Models / DeepSeek V4.1 Flash / API pricing

DeepSeek V4.1 Flash API pricing

Live per-token API pricing across providers, synced from OpenRouter. Compare input, output, and cache-read rates, throughput, latency, and uptime in one place - then estimate what your workload actually costs.

Refreshed about 19 hours ago via OpenRouter.

CHEAPEST PROVIDER

OpenInference - $0.02/M input, $1.00/M output , $0.015/M cache

Per 1M tokens, USD. Verify on the provider's site before committing.

See all providers below

Per-provider pricing

Live per-provider pricing, throughput and uptime - refreshed about 19 hours ago via OpenRouter. Click a column to sort.

Provider Type Input $/M Output $/M Cache $/M Tok/s Latency Uptime Value
OpenInference
API 0.02 1.00 0.015 - - 100.00% best uptime
Baidu
API 0.05 0.21 0.001 - - 100.00%
Relace
API 0.07 0.50 0.008 - - 100.00%
Decart
API 0.09 0.18 0.018 - - 100.00%
Sail Research
API 0.09 0.25 0.006 - - 100.00%
InferenceNet
API 0.10 0.72 0.008 - - 100.00%
AtlasCloud
API 0.14 0.54 0.014 - - 100.00%
StreamLake
API 0.15 0.59 0.003 - - 100.00%
CoreWeave
API 0.15 0.65 0.002 - - 100.00%
DigitalOcean
API 0.16 0.66 0.006 - - 100.00%
ModelRun
API 0.17 0.67 0.006 - - 100.00%
GMICloud
API 0.18 0.72 0.004 - - 100.00%
Novita
API 0.20 0.78 0.004 - - 100.00%
Mancer 2
API 0.20 1.00 0.015 - - 100.00%
Phala
API 0.21 0.84 0.004 - - 100.00%
Wafer
API 0.22 0.65 0.012 - - 100.00%
Makora
API 0.26 1.17 0.006 - - 100.00%
Crusoe
API 0.29 1.20 0.007 - - 100.00%
Nebius
API 0.30 1.20 0.010 - - 100.00%
Modal
API 0.30 1.20 0.030 - - 100.00%
SiliconFlow
API 0.30 1.20 0.006 - - 100.00%
Together
API 0.30 1.20 0.006 - - 100.00%
Parasail
API 0.30 1.20 0.006 - - 100.00%
Venice
API 0.30 1.20 0.008 - - 100.00%
Cohere
API 0.30 1.20 0.003 - - 100.00%
PrimeIntellect
API 0.30 1.20 0.006 - - 100.00%
Google
API 0.30 1.20 0.030 - - 100.00%
Alibaba
API 0.33 1.32 0.033 - - 100.00%
Fireworks
API 0.45 1.80 0.009 - - 100.00%
Morph
API 0.48 0.60 0.019 - - 100.00%
BaseTen
API 0.60 2.40 0.014 - - 100.00%
Reka risky
API 0.10 0.84 0.007 - - 91.65%
DeepInfra avoid
API 0.21 0.63 0.006 - - 0.00%
OpenCode Go
Sub - - - - - - $10.00/mo Go ($5 first month)

Default order: throughput among 95%+ uptime providers, then latency; subscriptions last. Sort by any column. Subscription rows show $/mo in the Value column - per-token columns are "-". Affiliate links are marked sponsored / nofollow. Confirm current pricing on the provider's site before committing.

PROGRAMMATIC

Get this data as JSON

Same provider table, machine-readable. No auth, no rate limit beyond the edge cache.

curl -s https://www.tokenstead.ai/models/deepseek-v4-1-flash/pricing.json

JSON: model metadata, cheapest_api, providers[], subscriptions[], verified_at. Unit is USD per 1M tokens.

NEXT STEP

Estimate what DeepSeek V4.1 Flash costs for your workload

Paste your prompt, set requests/day, and see monthly cost against self-hosting on your own GPU.

Open the calculator →
PRICE HISTORY

Inference cost over time

Data accumulates from the first daily sync - longer ranges populate over time. Prices come from OpenRouter snapshots, not a historical API.

Loading price history...