Prices per 1M tokens. A dash means no single price is listed.

API prices by model
ModelInputCache readOutputCapability (Epoch AI)
DeepSeek V4 Flash 0731Compare DeepSeek V4 Flash 0731 across 3 providers$0.06No single price$0.18Strong · 154.4

Rates, billing conditions and sources

DeepSeek V4 Flash 0731

Model ID: deepseek-ai/DeepSeek-V4-Flash-0731 · Context window: 1.04M tokens

All rates, conditions and sources

Conditions of every rate below:

  • DeepInfra public models API (api.deepinfra.com/models/list) cents_per_input_token / cents_per_output_token, converted exactly to USD per 1M tokens (cents per token × 10,000).
  • Model "deepseek-ai/DeepSeek-V4-Flash-0731" (the DeepInfra API model ID), listed as text-generation with token pricing and no discount, display-price override or deprecation at observation. The API states no region, endpoint or account eligibility.
  • Cached-input, cache-write, priority and flex fields exist in the API, but their units are undocumented, so no cache, priority or flex rate is published; missing cache prices are unknown, not zero. Batch, dedicated deployments and other DeepInfra products are out of scope.

Input: $0.06 per 1M tokens · Standard tier

  • Input tokens (cents_per_input_token).

Output: $0.18 per 1M tokens · Standard tier

  • Output tokens (cents_per_output_token).

Capability (Epoch AI): ECI 154.4 (90% range 152.6–156.4) · Epoch AI score for DeepSeek V4 Flash 0731, model dated Jul 31, 2026

Context window: 1,048,576 tokens

Price observed:

API availability: listed as available when checked (not a live service check)

Collection record

Raw API evidence ↗ · provider API · Claims: deepinfra-deepseek-v4-flash-0731: specifications · Retrieved · Checked · Reviewed · Freshness: unknown · Confidence: A

  • Official DeepInfra models API (https://api.deepinfra.com/models/list, raw SHA-256 7a28435c54ab95337f16d4b9653cd9d228910afa7f72c23504a0394876712f0b): the entry "model_name":"deepseek-ai/DeepSeek-V4-Flash-0731" has "max_tokens":1048576. DeepInfra's OpenAPI (https://api.deepinfra.com/openapi.json, raw SHA-256 3afd821882d88e460fd24c267a5f017a1421e90462ece904e8463320d4286c06, fetched 2026-10-14T01:51:46Z) defines this field of ModelOut, the /models/list item, as "The maximum context size of this model, if applicable". The model page (https://deepinfra.com/deepseek-ai/DeepSeek-V4-Flash-0731, raw SHA-256 8891dd9dfe798909dc94cce6369b5245f72961ea47a10cea259943dbb9b0b08a, fetched 2026-10-14T01:52:00Z) shows 1,048,576 in the chip labelled "Maximum Context Size (Input + Output)". This is DeepInfra's stated maximum context size for this listing; the model's developer and other hosts may state different limits.
  • Specifications only: no pricing, availability, capability or release-date assertion.

Raw API evidence ↗ · provider API · Claims: deepinfra-deepseek-v4-flash-0731: pricing · deepinfra-deepseek-v4-flash-0731: availability · 39 more claims about 20 other catalog entries · Retrieved · Checked · Review due · Confidence: B

  • Raw SHA-256: f7f0c0dbdd453d9ff09c5a14910974add885d38e4efef7f535a9d4fd6c4201dc; collector deepinfra-models-json-1.
  • Hosted listing and pricing observation only: the reviewed text-generation models from the full inventory; no checkpoint, developer, license, context-window, modality or release-date assertions. Like the other hosted providers (OpenRouter, Novita, PPIO, Fireworks AI), offers are not linked to checkpoints.
  • DeepInfra's OpenAPI spec lists this endpoint; cents_per_input_token and cents_per_output_token have titles only and name their own unit (cents per token); the rate_per_* (cache, priority, flex) fields have titles only and no stated unit, so they are not published. Availability rests on DeepInfra's own API listing the model with no deprecation or successor, as for Fireworks AI; a listing with a deprecation date is priced here but cites its own deprecation record for availability.
About capability scores (Epoch AI)

Capability scores: Epoch AI, 'Capabilities & benchmarking'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/benchmarks' [online resource], epoch.ai/benchmarks. Accessed Nov 18, 2026. Licensed CC BY 4.0; values here are rounded to one decimal place and grouped into bands.

The Epoch Capabilities Index (ECI) combines many benchmarks on a scale where Claude 3.5 Sonnet is 130 and GPT-5 is 150. Bands, on the displayed one-decimal score: Frontier 160+, Strong 150–159.9, Capable 140–149.9, Entry below 140. Each score has a 90% range, listed with each model's rates and sources; a range that crosses a band boundary is flagged there. Models are not ranked: neighbouring scores often overlap.

A benchmark is not your workload. Epoch's scores mostly reflect runs at the highest reasoning effort, which use more output tokens than default settings. Scores are dated and can shift between Epoch releases. A score belongs to the developer's model; a host listing shows the same model's score, but hosts may serve different versions or quantizations.

How headline rates are chosen

Headline rates use the directory's shared rule: the rate a buyer meets by default, chosen by billing, tier and context dimensions and never by price. Context caps, the bracket starting at zero and short-context variants are labeled. Every price is a listed price, not a service guarantee; each offer's details say what its source states about availability. Batch, off-peak and other variants remain in the details; where no single rate is the default, the table shows a dash.

No currency conversion is performed. Missing cache prices are unknown, not zero. Equal units do not establish equivalent models or service conditions. See the methodology and source register.