-gp/deepseek-v4.1-flash | $0.150 | $0.600 | 1M | 2026-09-10 |
| LLM Gateway llmgateway-providers | deepseek/deepseek-v4.1-flash | $0.150 | $0.600 | 1.05M | 2026-09-10 |
| LLM Gateway llmgateway-providers | runware/deepseek-v4.1-flash | $0.150 | $0.600 | 1.05M | 2026-09-10 |
| LLM Gateway llmgateway-providers | fireworks/deepseek-v4.1-flash | $0.220 | $0.660 | 1.05M | 2026-09-10 |
| LLM Gateway llmgateway-providers | together-ai/deepseek-v4.1-flash | $0.300 | $1.20 | 1.05M | 2026-09-10 |
| above.dev above | deepseek-v4.1-flash | $0.165 | $0.660 | 1M | 2026-09-10 |
| Kilo Gateway kilo | deepseek/deepseek-v4.1-flash | $0.300 | $1.20 | 1.05M | 2026-09-10 |
| Venice AI venice | deepseek-v4-1-flash | $0.375 | $1.50 | 1M | 2026-09-10 |
| Alibaba Token Plan (China) alibaba-token-plan-cn | deepseek-v4.1-flash | Unknown | Unknown | 1M | 2026-09-10 |
| Melious melious | deepseek-v4.1-flash | $0.232 | $1.16 | 1M | 2026-09-10 |
| ClinePass cline-pass | cline-pass/deepseek-v4.1-flash | $0.150 | $0.600 | 1M | 2026-09-10 |
| Neuralwatt neuralwatt | deepseek-v4.1-flash | $0.150 | $0.600 | 1.05M | 2026-09-10 |
| ZenMux zenmux | deepseek/deepseek-v4.1-flash | $0.150 | $0.600 | 1M | 2026-09-10 |
| Vancine vancine | deepseek-v4.1-flash | $0.240 | $0.960 | 1M | 2026-09-10 |
| Ollama Cloud ollama-cloud | deepseek-v4.1-flash | $0.150 | $0.600 | 1.05M | 2026-09-10 |
| Nebius Token Factory nebius | deepseek-ai/DeepSeek-V4.1-Flash | $0.300 | $1.20 | 1.05M | 2026-09-10 |
| GreenPT greenpt | deepseek-v4.1-flash | $0.256 | $1.28 | 1M | 2026-09-10 |
| Charm Hyper hyper | deepseek-v4.1-flash | $0.300 | $1.20 | 1.05M | 2026-09-10 |
| SCNet Token Plan scnet-token-plan | DeepSeek-V4.1-Flash | Unknown | Unknown | 1M | 2026-09-10 |
| Ofox ofox | deepseek/deepseek-v4.1-flash | $0.210 | $0.840 | 1M | 2026-09-10 |
| AIHubMix aihubmix | deepseek-v4.1-flash | $0.155 | $0.620 | 1M | 2026-09-10 |
| Merge Gateway merge-gateway | deepseek/deepseek-v4.1-flash | $0.150 | $0.600 | 1M | 2026-09-10 |
| OpenCode Go opencode-go | deepseek-v4.1-flash | $0.150 | $0.600 | 1M | 2026-09-10 |
| TensorX tensorx | deepseek/deepseek-v4.1-flash | $0.500 | $1.50 | 1.05M | 2026-09-10 |
| Eden AI edenai | deepinfra/deepseek-ai/DeepSeek-V4.1-Flash | $0.200 | $0.600 | 1.05M | 2026-09-10 |
| Eden AI edenai | together_ai/deepseek-ai/DeepSeek-V4.1-Flash | $0.300 | $1.20 | 1.05M | 2026-09-10 |
| Eden AI edenai | nebius/deepseek-ai/DeepSeek-V4.1-Flash | $0.300 | $1.20 | 1.05M | 2026-09-10 |
| Eden AI edenai | tensorx/deepseek/deepseek-v4.1-flash | $0.500 | $1.50 | 1.05M | 2026-09-10 |
| OpenCode Zen opencode | deepseek-v4.1-flash | $0.300 | $1.20 | 1M | 2026-09-10 |
| Kenari kenari | deepseek-v4-1-flash | Unknown | Unknown | 1M | 2026-09-10 |
| Requesty requesty | deepseek-v4.1-flash | $0.500 | $1.50 | 1.05M | 2026-09-10 |
| Synthetic synthetic | hf:deepseek-ai/DeepSeek-V4.1-Flash | $0.600 | $1.20 | 524K | 2026-09-10 |
| DevPass (LLM Gateway) llmgateway | deepseek-v4.1-flash | $0.150 | $0.600 | 1.05M | 2026-09-10 |
| Vivgrid vivgrid | deepseek-v4.1-flash | $0.310 | $1.23 | 1M | 2026-09-10 |
| Cortecs cortecs | deepseek-v4.1-flash | $0.300 | $1.20 | 1.05M | 2026-09-10 |
| CrossModel crossmodel | deepseek/deepseek-v4.1-flash | $0.270 | $1.08 | 1M | 2026-09-10 |
| AMD amd | DeepSeek-V4.1-Flash | $0.140 | $0.280 | 1.05M | 2026-09-10 |
| DigitalOcean digitalocean | deepseek-v4.1-flash | $0.300 | $1.20 | 1.05M | 2026-09-10 |
| Alibaba (China) alibaba-cn | deepseek-v4.1-flash | $0.298 | $1.19 | 1M | 2026-09-10 |
Data inconsistencies across providers
- context_window varies: 1000000, 1048000, 1048560, 1048576, 1050000, 524288
- modalities varies across offerings
Different providers report different values for this model. Quick facts above use the representative provider; consult the table for per-provider truth.
Frequently asked questions
How much does DeepSeek V4.1 Flash cost?
DeepSeek V4.1 Flash costs $0.140 per 1M input tokens and $0.280 per 1M output tokens, sourced from amd. Cache reads, audio tokens and >200K-context tiers (where applicable) are listed in the Pricing detail block above.
What is the context window of DeepSeek V4.1 Flash?
DeepSeek V4.1 Flash has a context window of 1.05M tokens, with a max output of 944K tokens per reply. This is the total combined size of prompt + completion.
Does DeepSeek V4.1 Flash support tool calling?
Yes. DeepSeek V4.1 Flash supports tool calling (function calling). This makes it suitable for production agent and automation workloads where the model has to invoke external functions reliably.
Does DeepSeek V4.1 Flash support structured output / JSON mode?
Yes. DeepSeek V4.1 Flash supports structured output / JSON-schema-constrained decoding. This makes it suitable for production agent and automation workloads where the model has to invoke external functions reliably.
Can DeepSeek V4.1 Flash accept image input?
Yes. DeepSeek V4.1 Flash accepts both text and image input. Vision pricing per image is usually billed on top of the regular token rate — check DeepSeek's docs for the exact rule.
Is DeepSeek V4.1 Flash open-weight?
Yes. DeepSeek V4.1 Flash's weights are publicly available, so you can self-host or fine-tune. Note that open weights ≠ open source — the training data and code are typically not released.
What are the best alternatives to DeepSeek V4.1 Flash?
If DeepSeek V4.1 Flash doesn't fit, consider DeepSeek V4 Pro, DeepSeek V4 Flash, DeepSeek V4 Flash 0731. Each one targets the same use case — see the Related links below for direct head-to-head pages.
Where does this data come from?
All numbers are normalised into a single canonical model record and reconciled with each provider's official documentation. We re-pull daily and write any changes (price, context, capability) to the /changelog page.
Explore more
More DeepSeek models
- DeepSeek V4 Pro$0.43 in / $0.87 out
- DeepSeek V4 Flash$0.15 in / $0.60 out
- DeepSeek V4 Flash 0731$0.04 in / $0.07 out
- DeepSeek V4 Pro 0813$0.35 in / $0.80 out
- DeepSeek-V3.2$0.18 in / $0.35 out
Capability lists this model is in
Last updated:
Pricing and capabilities are refreshed daily and reconciled against each provider's official documentation. Always verify critical production decisions with the provider directly.