DeepSeek V4 Pro
deepseek/v4-proPar DeepSeek · famille: deepseek-thinking · sorti 2026-04-24 · fin de connaissance: 2025-05
Prices in USD per 1M tokens. Unknown means the provider does not publish per-token pricing.
Capacités
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 output90
- Structured output / JSON mode50/50
- Tool calling20/20
- Temperature control10/10
- Price-friendly for high-volume10/20
Cost efficiency50
- Headline price (log-scaled)45/95
- Has prompt-cache pricing5/5
Long context90
- Context window (100K → 2M)80/90
- 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 | $10.44 $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 | $20.88 < $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 | $5.22 < $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 | $17.40 $0.02 per request | 8K input tokens (diff + surrounding files) and a 1K-token review comment. PR-bot workloads. |
Agent step per 1,000 steps | $22.97 $0.02 per request | 12K input tokens (long-running tool history) and a 600-token tool-call decision. Cost per agent step. |
Détail des tarifs
Tarif recommandé de deepseek · deepseek-v4-pro
Fournisseur le moins cher : wafer.ai · Unknown entrée + Unknown sortie
Disponible chez 24 fournisseurs
| Fournisseur | ID modèle fournisseur | Entrée / 1M | Sortie / 1M | Contexte | Publié le |
|---|---|---|---|---|---|
| DeepSeek deepseek | deepseek-v4-pro | $1.74 | $3.48 | 1M | 2026-04-24 |
| OpenRouter openrouter | deepseek/deepseek-v4-pro | $1.74 | $3.48 | 1.05M | 2026-04-24 |
| Vercel AI Gateway vercel | deepseek/deepseek-v4-pro | $1.74 | $3.48 | 1M | 2026-04-23 |
| Fireworks AI fireworks-ai | accounts/fireworks/models/deepseek-v4-pro | $1.74 | $3.48 | 1M | 2026-04-24 |
| Together AI togetherai | deepseek-ai/DeepSeek-V4-Pro | $2.10 | $4.40 | 512K | 2026-04-24 |
| Deep Infra deepinfra | deepseek-ai/DeepSeek-V4-Pro | $1.74 | $3.48 | 66K | 2026-04-24 |
| Hugging Face huggingface | deepseek-ai/DeepSeek-V4-Pro | $1.74 | $3.48 | 1.05M | 2026-04-24 |
| OpenCode Go opencode-go | deepseek-v4-pro | $1.74 | $3.48 | 1M | 2026-04-24 |
| Alibaba (China) alibaba-cn | deepseek-v4-pro | $1.74 | $3.48 | 1M | 2026-04-24 |
| ZenMux zenmux | deepseek/deepseek-v4-pro | $1.74 | $3.48 | 1M | 2026-04-24 |
| NovitaAI novita-ai | deepseek/deepseek-v4-pro | $1.69 | $3.38 | 1.05M | 2026-04-24 |
| Vivgrid vivgrid | deepseek-v4-pro | $1.74 | $3.48 | 1M | 2026-04-24 |
| Kilo Gateway kilo | deepseek/deepseek-v4-pro | $0.435 | $0.870 | 1.05M | 2026-04-24 |
| Nebius Token Factory nebius | deepseek-ai/DeepSeek-V4-Pro | $1.75 | $3.50 | 1M | 2026-04-24 |
| Ollama Cloud ollama-cloud | deepseek-v4-pro | Unknown | Unknown | 1.05M | 2026-04-24 |
| Baseten baseten | deepseek-ai/DeepSeek-V4-Pro | $1.74 | $3.48 | 1M | 2026-04-24 |
| FrogBot frogbot | deepseek-v4-pro | $1.74 | $3.48 | 128K | 2026-04-24 |
| Venice AI venice | deepseek-v4-pro | $1.73 | $3.80 | 1M | 2026-04-24 |
| AIHubMix aihubmix | deepseek-v4-pro | $0.478 | $0.956 | 1M | 2026-04-24 |
| Wafer wafer.ai | DeepSeek-V4-Pro | Unknown | Unknown | 1M | 2026-04-24 |
| Nvidia nvidia | deepseek-ai/deepseek-v4-pro | $1.74 | $3.48 | 1.05M | 2026-04-24 |
| DigitalOcean digitalocean | deepseek-v4-pro | $1.74 | $3.48 | 1.05M | 2026-04-24 |
| Cortecs cortecs | deepseek-v4-pro | $1.55 | $3.11 | 1.05M | 2026-04-24 |
| LLM Gateway llmgateway | deepseek-v4-pro | $1.74 | $3.48 | 1M | 2026-04-24 |
Incohérences de données entre fournisseurs
- context_window varies: 1000000, 1048576, 128000, 512000, 65536
Les fournisseurs rapportent des valeurs différentes pour ce modèle. Les infos clés ci-dessus utilisent un fournisseur représentatif ; voir le tableau pour le détail par fournisseur.
Frequently asked questions
How much does DeepSeek V4 Pro cost?
DeepSeek V4 Pro costs $1.74 per 1M input tokens and $3.48 per 1M output tokens, sourced from deepseek. 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 Pro?
DeepSeek V4 Pro has a context window of 1M tokens, with a max output of 384K tokens per reply. This is the total combined size of prompt + completion.
Does DeepSeek V4 Pro support tool calling?
Yes. DeepSeek V4 Pro 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 Pro support structured output / JSON mode?
Yes. DeepSeek V4 Pro 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 Pro accept image input?
No. DeepSeek V4 Pro only accepts text as input. If you need image input, see our /capabilities/vision list for current vision-capable models.
Is DeepSeek V4 Pro open-weight?
Yes. DeepSeek V4 Pro'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 Pro?
If DeepSeek V4 Pro doesn't fit, consider DeepSeek-V3.2, DeepSeek-R1-0528, DeepSeek-R1. 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 come from the public models.dev API and are normalised into a single canonical model record. We re-pull daily and write any changes (price, context, capability) to the /changelog page.
Explore more
More DeepSeek models
- DeepSeek-V3.2$0.26 in / $0.38 out
- DeepSeek-R1-0528$0.40 in / $1.70 out
- DeepSeek-R1$0.40 in / $1.70 out
- DeepSeek-V3.1$0.20 in / $0.70 out
- DeepSeek V4 Flash$0.14 in / $0.28 out
Capability lists this model is in
Dernière mise à jour :
Data is sourced from models.dev and normalized for comparison. Prices and capabilities may change. Always verify critical production decisions with the provider's official documentation.