← Compare all APIs

DeepSeek V4 Flash API prices

Compare routes under the same recorded conditions.

Official pricing source ↗

Compare request billing schedules

2 current routes have qualified request schedules. Prompt length, cache lifetime and search affect costs; base prices are not fixed rates.

deepseek/deepseek-v4-flash-0731 · standard · 2Compare request costs →

Fixed-rate channel comparison

API: deepseek/deepseek-v4-flash-0731 · USD · Standard · fp8 · 1.05M · Global

Reference: 1M input + 1M output tokens; no cache or extras. Not a bill.

2 channels in this scope; start with these 2 price candidates. Configuration is incomplete; equivalent replacement and savings are unverified.

View recorded configuration conditions

Context limit: 1048576

Input/output limits: Unrecorded / 943718

Regions: global

Billing scope: Unrecorded

Parameter declarations: frequency_penalty, include_reasoning, logit_bias, logprobs, max_tokens, presence_penalty, reasoning, reasoning_effort, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs, top_p

Native tool declarations: Source lists no entries

Implicit caching declaration: Yes

Account restriction: Unrecorded

Subroute label: No extra label

These are recorded source fields; actual capability, performance and account access remain unverified.

Change billing and configuration scope
Compare these 2 routes →

Nebius

nebius/fp8

Purchased through OpenRouter

$0.42

1M input + 1M output token subtotal

Input / output per 1M tokens: $0.14 / $0.28

Lowest reference rate in this group; verify output and access.

Use this endpoint
Official API docs ↗

Create a provider API key and set the local environment variable OPENROUTER_API_KEY, then run the example below.

Request URL
https://openrouter.ai/api/v1/chat/completions
Connection settings
Base URL: https://openrouter.ai/api/v1
Catalog model: deepseek/deepseek-v4-flash-0731
Request API model: deepseek/deepseek-v4-flash-0731
Protocol: openai
Provider routing: nebius/fp8
API key env: OPENROUTER_API_KEY
Docs: https://openrouter.ai/docs
curl
curl "https://openrouter.ai/api/v1/chat/completions" -H "Authorization: Bearer $OPENROUTER_API_KEY" -H "Content-Type: application/json" -d '{
  "model": "deepseek/deepseek-v4-flash-0731",
  "messages": [
    {
      "role": "user",
      "content": "Read this support ticket and return a JSON object with \"summary\", \"urgency\" (low, medium, or high), and \"next_step\". Use null for missing details.\n\nTicket: I paid for the Pro plan yesterday, but my account still shows Free. My team needs access before tomorrow’s demo."
    }
  ],
  "provider": {
    "order": [
      "nebius/fp8"
    ],
    "only": [
      "nebius/fp8"
    ],
    "allow_fallbacks": false,
    "quantizations": [
      "fp8"
    ]
  }
}'
Prompt for your coding agent
Use the OpenAI-compatible API at https://openrouter.ai/api/v1 with model "deepseek/deepseek-v4-flash-0731". Set provider.only to ["nebius/fp8"] and allow_fallbacks to false. Apply the recorded quantization filter. A base slug can match multiple endpoints, so confirm the served route before using the reference price. Read the API key from the OPENROUTER_API_KEY environment variable; never hardcode it. Pricing observed on 2026-11-22: $0.14 / 1M input tokens, $0.28 / 1M output tokens, $0.01 / 1M cache read tokens.  API integration docs: https://openrouter.ai/docs. Billing scope and conditions: Served by Nebius through OpenRouter, not a direct-provider contract. Published rates for route nebius/fp8; fp8 quantization. Other fees, tier conditions and regional access must be checked before use.. Source: https://openrouter.ai/api/v1/models/deepseek/deepseek-v4-flash-0731/endpoints.
Task test prompt
Read this support ticket and return a JSON object with "summary", "urgency" (low, medium, or high), and "next_step". Use null for missing details.

Ticket: I paid for the Pro plan yesterday, but my account still shows Free. My team needs access before tomorrow’s demo.
Price facts
Input: $0.14 / 1M tokens
Output: $0.28 / 1M tokens
Cache read: $0.01 / 1M tokens
Currency: USD
Regions: global
Unit source: api
Checked: 2026-11-22T09:20:22.910Z
Source: https://openrouter.ai/api/v1/models/deepseek/deepseek-v4-flash-0731/endpoints

Source check: 2026-11-22 · valid no later than 2026-11-23 09:21 UTC

Billing evidence and sources

deepseek/deepseek-v4-flash-0731 · nebius/fp8

Billing conditions

Served by Nebius through OpenRouter, not a direct-provider contract. Published rates for route nebius/fp8; fp8 quantization. Other fees, tier conditions and regional access must be checked before use.

Cache read / 1M
$0.01
Cache write / 1M
Not published
Per request
Not published
Route
nebius/fp8 · fp8

Declared parameters: frequency_penalty, include_reasoning, logit_bias, logprobs, max_tokens, presence_penalty, reasoning, reasoning_effort, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs, top_p

Price source ↗

Parasail

parasail/fp8

Purchased through OpenRouter

$0.42

1M input + 1M output token subtotal

Input / output per 1M tokens: $0.14 / $0.28

Alternative route in this group; price does not establish service performance.

Use this endpoint
Official API docs ↗

Create a provider API key and set the local environment variable OPENROUTER_API_KEY, then run the example below.

Request URL
https://openrouter.ai/api/v1/chat/completions
Connection settings
Base URL: https://openrouter.ai/api/v1
Catalog model: deepseek/deepseek-v4-flash-0731
Request API model: deepseek/deepseek-v4-flash-0731
Protocol: openai
Provider routing: parasail/fp8
API key env: OPENROUTER_API_KEY
Docs: https://openrouter.ai/docs
curl
curl "https://openrouter.ai/api/v1/chat/completions" -H "Authorization: Bearer $OPENROUTER_API_KEY" -H "Content-Type: application/json" -d '{
  "model": "deepseek/deepseek-v4-flash-0731",
  "messages": [
    {
      "role": "user",
      "content": "Read this support ticket and return a JSON object with \"summary\", \"urgency\" (low, medium, or high), and \"next_step\". Use null for missing details.\n\nTicket: I paid for the Pro plan yesterday, but my account still shows Free. My team needs access before tomorrow’s demo."
    }
  ],
  "provider": {
    "order": [
      "parasail/fp8"
    ],
    "only": [
      "parasail/fp8"
    ],
    "allow_fallbacks": false,
    "quantizations": [
      "fp8"
    ]
  }
}'
Prompt for your coding agent
Use the OpenAI-compatible API at https://openrouter.ai/api/v1 with model "deepseek/deepseek-v4-flash-0731". Set provider.only to ["parasail/fp8"] and allow_fallbacks to false. Apply the recorded quantization filter. A base slug can match multiple endpoints, so confirm the served route before using the reference price. Read the API key from the OPENROUTER_API_KEY environment variable; never hardcode it. Pricing observed on 2026-11-22: $0.14 / 1M input tokens, $0.28 / 1M output tokens, $0.05 / 1M cache read tokens.  API integration docs: https://openrouter.ai/docs. Billing scope and conditions: Served by Parasail through OpenRouter, not a direct-provider contract. Published rates for route parasail/fp8; fp8 quantization. Other fees, tier conditions and regional access must be checked before use.. Source: https://openrouter.ai/api/v1/models/deepseek/deepseek-v4-flash-0731/endpoints.
Task test prompt
Read this support ticket and return a JSON object with "summary", "urgency" (low, medium, or high), and "next_step". Use null for missing details.

Ticket: I paid for the Pro plan yesterday, but my account still shows Free. My team needs access before tomorrow’s demo.
Price facts
Input: $0.14 / 1M tokens
Output: $0.28 / 1M tokens
Cache read: $0.05 / 1M tokens
Currency: USD
Regions: global
Unit source: api
Checked: 2026-11-22T09:20:22.910Z
Source: https://openrouter.ai/api/v1/models/deepseek/deepseek-v4-flash-0731/endpoints

Source check: 2026-11-22 · valid no later than 2026-11-23 09:21 UTC

Billing evidence and sources

deepseek/deepseek-v4-flash-0731 · parasail/fp8

Billing conditions

Served by Parasail through OpenRouter, not a direct-provider contract. Published rates for route parasail/fp8; fp8 quantization. Other fees, tier conditions and regional access must be checked before use.

Cache read / 1M
$0.05
Cache write / 1M
Not published
Per request
Not published
Route
parasail/fp8 · fp8

Declared parameters: frequency_penalty, include_reasoning, logit_bias, logprobs, max_tokens, presence_penalty, reasoning, reasoning_effort, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs, top_p

Price source ↗
Compare saved channels →
All quotes, filters and usage tools
History · Billing and conditions

DeepSeek V4 Flash API pricing: official and providers: 33 current published quote records across 3 exact API IDs and 18 providers. Compare API versions, currencies, regions and billing conditions separately; prices do not prove task quality or account access.

Latest recorded source check: 2026-11-22

Recorded changes

Latest 100 recorded price and availability changes
ObservedModel / provider routeChangeInput rateOutput rate

DeepSeek: DeepSeek V4 Flash 0731

Wafer · wafer/fast

Source ↗
Increase$0.13 / 1M tokens → $0.14 / 1M tokens$0.23 / 1M tokens → $0.23 / 1M tokens

DeepSeek: DeepSeek V4 Flash 0731

Wafer · wafer/fast

Source ↗
Decrease$0.14 / 1M tokens → $0.13 / 1M tokens$0.23 / 1M tokens → $0.23 / 1M tokens

DeepSeek: DeepSeek V4 Flash 0731

Alibaba · alibaba

Source ↗
Increase$0.176 / 1M tokens → $0.352 / 1M tokens$0.528 / 1M tokens → $1.056 / 1M tokens

DeepSeek: DeepSeek V4 Flash 0731

Alibaba · alibaba/us-east-1

Source ↗
Increase$0.187 / 1M tokens → $0.374 / 1M tokens$0.561 / 1M tokens → $1.122 / 1M tokens

DeepSeek: DeepSeek V4 Flash 0423

AtlasCloud · atlas-cloud/fp4

Source ↗
Removed

missing → removed

$0.14 / 1M tokens → $0.14 / 1M tokens$0.28 / 1M tokens → $0.28 / 1M tokens

DeepSeek: DeepSeek V4 Flash 0731

Alibaba · alibaba

Source ↗
Decrease$0.352 / 1M tokens → $0.176 / 1M tokens$1.056 / 1M tokens → $0.528 / 1M tokens

DeepSeek: DeepSeek V4 Flash 0731

Alibaba · alibaba/us-east-1

Source ↗
Decrease$0.374 / 1M tokens → $0.187 / 1M tokens$1.122 / 1M tokens → $0.561 / 1M tokens

DeepSeek: DeepSeek V4 Flash 0731

AtlasCloud · atlas-cloud/fp4

Source ↗
Removed

missing → removed

$0.44 / 1M tokens → $0.44 / 1M tokens$1.32 / 1M tokens → $1.32 / 1M tokens

DeepSeek: DeepSeek V4 Flash 0423

Relace · relace/fp4

Source ↗
Decrease$0.0155 / 1M tokens → $0.0138 / 1M tokens$0.45 / 1M tokens → $0.45 / 1M tokens

DeepSeek: DeepSeek V4 Flash 0423

Baidu · baidu/fp8

Source ↗
Decrease$0.0164 / 1M tokens → $0.0146 / 1M tokens$0.0328 / 1M tokens → $0.0291 / 1M tokens

DeepSeek: DeepSeek V4 Flash 0423

GMICloud · gmicloud/fp8

Source ↗
Removed

missing → removed

$0.091 / 1M tokens → $0.091 / 1M tokens$0.182 / 1M tokens → $0.182 / 1M tokens

DeepSeek: DeepSeek V4 Flash 0731

GMICloud · gmicloud/fp8

Source ↗
Removed

missing → removed

$0.286 / 1M tokens → $0.286 / 1M tokens$0.858 / 1M tokens → $0.858 / 1M tokens

DeepSeek: DeepSeek V4 Flash 0423

Relace · relace/fp4

Source ↗
Decrease$0.0419 / 1M tokens → $0.0155 / 1M tokens$0.45 / 1M tokens → $0.45 / 1M tokens

DeepSeek: DeepSeek V4 Flash 0423

Baidu · baidu/fp8

Source ↗
Decrease$0.0448 / 1M tokens → $0.0164 / 1M tokens$0.0896 / 1M tokens → $0.0328 / 1M tokens

DeepSeek: DeepSeek V4 Flash 0423

StreamLake · streamlake/fp8

Source ↗
Decrease$0.0441 / 1M tokens → $0.028 / 1M tokens$0.0882 / 1M tokens → $0.056 / 1M tokens

DeepSeek: DeepSeek V4 Flash 0423

Mancer 2 · mancer/fp8

Source ↗
Increase$0.15 / 1M tokens → $0.18 / 1M tokens$0.50 / 1M tokens → $0.50 / 1M tokens

DeepSeek: DeepSeek V4 Flash 0731

Mancer 2 · mancer/fp8

Source ↗
Billing

Cache, discount or other billing fields

$0.15 / 1M tokens → $0.15 / 1M tokens$0.50 / 1M tokens → $0.50 / 1M tokens

DeepSeek: DeepSeek V4 Flash 0731

Alibaba · alibaba

Source ↗
Increase$0.176 / 1M tokens → $0.352 / 1M tokens$0.528 / 1M tokens → $1.056 / 1M tokens

DeepSeek: DeepSeek V4 Flash 0731

Alibaba · alibaba/us-east-1

Source ↗
Increase$0.187 / 1M tokens → $0.374 / 1M tokens$0.561 / 1M tokens → $1.122 / 1M tokens

DeepSeek: DeepSeek V4 Flash 0731

Cloudflare · cloudflare

Source ↗
Removed

missing → removed

$0.44 / 1M tokens → $0.44 / 1M tokens$1.32 / 1M tokens → $1.32 / 1M tokens

DeepSeek: DeepSeek V4 Flash 0731

Reka · reka

Source ↗
Removed

missing → removed

$0.10 / 1M tokens → $0.10 / 1M tokens$0.42 / 1M tokens → $0.42 / 1M tokens

DeepSeek: DeepSeek V4 Flash 0423

Relace · relace/fp4

Source ↗
Decrease$0.05 / 1M tokens → $0.0419 / 1M tokens$0.45 / 1M tokens → $0.45 / 1M tokens

DeepSeek: DeepSeek V4 Flash 0423

StreamLake · streamlake/fp8

Source ↗
Decrease$0.0826 / 1M tokens → $0.0441 / 1M tokens$0.1652 / 1M tokens → $0.0882 / 1M tokens

DeepSeek: DeepSeek V4 Flash 0423

Baidu · baidu/fp8

Source ↗
Decrease$0.14 / 1M tokens → $0.0448 / 1M tokens$0.28 / 1M tokens → $0.0896 / 1M tokens

DeepSeek: DeepSeek V4 Flash 0423

Fireworks · fireworks

Source ↗
Decrease$0.105 / 1M tokens → $0.07 / 1M tokens$0.21 / 1M tokens → $0.14 / 1M tokens

DeepSeek: DeepSeek V4 Flash 0423

Venice · venice

Source ↗
Increase$0.0966 / 1M tokens → $0.138 / 1M tokens$0.1925 / 1M tokens → $0.275 / 1M tokens

DeepSeek: DeepSeek V4 Flash 0731

Baidu · baidu/fp8

Source ↗
Decrease$0.44 / 1M tokens → $0.044 / 1M tokens$1.32 / 1M tokens → $0.132 / 1M tokens

DeepSeek: DeepSeek V4 Flash 0731

Wafer · wafer/us

Source ↗
Decrease$0.047 / 1M tokens → $0.0443 / 1M tokens$0.30 / 1M tokens → $0.30 / 1M tokens

DeepSeek: DeepSeek V4 Flash 0731

StreamLake · streamlake/fp8

Source ↗
Decrease$0.132 / 1M tokens → $0.088 / 1M tokens$0.396 / 1M tokens → $0.264 / 1M tokens

DeepSeek: DeepSeek V4 Flash 0731

Cohere · cohere/fp8

Source ↗
Decrease$0.14 / 1M tokens → $0.11 / 1M tokens$0.28 / 1M tokens → $0.22 / 1M tokens

DeepSeek: DeepSeek V4 Flash 0731

Alibaba · alibaba

Source ↗
Decrease$0.352 / 1M tokens → $0.176 / 1M tokens$1.056 / 1M tokens → $0.528 / 1M tokens

DeepSeek: DeepSeek V4 Flash 0731

Alibaba · alibaba/us-east-1

Source ↗
Decrease$0.374 / 1M tokens → $0.187 / 1M tokens$1.122 / 1M tokens → $0.561 / 1M tokens

DeepSeek: DeepSeek V4 Flash 0731

Novita · novita/fp8

Source ↗
Increase$0.4092 / 1M tokens → $0.418 / 1M tokens$1.2276 / 1M tokens → $1.254 / 1M tokens

DeepSeek: DeepSeek V4 Flash 0423

StreamLake · streamlake/fp8

Source ↗
Increase$0.07 / 1M tokens → $0.0826 / 1M tokens$0.14 / 1M tokens → $0.1652 / 1M tokens

DeepSeek: DeepSeek V4 Flash 0423

Baidu · baidu/fp8

Source ↗
Increase$0.05 / 1M tokens → $0.14 / 1M tokens$0.10 / 1M tokens → $0.28 / 1M tokens

DeepSeek: DeepSeek V4 Flash 0731

Wafer · wafer/us

Source ↗
Increase$0.0434 / 1M tokens → $0.047 / 1M tokens$0.30 / 1M tokens → $0.30 / 1M tokens

DeepSeek: DeepSeek V4 Flash 0731

Nebius · nebius/fp8

Source ↗
Restored

removed → active

$0.14 / 1M tokens → $0.14 / 1M tokens$0.28 / 1M tokens → $0.28 / 1M tokens

DeepSeek: DeepSeek V4 Flash 0731

Alibaba · alibaba

Source ↗
Increase$0.176 / 1M tokens → $0.352 / 1M tokens$0.528 / 1M tokens → $1.056 / 1M tokens

DeepSeek: DeepSeek V4 Flash 0731

Alibaba · alibaba/us-east-1

Source ↗
Increase$0.187 / 1M tokens → $0.374 / 1M tokens$0.561 / 1M tokens → $1.122 / 1M tokens

DeepSeek: DeepSeek V4 Flash 0731

Baidu · baidu/fp8

Source ↗
Increase$0.0898 / 1M tokens → $0.44 / 1M tokens$0.2693 / 1M tokens → $1.32 / 1M tokens

Showing up to 100 recent events. Prices for unavailable endpoints are retained for reference. Failed source checks do not establish that a price stayed unchanged.

Open a quote’s billing details for cache reads/writes, request fees and endpoint instructions. Batch, free, promotional and off-peak tiers are selected separately. Context-tier, storage, search, tax and platform fees may be excluded.

Find lower-cost alternatives

Find lower-cost alternatives

Choose your existing model to find lower reference costs with matching declared technical constraints. Output quality remains unverified.

Loading verified quotes…

Users’ choices · DeepSeek V4 Flash

Describe your work to find related tasks.

Public scores by use

The same model scores differently by use. Once you pick a use, the site applies that use’s quality gate before comparing cost.

Text

  • Answer from sources143951170 votes · 2026-11-19
  • Chinese14702928 votes · 2026-11-19
  • Classify142817672 votes · 2026-11-19
  • Extract fields142817672 votes · 2026-11-19
  • General text143651238 votes · 2026-11-19
  • Multi-turn14539257 votes · 2026-11-19
  • Summarize144822900 votes · 2026-11-19
  • Translate & rewrite142328439 votes · 2026-11-19
  • Write14078409 votes · 2026-11-19

Code & tools

  • Code148415083 votes · 2026-11-19
  • Web & frontend15824803 votes · 2026-11-20

Industry

  • Business & finance143810253 votes · 2026-11-19
  • Legal & government14484056 votes · 2026-11-19
  • Medical & health14593605 votes · 2026-11-19

Scores come from Arena public-preference leaderboards (CC BY 4.0), latest published 2026-11-20. They describe the model, not your task’s success rate or a quantized channel. Arena ↗

View independent evaluation on Artificial Analysis ↗ · external link; we do not copy its scores or prices.

Declared model facts

Declared fields from the OpenRouter model catalog, bound to exact API IDs; not our tests, price approval or account availability.

Input
Text
Output
Text
Context
1.05M
Reasoning parameter
Supported
Knowledge cutoff
Not declared
Open-weights clue
deepseek-ai/DeepSeek-V4-Flash
Per-API facts · 3 versions
  • deepseek/deepseek-v4-flash · text → text · 1.05M · reasoning
  • deepseek/deepseek-v4-flash-0731 · text → text · 1.05M · reasoning
  • deepseek/deepseek-v4-flash-0731:batch · text → text · 1.05M · reasoning

Source: https://openrouter.ai/api/v1/models, captured 2026-11-21T09:20:20.905Z, raw SHA-256: 19214ba490361282… . Unstated facts stay unknown and are not inferred from names or sibling models.

Classification sources

Source declarations for registered versions; not task quality, current account availability or price approval. Unknown versions do not inherit sibling classifications.

Model variants

Snapshots and routing variants remain distinct. Choose an exact ID in the comparison before deciding; model quality and access conditions need your own review.

More from this maker

DeepSeek →