DeepSeek V4 Pro 0813 vs DeepSeek V4 Pro API pricing
Updated
DeepSeek V4 Pro 0813: USD 0.85 input, USD 2.65 output per 1M tokens (Chutes). DeepSeek V4 Pro: USD 0.50 input, USD 2 output per 1M tokens (Relace). At 3 input tokens per output token, DeepSeek V4 Pro 0813 costs 49% more than DeepSeek V4 Pro (USD 1.30 vs USD 0.875 per 1M).
How do DeepSeek V4 Pro 0813 and DeepSeek V4 Pro differ on price?
- Cheapest input price: DeepSeek V4 Pro USD 0.50 against USD 0.85 per 1M tokens, so DeepSeek V4 Pro 0813 costs 1.7× as much (70% more).
- Cheapest output price: DeepSeek V4 Pro USD 1.914 against USD 2.60 per 1M tokens, so DeepSeek V4 Pro 0813 costs 1.36× as much (36% more).
- Among the 201 indexed models, DeepSeek V4 Pro 0813 ranks 140th cheapest and DeepSeek V4 Pro 124th on the 3:1 blend.
- No input:output mix changes the answer: DeepSeek V4 Pro is cheaper at every mix before cache discounts.
- Both list cached-input discounts: DeepSeek V4 Pro 0813 at 17 standard prices of 17, from USD 0.0352 (GMI Cloud, 97% below that provider's input price); DeepSeek V4 Pro at 11 standard prices of 12, from USD 0.05 (Relace, 90% below that provider's input price).
- Both state a context window of up to 1,048,576 tokens.
- DeepSeek V4 Pro 0813 has 17 providers with a standard price, 5 more than DeepSeek V4 Pro; 8 providers sell both (GMI Cloud, DeepInfra, SiliconFlow, Novita AI and 4 more).
- On one account, GMI Cloud charges USD 1.584 for DeepSeek V4 Pro 0813 (1.22× its cheapest price) and USD 1.196 for DeepSeek V4 Pro (1.37× its cheapest price) at 3:1, the lowest combined price among the providers that sell both.
- Shopping around matters more for DeepSeek V4 Pro: its dearest standard price is 3.4× its cheapest, against 1.9× for DeepSeek V4 Pro 0813.
- DeepSeek's own API charges USD 1.98 for DeepSeek V4 Pro 0813 at 3:1, 52% above the cheapest provider (Chutes).
- DeepSeek V4 Pro 0813 has a batch price at 1 provider, from USD 0.99 at 3:1 (Doubleword); DeepSeek V4 Pro has no batch price on file.
- For the one-developer coding agent preset, the gap is USD 2,009 a year in DeepSeek V4 Pro's favour (DeepSeek V4 Pro 0813 USD 558.90 a month, DeepSeek V4 Pro USD 391.50).
- Per character of input, DeepSeek V4 Pro 0813 costs 1.7× as much as DeepSeek V4 Pro in every measured language, because both use the DeepSeek V4.1 Flash tokenizer.
DeepSeek V4 Pro 0813 and DeepSeek V4 Pro prices side by side
USD per 1M tokens, standard tier. "Cheapest" is the lowest price at 3 input tokens to 1 output token; each line can come from a different provider.
| Price | DeepSeek V4 Pro 0813 | DeepSeek V4 Pro |
|---|---|---|
| Model page | DeepSeek V4 Pro 0813 DeepSeek · 17 providers | DeepSeek V4 Pro DeepSeek · 12 providers |
| Cheapest standard price, blended 3:1 | USD 1.30 USD 0.85 in / USD 2.65 out at Chutes Chutes page checked 2026-11-15 | USD 0.875 lower USD 0.50 in / USD 2 out at Relace Relace page checked 2026-11-16 |
| Cheapest input | USD 0.85 Chutes source | USD 0.50 lower Relace source |
| Cheapest cached input | USD 0.0352 lower promo GMI Cloud source | USD 0.05 Relace source |
| Cheapest output | USD 2.60 DeepInfra source | USD 1.914 lower promo GMI Cloud source |
| Maker's own API | USD 1.32 / USD 3.96 DeepSeek source | USD 1.32 / USD 3.96 DeepSeek, serving version source |
| Median standard price | USD 1.32 / USD 3.96 input / output, 17 prices | USD 1.625 / USD 3.2505 input / output, 12 prices |
| Context window | 1,048,576 tokens, largest stated; from 1,000,000 at some providers | 1,048,576 tokens, largest stated; from 262,144 at some providers |
| Providers with a standard price | 17 | 12 |
- Lower marks the lower price on a line; tie, equal prices. Other tiers and free rows are on the model pages.
- Promo: the provider calls the price promotional or discounted, so it is current now and can end without notice.
Report a wrong price or number (email to info@broadnet.ai, with this page's link filled in).
What do DeepSeek V4 Pro 0813 and DeepSeek V4 Pro cost for a real workload?
30 days at each model's cheapest standard price for the workload (presets of the cost calculator; cached input at the cached price where listed).
| Workload | DeepSeek V4 Pro 0813 | DeepSeek V4 Pro | Difference |
|---|---|---|---|
| Support chatbot 2,000 requests a day, 1,500 input tokens (60% cached), 300 output | USD 85.14 Sail Research | USD 56.70 Relace | USD 28.44 DeepSeek V4 Pro lower |
| RAG over documents 1,000 requests a day, 8,000 input tokens (30% cached), 500 output | USD 193.35 Chutes | USD 117.60 Relace | USD 75.75 DeepSeek V4 Pro lower |
| Coding agent (one developer) 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning | USD 558.90 Sail Research | USD 391.50 Relace | USD 167.40 DeepSeek V4 Pro lower |
DeepSeek V4 Pro is cheaper on all three workloads. The widest gap is on RAG over documents: the dearer model costs 64% more than the cheaper one.
Does the cheaper model change with your input:output ratio?
DeepSeek V4 Pro is cheaper at every mix of input and output tokens, before cache discounts: its cheapest input price and its cheapest output price are both at or below DeepSeek V4 Pro 0813's, so the input:output ratio never changes the answer.
| Input : output tokens | DeepSeek V4 Pro 0813 | DeepSeek V4 Pro |
|---|---|---|
| 1 : 3 (long answers) | USD 2.20 Chutes | USD 1.625 lower Relace |
| 1 : 1 | USD 1.75 Chutes | USD 1.25 lower Relace |
| 3 : 1 (the site’s blend) | USD 1.30 Chutes | USD 0.875 lower Relace |
| 10 : 1 (retrieval, long prompts) | USD 1.014 Chutes | USD 0.6364 lower Relace |
| 30 : 1 (agents, big contexts) | USD 0.9081 Chutes | USD 0.5484 lower Relace |
USD per 1M tokens at the cheapest standard provider for each mix, before cache discounts. Thinking tokens bill as output.
What do DeepSeek V4 Pro 0813 and DeepSeek V4 Pro cost per character in other languages?
Cost to send 1M characters at each model's cheapest non-promotional standard input price, with the DeepSeek V4.1 Flash tokenizer for DeepSeek V4 Pro 0813 (the same one for both, so the gap equals the price gap):
| Content | DeepSeek V4 Pro 0813 | DeepSeek V4 Pro |
|---|---|---|
| English | USD 0.182 Chutes | USD 0.107 lower Relace |
| Arabic MSA | USD 0.320 Chutes | USD 0.188 lower Relace |
| Egyptian Arabic | USD 0.329 Chutes | USD 0.193 lower Relace |
| Hindi | USD 0.491 Chutes | USD 0.289 lower Relace |
| Chinese | USD 0.498 Chutes | USD 0.293 lower Relace |
| Spanish | USD 0.219 Chutes | USD 0.129 lower Relace |
| Code | USD 0.224 Chutes | USD 0.132 lower Relace |
From the real cost by language dataset (measured tokens per character on FLORES-200 and other texts). Your own text will differ.
Published results on the same benchmark
BroadNet did not run these benchmarks. BroadRouter is BroadNet's site. Each row pairs results from one source with the same setting for both models, as published; results from different sources or settings are never put side by side. One benchmark says little about your own workload.
| Benchmark | DeepSeek V4 Pro 0813 | DeepSeek V4 Pro | Source and setting |
|---|---|---|---|
| GPQA Diamond | 0.917 | 0.896 | Epoch AI, checked 2026-11-16 Max reasoning setting, mean score on a 0 to 1 scale |
Epoch AI rows: Epoch AI, Capabilities & benchmarking, licensed CC BY 4.0, shown as the mean score on a 0 to 1 scale, rounded to three decimals (hover a value for the exact figure).
All published results for each model, with every setting: DeepSeek V4 Pro 0813 · DeepSeek V4 Pro.
Check it on your own traffic
- DeepSeek V4 Pro 0813 API pricing: all 17 providers and other tiers.
- DeepSeek V4 Pro API pricing: all 12 providers and other tiers.
- Cost calculator with DeepSeek V4 Pro 0813 and DeepSeek V4 Pro preloaded
- DeepSeek token counter
- Prompt caching calculator
More comparisons: GLM 5.3 vs DeepSeek V4 Pro 0813 · DeepSeek V4 Pro vs DeepSeek V3.2 · DeepSeek V4 Pro vs GLM 5.3 · DeepSeek V4 Pro vs Qwen3.8 Max · DeepSeek V4 Pro vs Kimi K3 · GPT-6 Sol vs DeepSeek V4 Pro · DeepSeek V4 Pro vs DeepSeek V4 Flash · every DeepSeek V4 Pro 0813 comparison · every DeepSeek V4 Pro comparison · all 662 price comparisons
Questions
Is DeepSeek V4 Pro 0813 cheaper than DeepSeek V4 Pro?
No. On a blend of 3 input tokens to 1 output token, DeepSeek V4 Pro costs USD 0.875 per 1M tokens and DeepSeek V4 Pro 0813 USD 1.30, at each model's cheapest standard price. For input alone, DeepSeek V4 Pro is cheaper (USD 0.50 against USD 0.85 per 1M); for output alone, DeepSeek V4 Pro is (USD 1.914 against USD 2.60). This compares price only, not quality.
What do DeepSeek V4 Pro 0813 and DeepSeek V4 Pro cost per 1M tokens?
DeepSeek V4 Pro 0813: from USD 0.85 input and USD 2.65 output at Chutes; DeepSeek's own API charges USD 1.32 / USD 3.96; median of 17 standard prices USD 1.32 / USD 3.96. DeepSeek V4 Pro: from USD 0.50 input and USD 2 output at Relace; DeepSeek's own API charges USD 1.32 / USD 3.96; median of 12 standard prices USD 1.625 / USD 3.2505. Each price is read from the provider's own pricing page; the source is linked in the table.
Which providers sell both DeepSeek V4 Pro 0813 and DeepSeek V4 Pro?
8 providers have a standard price for both: GMI Cloud (USD 1.584 and USD 1.196 at 3:1), DeepInfra (USD 1.625 and USD 1.625 at 3:1), SiliconFlow (USD 1.98 and USD 1.91 at 3:1), Novita AI (USD 1.98 and USD 2 at 3:1), Baidu (USD 1.98 and USD 2.112 at 3:1), DigitalOcean (USD 1.98 and USD 2.175 at 3:1), Venice (USD 2.475 and USD 2.063 at 3:1), Alibaba Cloud (USD 1.98 and USD 3 at 3:1). The first is the lowest combined price. Buying each model from its own cheapest provider costs USD 1.30 and USD 0.875.
Which is cheaper for a coding agent or a chatbot, DeepSeek V4 Pro 0813 or DeepSeek V4 Pro?
For a coding agent (1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning): USD 558.90 a month on DeepSeek V4 Pro 0813 (Sail Research) against USD 391.50 on DeepSeek V4 Pro (Relace), a difference of USD 167.40. For a support chatbot (2,000 requests a day, 1,500 input tokens (60% cached), 300 output): USD 85.14 a month on DeepSeek V4 Pro 0813 (Sail Research) against USD 56.70 on DeepSeek V4 Pro (Relace), a difference of USD 28.44. Each uses the cheapest standard price for that workload, cached input included. Try your own numbers.
At what input:output ratio does the cheaper of DeepSeek V4 Pro 0813 and DeepSeek V4 Pro change?
DeepSeek V4 Pro is cheaper at every mix of input and output tokens, before cache discounts: its cheapest input price and its cheapest output price are both at or below DeepSeek V4 Pro 0813's, so the input:output ratio never changes the answer.
Do DeepSeek V4 Pro 0813 and DeepSeek V4 Pro have cached input pricing?
DeepSeek V4 Pro 0813 from USD 0.0352 per 1M cached input tokens (GMI Cloud; 17 of 17 standard prices list a discount). DeepSeek V4 Pro from USD 0.05 per 1M cached input tokens (Relace; 11 of 12 standard prices list a discount). Cached tokens are billed at the input price where no cache price is published.
Which has the larger context window, DeepSeek V4 Pro 0813 or DeepSeek V4 Pro?
Both go up to 1,048,576 tokens on the providers that state it.
Which scores higher on GPQA Diamond, DeepSeek V4 Pro 0813 or DeepSeek V4 Pro?
Per Epoch AI (checked 2026-11-16), DeepSeek V4 Pro 0813 scores 0.917 and DeepSeek V4 Pro scores 0.896 on GPQA Diamond (Max reasoning setting, mean score on a 0 to 1 scale). BroadNet did not run these benchmarks, and one benchmark says little about your own workload. Every result both models share, with sources.
Read as MarkdownAsk ChatGPTAsk ClaudeAsk Perplexity
Sources
- Chutes: pricing (checked 2026-11-15)
- DeepInfra: pricing (checked 2026-11-14)
- GMI Cloud: pricing (checked 2026-11-15)
- DeepSeek: own API pricing (checked 2026-11-14)
- Relace: pricing (checked 2026-11-16)
- GMI Cloud: pricing (checked 2026-11-15)
- Sail Research: pricing (checked 2026-11-16)
- DeepInfra: pricing (checked 2026-11-14)
- SiliconFlow: pricing (checked 2026-11-14)
- Novita AI: pricing (checked 2026-11-14)
- Baidu: pricing (checked 2026-11-15)
- DigitalOcean: pricing (checked 2026-11-14)
- Venice: pricing (checked 2026-11-15)
- Alibaba Cloud: pricing (checked 2026-11-14)
- Doubleword: pricing (checked 2026-11-16)
- Epoch AI benchmark data, CC BY 4.0 (checked 2026-11-16)