DeepInfra raises $107M Series B to scale the inference cloud — read the announcement

DeepSeek V4 Pro Pricing (0813): Providers & Cost Guide 2026

Published on 2026.04.30 by DeepInfra
DeepSeek V4 Pro Pricing (0813): Providers & Cost Guide 2026

Updated November 2026 for the DeepSeek-V4-Pro-0813 release.

DeepSeek-V4-Pro-0813 is the GA release of DeepSeek V4 Pro, an open-weight Mixture-of-Experts model with 1.6T total parameters, 49B active parameters and a 1M-token context window. DeepSeek released it on August 13, 2026, and it has been on DeepInfra since August 18. It ships under the MIT license and supports JSON mode, structured output and function calling. It replaces the preview DeepSeek first released on April 24, 2026.

On DeepInfra, DeepSeek V4 Pro costs $1.30 per 1M input tokens, $2.60 per 1M output tokens and $0.10 per 1M cached input tokens. There is no promo running; that is the list price. The Flex tier drops it to $1.04 / $2.08 / $0.08, and Priority raises it to $1.95 / $3.90 / $0.15.

Artificial Analysis now tracks 8 API providers for the 0813 model. DeepInfra has the lowest output price of the eight and the second-lowest blended price ($0.59 per 1M tokens, behind GMI at $0.55), with a 0.0% endpoint error rate. It is not the cheapest place for cached input, and DeepSeek’s own API is now cheaper than everyone during its off-peak hours. This guide covers both, plus five worked monthly cost scenarios.

For developers and ML teams, the question is not whether DeepSeek V4 Pro is capable. It is whether its price profile fits your workload: how much you send, how much it writes back, how much of your prompt repeats, and whether your jobs can wait.

DeepSeek V4 Pro Executive Summary

DeepSeek V4 Pro is an open-weight reasoning model for coding, long-context analysis and agent workflows. If output tokens drive your bill, DeepInfra is the cheapest of the eight providers Artificial Analysis measures. If your traffic is mostly cache reads, or your batch jobs can run in DeepSeek’s off-peak window, other routes cost less per token. The table below maps each case to a route.

Pricing as of 2026-11-16.

Best ForProvider RecommendationWhy
Output-heavy production workloadsDeepInfra (Standard)$2.60 per 1M output tokens, the lowest output price among the 8 providers on Artificial Analysis. Most of the others charge $3.96.
Batch and non-urgent jobsDeepInfra Flex, or DeepSeek off-peakFlex bills $1.04 input and $2.08 output per 1M tokens. DeepSeek’s off-peak rate ($0.66 / $1.98) is lower still if you can schedule into its window.
Cache-heavy agents and RAGDeepSeek API, or providers with a $0.044 cache rateCache reads cost $0.044 per 1M on DeepSeek (peak), DigitalOcean, Novita and SiliconFlow, against $0.10 on DeepInfra. DeepInfra’s lower output price wins back the gap once output is a real share of the bill.
Lowest blended priceGMI, with DeepInfra close behind$0.55 vs $0.59 per 1M on Artificial Analysis’s 7:2:1 cache, input and output blend.
Fastest output and lowest answer latencyDigitalOcean140.0 tokens per second and 31.67 seconds to the first answer token, the best on both. Its error rate is 3.1%.
Reliability and complianceDeepInfra0.0% error rate on Artificial Analysis, plus zero retention, SOC 2 and ISO 27001, and Priority ($1.95 / $3.90) when you need capacity at busy times.
Single API across many providersOpenRouterLists 20 providers on the 0813 model and can fail over between them.

Verdict: start with DeepInfra Standard for interactive traffic, move anything that can wait to Flex, and check DeepSeek’s off-peak rates if you run large scheduled batches. Pick a faster provider only when response time is the hard constraint.

Sources: Artificial Analysis providers page (DeepSeek V4 Pro 0813, Max reasoning effort), DeepSeek Models & Pricing, the DeepInfra model page and OpenRouter, accessed 2026-11-16.

What Changed in DeepSeek-V4-Pro-0813

0813 is the same base architecture as the April preview, with new post-training and a built-in speculative decoding module. DeepSeek’s own model name on its API, deepseek-v4-pro, now serves 0813. Here is what changed in the model, then in pricing and availability.

The model

AreaApril preview0813 (GA)
ReleaseApril 24, 2026August 13, 2026
Reasoning controlThree modes (Non-think, Think High, Think Max) set by a special system promptreasoning_effort: low, high or max
Speculative decodingNone in the checkpointDSpark module built into the checkpoint
Recommended top_p1.00.95 for agentic tasks, 1.0 otherwise
Max output (vendor guidance)384K context recommended for Think Max384K for high and max effort
Context window1M1M (unchanged)
VisionNot supportedNot supported

DeepSeek reports large gains on agentic and coding benchmarks. On its Hugging Face model card, DeepSWE rises from 12.8 to 62.7, Terminal Bench 2.1 from 72.1 to 87.9, and NL2Repo from 38.5 to 61.5. These are vendor-reported numbers run on DeepSeek’s own harness. On Artificial Analysis’s independent Intelligence Index, 0813 (Max) scores 23, level with the median of comparable open-weight models. See the DeepSeek V4 Pro model overview for the full benchmark table.

Pricing and availability

AreaEarlier version of this guideCurrent
DeepInfra model IDdeepseek-ai/DeepSeek-V4-Prodeepseek-ai/DeepSeek-V4-Pro-0813
DeepInfra input / output / cached (per 1M)$1.74 / $3.48 / $0.145$1.30 / $2.60 / $0.10
DeepInfra service tiersStandard onlyStandard, Flex (0.8×) and Priority (1.5×)
Serving precision on DeepInfraFP4fp8
Max output on DeepInfraNot stated384K tokens (65,536 by default if max_tokens is unset)
DeepSeek first-party pricingOne flat ratePeak and off-peak: $1.32 / $3.96 peak, $0.66 / $1.98 off-peak
Providers on Artificial Analysis6, then 108
Blended price method3:1 input to output7:2:1 cache hit, input and output
DeepInfra blended price$2.17 per 1M (3:1)$0.59 per 1M (7:2:1)

The two blended prices use different ratios, so they are not directly comparable. The current blend weights cache reads at 70%, which is why blended figures now sit well below list prices.

The original deepseek-ai/DeepSeek-V4-Pro ID is still live on DeepInfra at the same price. New integrations should use the 0813 ID.

Understanding Tokens and How You’re Charged

If you have ever looked at a model bill and thought, “that prompt was not that long,” this is the part that explains why it was.

A token is a chunk of text the model reads or generates. It is not the same thing as a word. Short words may be one token. Longer words, code, JSON, whitespace patterns and odd punctuation can split into more. Pricing is based on tokens, so the shape of your workload matters more than the raw character count.

  • Input tokens are everything you send to the model: system prompt, user message, tool schemas, retrieved context, chat history, and any scaffolding your app injects.
  • Output tokens are everything the model sends back: answers, code, JSON objects, function-call arguments and, for a reasoning model like this one, the reasoning itself.
  • Cached tokens are repeated prompt content the provider has already processed. They bill at a lower rate. Long system prompts, reused documents and persistent agent instructions benefit most.
  • Blended price is the comparison shortcut benchmarks use. Artificial Analysis blends 7 parts cache hit, 2 parts input and 1 part output. That assumes a cache-heavy workload, which favors providers with cheap cache reads. It is not your bill unless your traffic matches that mix.
Token typeWhat it isWhy it matters for DeepSeek V4 Pro
Input tokensTokens you send in the requestThe largest cost for RAG, long-context and agent workloads. A full 1M-token prompt costs about $1.36 uncached on DeepInfra.
Output tokensTokens the model generates, reasoning includedReasoning tokens bill at the output rate. This is where DeepInfra’s $2.60 rate saves the most.
Cached input tokensRepeated prompt prefix billed at a discountDeepInfra charges $0.10 (92% off its own input rate). Some providers charge $0.022 to $0.044.
Max output tokensThe cap on one responseUp to 384K on DeepInfra. If you leave max_tokens unset, the default is 65,536.
Blended tokensA weighted mix of cache, input and output pricesUseful for ranking providers, unreliable for forecasting your own bill.

What this means for 0813 specifically:

  • It writes a lot. Artificial Analysis counted 119M output tokens to run its Intelligence Index at Max effort, against a 104M median for comparable models, and rates it “somewhat verbose”.
  • Reasoning effort is a cost dial. low, high and max change how many reasoning tokens the model produces before it answers, and every one of them bills as output.
  • A long answer has a real price. A response that runs to the 65,536-token default costs about $0.17 in output on DeepInfra Standard. One that uses the full 384K costs about $1.02. Set max_tokens to what the task needs.
  • Caching helps, but shop the cache rate. DeepInfra’s $0.10 cache read is 2.3× DeepSeek’s peak rate ($0.044) and 4.5× its off-peak rate ($0.022). Flex brings DeepInfra’s cache read to $0.08.

Provider Token Cost Tradeoffs for DeepSeek V4 Pro

DeepSeek V4 Pro is one of those models where the headline price can mislead you if you don’t check how each provider bills input, output and cache reads separately. All prices are per 1M tokens.

Provider / routeInputOutputCachedAdvantageDisadvantageBest fit
DeepInfra Standard$1.30$2.60$0.10Lowest output price on Artificial Analysis; 0.0% error rate; same rate around the clockCache read is 2–5× some other providers; 65.1 t/s output speedInteractive apps, code generation, agents with real output volume
DeepInfra Flex$1.04$2.08$0.0820% off every line; a request Flex rejects is not chargedWaits up to 10 minutes for capacity, then returns HTTP 429Batch jobs, evals, backfills
DeepInfra Priority$1.95$3.90$0.15Priority capacity when demand peaks1.5× the Standard rateLatency-sensitive production paths
DeepSeek API, peak$1.32$3.96$0.044The model creator’s own API; cheap cache readsHighest output price here; peak runs 01:00–04:00 and 06:00–10:00 UTC on weekdaysCache-heavy traffic during Asian and European business hours
DeepSeek API, off-peak$0.66$1.98$0.022Lowest first-party rate; covers about 79% of the week, including the US Eastern working dayPrice depends on the clock; 500-request concurrency limitScheduled batch work that fits the window
GMI$1.056$3.168$0.035Lowest input price and lowest blended price ($0.55) on Artificial AnalysisOutput costs 22% more than DeepInfraInput-heavy, cache-heavy workloads
DigitalOcean$1.32$3.96$0.044Fastest output (140.0 t/s) and first answer token (31.67 s)3.1% error rate; top-tier output priceLatency-critical user-facing features
Novita$0.99 (OpenRouter) / $1.32 (Artificial Analysis)$2.97 / $3.96$0.033 / $0.044Second-cheapest cost per Index task on Artificial Analysis ($1.86); 0.0% error ratePrice differs by routeCache-heavy agent loops
Baseten$1.32$3.96$0.132Second-fastest output (114.2 t/s)Highest cache rate and blended price ($0.75)Speed over cost
OpenRouter$0.10 to $1.98 input across 26 endpointsVaries by endpointVariesOne API key, automatic failover across 20 providersThe provider serving your request sets the price and cache behaviorMulti-provider fallback
Self-hosting (MIT weights)GPU costGPU costn/aFull control; weights are on Hugging FaceA 1.6T-parameter model needs a large multi-GPU cluster and an ops teamVery high, steady volume or strict data residency

Source: Artificial Analysis providers page, OpenRouter (0813), DeepSeek Models & Pricing and the DeepInfra model page, accessed 2026-11-16. Artificial Analysis lists DeepSeek at its peak rate.

Output price is where DeepInfra leads.

  • $2.60 per 1M output tokens is the lowest of the 8 providers Artificial Analysis measures. Six of the eight charge $3.96, and GMI charges $3.168.
  • Output is the expensive line for a verbose reasoning model, so this gap compounds: at 100M output tokens a month, $2.60 vs $3.96 is $136.
  • OpenRouter does list a few cheaper output routes, mostly at DeepSeek’s off-peak rate (around $1.98), plus Alibaba at $1.742 and Baidu at $1.976.

Cached input is where DeepInfra does not lead.

  • DeepInfra’s $0.10 cache read is a 92% discount on its own input rate, but DeepSeek, DigitalOcean, Novita and SiliconFlow charge $0.044, Nebius $0.04 and GMI $0.035.
  • That is why DeepInfra places 5th of 8 on Artificial Analysis’s cost per Index task ($2.98), a cache-heavy agentic run. DeepSeek ($1.77) and Novita ($1.86) lead it.
  • Flex narrows the cache gap ($0.08) and widens the output lead ($2.08). If more than a small share of your bill is output, DeepInfra usually comes out ahead anyway; Scenario 1 below shows the break-even.

DeepSeek’s peak and off-peak pricing changes the comparison.

  • At peak, DeepSeek’s first-party API costs more than DeepInfra on input ($1.32 vs $1.30) and much more on output ($3.96 vs $2.60).
  • Off-peak, it costs half its peak rate: $0.66 input and $1.98 output, below DeepInfra Standard and Flex on raw tokens.
  • Peak covers seven hours on weekdays (01:00–04:00 and 06:00–10:00 UTC). Everything else is off-peak, so a US team may find much of its traffic already falls in the cheaper window.

Practical rule of thumb for DeepSeek V4 Pro billing

  • If you generate long answers, code or reasoning traces: output price matters most, and DeepInfra’s $2.60 (or $2.08 on Flex) is the lowest on Artificial Analysis.
  • If you resend large prompts and generate little: cache-read price matters most, and the $0.022–$0.044 providers win.
  • If your jobs can wait: use DeepInfra Flex, or schedule them into DeepSeek’s off-peak window and compare.
  • If you use OpenRouter: check which provider is actually serving your request, because price and cache support vary by provider.

Cost trap to avoid: comparing providers on blended price alone. The 7:2:1 blend assumes 70% of your tokens are cache hits. If your app is output-heavy, the provider with the lowest blended price can be the most expensive one on your invoice.

Reasoning Effort and Output Token Cost

0813 replaces the preview’s three prompt-based modes with one parameter, reasoning_effort, which takes low, high or max. DeepSeek describes low for simple tasks, high for daily agent workflows and max for complex tasks. On DeepInfra you can also send "none" to switch thinking off.

Reasoning tokens bill at the same rate as the final answer: $2.60 per 1M on DeepInfra Standard, $2.08 on Flex. A max request can cost several times what the same prompt costs at low. Artificial Analysis measured 119M output tokens at Max against 98.4M at High, about 21% more for one setting change.

If your app defaults to high effort for every request, check that the task needs it. Classification, extraction and short-answer tasks rarely benefit from max. Here is a batch-friendly request that sets effort, caps output and uses Flex:

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["DEEPINFRA_API_KEY"],
    base_url="https://api.deepinfra.com/v1/openai",
)

response = client.chat.completions.create(
    model="deepseek-ai/DeepSeek-V4-Pro-0813",
    messages=[{"role": "user", "content": "Summarize this contract clause in three bullets: ..."}],
    max_tokens=4096,
    extra_body={
        "reasoning_effort": "low",
        "service_tier": "flex",
    },
)
print(response.choices[0].message.content)
copy

Drop "service_tier": "flex" for Standard pricing, or set it to "priority" for the Priority tier. The API reference lists every parameter.

Choosing Between DeepSeek V4 Pro 0813 and V4.1 Flash

DeepSeek V4 Pro is the largest model in the V4 family. It is no longer the top scorer, though. On Artificial Analysis’s Intelligence Index, DeepSeek V4.1 Flash 1017 scores 33 against 23 for V4 Pro 0813 (Max), and Artificial Analysis now calls V4.1 Flash DeepSeek’s flagship. V4.1 Flash costs $0.20 input and $0.60 output per 1M tokens on DeepInfra and accepts image input, which V4 Pro does not.

Use V4 Pro 0813 when your own evals show it does better on your tasks, for example on the long agentic coding runs where DeepSeek’s vendor-reported gains are largest. Otherwise, test V4.1 Flash first. The DeepSeek V4.1 Flash pricing guide has the full cost breakdown.

DeepInfra: the power user’s choice for DeepSeek V4 Pro

DeepInfra combines straightforward token pricing with infrastructure built for production. The platform runs on bare-metal infrastructure, which removes a layer of virtualization overhead that can affect both performance consistency and cost. Standard pricing is $1.30 per 1M input tokens, $2.60 per 1M output tokens and $0.10 per 1M cached tokens, with Flex and Priority tiers for jobs that need a lower price or faster service.

Model / listingBest use caseContext windowInput price (per 1M)Output price (per 1M)
DeepSeek-V4-Pro-0813 (Standard)Reasoning, coding and agent workflows1M$1.30$2.60
DeepSeek-V4-Pro-0813 (Flex)Batch jobs, evals, backfills1M$1.04$2.08
DeepSeek-V4-Pro-0813 (Priority)Latency-sensitive production paths1M$1.95$3.90

The model runs at fp8 with a 1M-token context window and up to 384K output tokens. It supports JSON mode, structured output, function calling and reasoning control. The API is OpenAI-compatible: point your client at https://api.deepinfra.com/v1/openai, call /chat/completions and authenticate with Authorization: Bearer $DEEPINFRA_API_KEY. DeepInfra applies a zero-retention policy, holds SOC 2 and ISO 27001 certification, and offers private deployments when you need dedicated capacity.

Why this matters: on the $1.32 / $3.96 rate most Artificial Analysis providers list, every 1M output tokens costs $1.36 more than on DeepInfra. For a reasoning model that writes long answers, that difference is most of the bill.

On speed, DeepInfra’s endpoint measured 65.1 tokens per second and 2.17 seconds to first token on Artificial Analysis, mid-to-low in the field, so pick DigitalOcean or Baseten if raw throughput decides it. DeepInfra’s 0.0% error rate means fewer retries, and retries are output tokens you pay for twice. Teams comparing options across the broader model catalog can run V4 Pro and its lighter siblings on the same account and bill.

Real-World Cost Scenarios for Developers

Below are five developer scenarios with monthly costs on DeepInfra, using Standard rates ($1.30 / $2.60 / $0.10) unless a scenario says otherwise. DeepInfra is not the cheapest route in every one of them, and each scenario says when it isn’t. Each one also prices the same workload on another route, using DeepSeek’s first-party API at its peak rate or the $1.32 / $3.96 rate that six of Artificial Analysis’s eight providers list.

Scenario 1: RAG support bot with a large repeated knowledge prefix

If you are building a support copilot or internal docs assistant, you resend the same long system prompt, retrieval scaffold and tool instructions on every request. Caching is the main lever here, so this is the scenario where DeepInfra’s cache rate matters most. Our guide to prompt hygiene for cheaper, faster LLM calls covers how to keep that prefix cacheable.

Assumptions: 1,000 requests per month; 80,000 input tokens per request, of which 60,000 are cached and 20,000 bill at the normal input rate; 4,000 output tokens per request.

VolumeModelProviderInput tokensOutput tokensMonthly cost
1,000 requestsDeepSeek-V4-Pro-0813DeepInfra20M standard + 60M cached4M$42.40

Cost breakdown

  • Standard input: 20M × $1.30/1M = $26.00
  • Cached input: 60M × $0.10/1M = $6.00
  • Output: 4M × $2.60/1M = $10.40
  • Total: $42.40/month

Why DeepInfra fits: the cache discount cuts the 60M repeated tokens from $78.00 to $6.00, and the low output rate keeps answers cheap. JSON mode and function calling cover structured retrieval and tool use. On Flex, the same month costs $33.92.

Same workload on DeepSeek’s API at peak rates: 20M × $1.32 + 60M × $0.044 + 4M × $3.96 = $26.40 + $2.64 + $15.84 = $44.88, or $2.48 more than DeepInfra. DeepSeek’s cache line is $3.36 cheaper, but its output line costs $5.44 more. With a higher cache share and shorter answers, DeepSeek would win this scenario.

Scenario 2: Code review and patch generation assistant

For a coding assistant that reads diffs, repository context and issue text, then emits structured review comments or patch suggestions, DeepSeek-V4-Pro-0813 is attractive on capability alone. DeepInfra makes it easy to run that workload with predictable pricing and tool-friendly output.

Assumptions: 10,000 requests per month; 12,000 input tokens and 2,000 output tokens per request.

VolumeModelProviderInput tokensOutput tokensMonthly cost
10,000 requestsDeepSeek-V4-Pro-0813DeepInfra120M20M$208.00

Cost breakdown

  • Input: 120M × $1.30/1M = $156.00
  • Output: 20M × $2.60/1M = $52.00
  • Total: $208.00/month

Why DeepInfra fits: DeepSeek reports 0813 at 62.7 on DeepSWE and 61.5 on NL2Repo (vendor-reported), up from 12.8 and 38.5 for the preview, which is the profile code-assistant builders want. JSON mode keeps review findings in a stable schema, and function calling lets the assistant trigger CI checks or repo lookups.

Same workload at $1.32 / $3.96: 120M × $1.32 + 20M × $3.96 = $158.40 + $79.20 = $237.60, or $29.60 more than DeepInfra.

Scenario 3: Agent workflow with persistent tool schemas and system instructions

Agent systems pay an invisible tax: they keep resending the same policy text, tool definitions and orchestration instructions. As DeepInfra’s role as a Hugging Face Inference Provider shows, chat completion on open-weight LLMs like DeepSeek V4 Pro is a first-class workload on the platform.

Assumptions: 50,000 requests per month; 10,000 input tokens per request (6,000 cached, 4,000 standard); 1,000 output tokens per request.

VolumeModelProviderInput tokensOutput tokensMonthly cost
50,000 requestsDeepSeek-V4-Pro-0813DeepInfra200M standard + 300M cached50M$420.00

Cost breakdown

  • Standard input: 200M × $1.30/1M = $260.00
  • Cached input: 300M × $0.10/1M = $30.00
  • Output: 50M × $2.60/1M = $130.00
  • Total: $420.00/month

Why DeepInfra fits: this is the classic agent loop with repeated scaffolding. Function calling and structured output are supported, and DeepSeek reports 74.1 on Toolathlon-Verified for 0813 (vendor-reported). A 0.0% error rate matters more here than anywhere else, because a failed step in a multi-step agent run wastes every token before it. Moving this job to Flex brings it to $336.00.

Same workload on DeepSeek’s API at peak rates: 200M × $1.32 + 300M × $0.044 + 50M × $3.96 = $264.00 + $13.20 + $198.00 = $475.20, or $55.20 more. DeepSeek’s cache line costs $16.80 less than DeepInfra’s; its output line costs $68.00 more.

Scenario 4: Batch document analysis on Flex vs DeepSeek off-peak

Contract review, research summarization and policy extraction rarely need an answer in seconds. They can run overnight, which opens up two cheaper options: DeepInfra Flex and DeepSeek’s off-peak rate. This scenario compares both, on two batch shapes.

Assumptions (4a, document extraction): 2,000 documents per month; 100,000 input tokens and 5,000 output tokens per document; no caching. Assumptions (4b, generation-heavy batch): 20,000 jobs per month, such as synthetic data or test generation; 3,000 input tokens and 6,000 output tokens per job.

VolumeModelRouteInput tokensOutput tokensMonthly cost
4a: 2,000 docsDeepSeek-V4-Pro-0813DeepInfra Standard200M10M$286.00
4a: 2,000 docsDeepSeek-V4-Pro-0813DeepInfra Flex200M10M$228.80
4a: 2,000 docsDeepSeek V4 ProDeepSeek API, off-peak200M10M$151.80
4b: 20,000 jobsDeepSeek-V4-Pro-0813DeepInfra Standard60M120M$390.00
4b: 20,000 jobsDeepSeek-V4-Pro-0813DeepInfra Flex60M120M$312.00
4b: 20,000 jobsDeepSeek V4 ProDeepSeek API, off-peak60M120M$277.20

Cost breakdown, 4a (document extraction)

  • DeepInfra Standard: 200M × $1.30 + 10M × $2.60 = $260.00 + $26.00 = $286.00
  • DeepInfra Flex: 200M × $1.04 + 10M × $2.08 = $208.00 + $20.80 = $228.80
  • DeepSeek off-peak: 200M × $0.66 + 10M × $1.98 = $132.00 + $19.80 = $151.80

Cost breakdown, 4b (generation-heavy)

  • DeepInfra Standard: 60M × $1.30 + 120M × $2.60 = $78.00 + $312.00 = $390.00
  • DeepInfra Flex: 60M × $1.04 + 120M × $2.08 = $62.40 + $249.60 = $312.00
  • DeepSeek off-peak: 60M × $0.66 + 120M × $1.98 = $39.60 + $237.60 = $277.20

What the numbers say: on raw token price, DeepSeek’s off-peak rate wins both batches. How much depends on the shape. On input-heavy extraction (4a), off-peak is $77.00 below Flex, because its input rate ($0.66) is well under Flex’s ($1.04). On output-heavy generation (4b), the gap shrinks to $34.80, because Flex’s output rate ($2.08) is within 5% of off-peak’s ($1.98). Run either batch during DeepSeek’s peak hours and it costs $303.60 (4a) or $554.40 (4b), more than DeepInfra Standard.

Why DeepInfra Flex still fits: Flex prices are the same at any hour, so you don’t have to fit jobs into a time window or re-plan around holidays. A request Flex can’t place within 10 minutes returns a 429 and is not charged. You also keep DeepInfra’s zero-retention policy, SOC 2 and ISO 27001, and one bill across every model you run. If none of that matters and your batches fit the off-peak window, DeepSeek’s API is the cheaper route for this job.

Scenario 5: Private enterprise deployment for internal engineering tools

Sometimes the main advantage is not raw throughput. It is running the model in a controlled setup while keeping pricing easy to forecast. Here DeepInfra’s compliance posture and private deployment option count for more than a leaderboard position.

Assumptions: 25,000 requests per month; 8,000 input tokens and 1,500 output tokens per request.

VolumeModelProviderInput tokensOutput tokensMonthly cost
25,000 requestsDeepSeek-V4-Pro-0813DeepInfra200M37.5M$357.50

Cost breakdown

  • Input: 200M × $1.30/1M = $260.00
  • Output: 37.5M × $2.60/1M = $97.50
  • Total: $357.50/month

Why DeepInfra fits: internal copilots, secure workflow assistants and engineering automation need zero retention, SOC 2 and ISO 27001, which DeepInfra has. JSON mode and function calling carry over to production integrations, and a private deployment is available if you need dedicated capacity. If part of this traffic is latency-sensitive, Priority runs the same month at $536.25.

Same workload at $1.32 / $3.96: 200M × $1.32 + 37.5M × $3.96 = $264.00 + $148.50 = $412.50, or $55.00 more than DeepInfra.

Monthly Cost Summary Across Scenarios

ScenarioMonthly requestsDeepInfra StandardDeepInfra FlexComparison routePrimary cost driver
1. RAG support bot1,000$42.40$33.92$44.88 (DeepSeek peak)Cached input
2. Code review assistant10,000$208.00$166.40$237.60 ($1.32 / $3.96)Input and output volume
3. Agent workflow50,000$420.00$336.00$475.20 (DeepSeek peak)Cache at scale, output
4a. Batch document extraction2,000$286.00$228.80$151.80 (DeepSeek off-peak)Input volume
4b. Batch generation20,000$390.00$312.00$277.20 (DeepSeek off-peak)Output volume
5. Private enterprise tools25,000$357.50$286.00$412.50 ($1.32 / $3.96)Output volume, compliance

What these scenarios say about DeepInfra

  • Output price drives the wins. In every interactive scenario, DeepInfra beats the $3.96-output routes because of its $2.60 output rate, even where its cache rate is higher.
  • Cache-heavy, low-output traffic is the exception. Scenario 1 is close ($2.48) because DeepSeek’s $0.044 cache read nearly offsets DeepInfra’s output advantage. Push the cache share higher and DeepSeek wins.
  • Flex takes 20% off everything. It is the easiest saving in this guide: one request field, no time windows.
  • DeepSeek off-peak is cheapest for schedulable batches. Flex comes within about 12% on output-heavy jobs but trails by about half on input-heavy ones.
  • Reliability and compliance aren’t on the token price sheet. A 0.0% error rate, zero retention and SOC 2 / ISO 27001 are why teams pick DeepInfra when the per-token prices are close.

Conclusion

Picking a provider for DeepSeek V4 Pro 0813 comes down to matching its pricing to how your workload behaves. The model is the same wherever you run it. What differs is how you pay for its output, its cache reads and the hours you run it.

Three criteria matter most. First, output price: 0813 is a verbose reasoning model, and DeepInfra’s $2.60 per 1M output tokens is the lowest among the providers Artificial Analysis measures. Second, cache rate: if your app is mostly repeated context with short answers, providers charging $0.022–$0.044 for cache reads will undercut DeepInfra’s $0.10, so run the numbers for your traffic. Third, timing: anything that can wait should go to DeepInfra Flex ($1.04 / $2.08), or into DeepSeek’s off-peak window if the schedule and its 500-request concurrency limit suit you.

DeepInfra also covers what matters past the prototype: SOC 2 and ISO 27001, zero retention, private deployments, Priority capacity and a 0.0% measured error rate. If V4 Pro is more model than a task needs, DeepSeek V4.1 Flash 1017 scores higher on Artificial Analysis at a fraction of the price.

Start with DeepInfra and run your real prompt mix: the DeepSeek-V4-Pro-0813 model page has a demo, and the API reference shows every parameter. For speed and latency by provider, see the DeepSeek V4 Pro API benchmarks; for a ranked list, see the best DeepSeek V4 API providers.

Frequently Asked Questions

How much does DeepSeek V4 Pro cost on DeepInfra?

DeepSeek-V4-Pro-0813 costs $1.30 per 1M input tokens, $2.60 per 1M output tokens and $0.10 per 1M cached input tokens on DeepInfra’s Standard tier. Flex costs $1.04 / $2.08 / $0.08 and Priority costs $1.95 / $3.90 / $0.15. Pricing as of 2026-11-16.

What is DeepSeek V4 Pro 0813?

It is the GA release of DeepSeek V4 Pro, published by DeepSeek on August 13, 2026. It keeps the preview’s architecture and 1M context, adds a three-level reasoning_effort setting (low, high, max) and a built-in speculative decoding module, and posts large vendor-reported gains on agentic and coding benchmarks. On DeepInfra its model ID is deepseek-ai/DeepSeek-V4-Pro-0813.

Is DeepSeek’s own API cheaper than DeepInfra for V4 Pro?

It depends on the time of day. At peak (01:00–04:00 and 06:00–10:00 UTC on weekdays), DeepSeek charges $1.32 input and $3.96 output, so DeepInfra is cheaper on both. Off-peak, DeepSeek charges $0.66 and $1.98, below DeepInfra Standard and Flex. DeepSeek’s cache reads ($0.044 peak, $0.022 off-peak) are cheaper than DeepInfra’s at any hour.

Is DeepInfra cheaper than OpenRouter for DeepSeek V4 Pro?

It depends on which provider OpenRouter routes your request to. OpenRouter lists 26 endpoints for the 0813 model, including DeepInfra’s own Standard, Flex and Priority endpoints at the same prices. A few routes have lower output prices, mostly at DeepSeek’s off-peak rate. Most charge more for output than DeepInfra.

Does DeepSeek V4 Pro support prompt caching?

Yes. DeepInfra bills cached input at $0.10 per 1M tokens, 92% off its standard input rate. Several other providers charge less for cache reads, from $0.022 to $0.044 per 1M.

What is the context window and max output for DeepSeek V4 Pro?

The context window is 1,048,576 tokens (1M). On DeepInfra, a single response can run to 384K tokens; if you don’t set max_tokens, the default is 65,536.

Is DeepSeek V4 Pro open source?

Yes. DeepSeek releases V4 Pro under the MIT license, with commercial use allowed. The 0813 weights are on Hugging Face.

Does DeepInfra retain my data when I use DeepSeek V4 Pro?

No. DeepInfra applies a zero-retention policy: request data is not stored after the response is returned.

Related articles
Kimi K2.6 is Now Available on DeepInfraKimi K2.6 is Now Available on DeepInfra<p>Kimi K2.6 can coordinate up to 300 sub-agents executing 4,000 steps in a single autonomous run — Moonshot AI&#8217;s answer to the gap between what frontier models can do in a chat window and what production agentic systems actually need. Built for long-horizon coding, deep research, and complex orchestration, the model is open source under [&hellip;]</p>
NVIDIA Nemotron API Pricing Guide 2026NVIDIA Nemotron API Pricing Guide 2026<p>While everyone knows Llama 3 and Qwen, a quieter revolution has been happening in NVIDIA&#8217;s labs. They have been taking standard Llama models and &#8220;supercharging&#8221; them using advanced alignment techniques and pruning methods. The result is Nemotron—a family of models that frequently tops the &#8220;Helpfulness&#8221; leaderboards (like Arena Hard), often beating GPT-4o while being significantly [&hellip;]</p>
Accelerating Reasoning Workflows with Nemotron 3 Nano on DeepInfraAccelerating Reasoning Workflows with Nemotron 3 Nano on DeepInfraDeepInfra is an official launch partner for NVIDIA Nemotron 3 Nano, the newest open reasoning model in the Nemotron family. Our goal is to give developers, researchers, and teams the fastest and simplest path to using Nemotron 3 Nano from day one.