DeepSeek V4 Flash 0731
deepseek/v4-flash-0731By DeepSeek · family: deepseek-flash · released 2026-07-31 · 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 output100
- Structured output / JSON mode50/50
- Tool calling20/20
- Temperature control10/10
- Price-friendly for high-volume20/20
Cost efficiency91
- Headline price (log-scaled)86/95
- Has prompt-cache pricing5/5
Long context96
- Context window (100K → 2M)86/90
- Has published price for full window10/10
Production-readiness98
- Number of independent providers40/40
- Has published per-token price20/20
- Context window ≥ 8K15/15
- No data inconsistencies across providers8/10
- 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 | $0.21 < $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 | $0.42 < $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 | $0.11 < $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 | $0.35 < $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 | $0.46 < $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 merge-gateway · deepseek/deepseek-v4-flash-0731
Cheapest provider: alibaba-token-plan · Unknown input + Unknown output
Available on 47 providers
| Provider | Provider model id | Input / 1M | Output / 1M | Context | Released |
|---|---|---|---|---|---|
| OpenRouter openrouter | deepseek/deepseek-v4-flash-0731 | $0.021 | $0.320 | 1.31M | 2026-07-31 |
| Vercel AI Gateway vercel | deepseek/deepseek-v4-flash-0731 | $0.076 | $0.153 | 1M | 2026-07-31 |
| Together AI togetherai | deepseek-ai/DeepSeek-V4-Flash-0731 | $0.140 | $0.280 | 1.05M | 2026-07-31 |
| Deep Infra deepinfra | deepseek-ai/DeepSeek-V4-Flash-0731 | $0.060 | $0.180 | 1.05M | 2026-07-31 |
| Hugging Face huggingface | deepseek-ai/DeepSeek-V4-Flash-0731 | $0.140 | $0.280 | 1.05M | 2026-07-31 |
| Perplexity Agent perplexity-agent | deepseek/deepseek-v4-flash-0731 | $0.130 | $0.260 | 1M | 2026-07-31 |
| EmpirioLabs AI empiriolabs | deepseek-v4-flash-0731 | $0.424 | $1.27 | 1M | 2026-07-31 |
| Alibaba Token Plan alibaba-token-plan | deepseek-v4-flash-0731 | Unknown | Unknown | 1M | 2026-07-31 |
| Cloudflare Workers AI cloudflare-workers-ai | @cf/deepseek-ai/deepseek-v4-flash-0731 | $0.440 | $1.32 | 1.31M | 2026-07-31 |
| NanoGPT nano-gpt | deepseek/deepseek-v4-flash-0731 | $0.050 | $0.160 | 1M | 2026-07-31 |
| CrofAI crof | deepseek-v4-flash-0731 | $0.080 | $0.100 | 1M | 2026-07-31 |
| Baseten baseten | deepseek-ai/DeepSeek-V4-Flash-0731 | $0.130 | $0.260 | 1.05M | 2026-07-31 |
| CoreWeave wandb | deepseek-ai/DeepSeek-V4-Flash-0731 | $0.130 | $0.280 | 262K | 2026-07-31 |
| SiliconFlow siliconflow | deepseek-ai/DeepSeek-V4-Flash-0731 | $0.220 | $0.660 | 1M | 2026-07-31 |
| Bothub bothub | deepseek-v4-flash-0731 | $0.100 | $0.280 | 1M | 2026-07-31 |
| Kilo Gateway kilo | deepseek/deepseek-v4-flash-0731 | $0.440 | $1.32 | 1.05M | 2026-07-31 |
| Venice AI venice | deepseek-v4-flash-0731 | $0.175 | $0.350 | 1M | 2026-07-31 |
| Alibaba Token Plan (China) alibaba-token-plan-cn | deepseek-v4-flash-0731 | Unknown | Unknown | 1M | 2026-07-31 |
| Melious melious | deepseek-v4-flash-0731 | $0.116 | $0.290 | 1M | 2026-07-31 |
| IteraCompute iteracompute | deepseek/deepseek-v4-flash-0731 | $0.340 | $1.05 | 970K | 2026-07-31 |
| Alibaba alibaba | deepseek-v4-flash-0731 | $0.200 | $0.400 | 1M | 2026-07-31 |
| Inceptron inceptron | deepseek-ai/DeepSeek-V4-Flash-0731 | $0.130 | $0.280 | 1.05M | 2026-07-31 |
| Ollama Cloud ollama-cloud | deepseek-v4-flash:0731 | $0.220 | $0.660 | 1.05M | 2026-07-31 |
| Ambient ambient | deepseek/deepseek-v4-flash-0731 | $0.080 | $0.180 | 1.05M | 2026-07-31 |
| Nebius Token Factory nebius | deepseek-ai/DeepSeek-V4-Flash-0731 | $0.140 | $0.280 | 1.02M | 2026-07-31 |
| Scaleway scaleway | deepseek-v4-flash-0731 | $0.468 | $0.936 | 256K | 2026-07-31 |
| GreenPT greenpt | deepseek-v4-flash-0731 | $0.160 | $0.399 | 1M | 2026-07-31 |
| Charm Hyper hyper | deepseek-v4-flash-0731 | $0.440 | $1.32 | 1M | 2026-08-02 |
| OrcaRouter orcarouter | deepseek/deepseek-v4-flash-0731 | $0.147 | $0.295 | 1M | 2026-07-31 |
| SCNet Token Plan scnet-token-plan | DeepSeek-V4-Flash-0731 | Unknown | Unknown | 1M | 2026-07-31 |
| Ofox ofox | deepseek/deepseek-v4-flash-0731 | $0.308 | $0.924 | 1M | 2026-07-31 |
| AIHubMix aihubmix | deepseek-v4-flash-0731 | $0.142 | $0.284 | 1M | 2026-07-31 |
| Merge Gateway merge-gateway | deepseek/deepseek-v4-flash-0731 | $0.035 | $0.070 | 1.05M | 2026-07-31 |
| Nvidia nvidia | deepseek-ai/deepseek-v4-flash-0731 | Unknown | Unknown | 1M | 2026-07-31 |
| OpenReason openreason | deepseek-ai/deepseek-v4-flash-0731 | $0.137 | $0.274 | 1M | 2026-07-31 |
| TensorX tensorx | deepseek/deepseek-v4-flash-0731 | $0.250 | $0.300 | 1.05M | 2026-07-31 |
| Eden AI edenai | deepinfra/deepseek-ai/DeepSeek-V4-Flash-0731 | $0.060 | $0.180 | 1.05M | 2026-07-31 |
| Eden AI edenai | together_ai/deepseek-ai/DeepSeek-V4-Flash-0731 | $0.140 | $0.280 | 1.05M | 2026-07-31 |
| Eden AI edenai | flexai/DeepSeek-V4-Flash-0731 | $0.060 | $0.180 | 1.05M | 2026-07-31 |
| Eden AI edenai | nebius/deepseek-ai/DeepSeek-V4-Flash-0731 | $0.140 | $0.280 | 1.02M | 2026-07-31 |
| Eden AI edenai | scaleway/deepseek-v4-flash-0731 | $0.456 | $0.912 | 256K | 2026-07-31 |
| Eden AI edenai | cloudflare/@cf/deepseek-ai/deepseek-v4-flash-0731 | $0.440 | $1.32 | 1.31M | 2026-07-31 |
| Eden AI edenai | tensorx/deepseek/deepseek-v4-flash-0731 | $0.250 | $0.300 | 1.05M | 2026-07-31 |
| Requesty requesty | deepseek-v4-flash-0731 | $0.280 | $0.560 | 1.05M | 2026-07-31 |
| Cortecs cortecs | deepseek-v4-flash-0731 | $0.090 | $0.170 | 1.05M | 2026-07-31 |
| RunInfra runinfra | deepseek-ai/DeepSeek-V4-Flash-0731 | $0.130 | $0.270 | 1.05M | 2026-07-31 |
| DigitalOcean digitalocean | deepseek-v4-flash-0731 | $0.140 | $0.280 | 1.05M | 2026-07-31 |
Data inconsistencies across providers
- context_window varies: 1000000, 1024000, 1048576, 1310720, 256000, 262144, 970000
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 Flash 0731 cost?
DeepSeek V4 Flash 0731 costs $0.035 per 1M input tokens and $0.070 per 1M output tokens, sourced from merge-gateway. 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 Flash 0731?
DeepSeek V4 Flash 0731 has a context window of 1.31M tokens, with a max output of 944K tokens per reply. This is the total combined size of prompt + completion.
Does DeepSeek V4 Flash 0731 support tool calling?
Yes. DeepSeek V4 Flash 0731 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 Flash 0731 support structured output / JSON mode?
Yes. DeepSeek V4 Flash 0731 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 Flash 0731 accept image input?
No. DeepSeek V4 Flash 0731 only accepts text as input. If you need image input, see our /capabilities/vision list for current vision-capable models.
Is DeepSeek V4 Flash 0731 open-weight?
Yes. DeepSeek V4 Flash 0731'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 Flash 0731?
If DeepSeek V4 Flash 0731 doesn't fit, consider DeepSeek V4 Pro, DeepSeek V4 Flash, DeepSeek V4.1 Flash. 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 V4.1 Flash$0.14 in / $0.28 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.