DeepSeek V4 Flash 0731 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 12 hours ago via OpenRouter - some pricing may be stale.
OpenInference - $0.01/M input, $0.28/M output , $0.006/M cache
Per 1M tokens, USD. Verify on the provider's site before committing.
Per-provider pricing
Live per-provider pricing, throughput and uptime - refreshed about 12 hours ago via OpenRouter. Click a column to sort.
some pricing may be stale - last verified 2026-10-09
| Provider | Type | Input $/M | Output $/M | Cache $/M | Tok/s | Latency | Uptime | Value |
|---|---|---|---|---|---|---|---|---|
|
OpenInference
|
API | 0.01 | 0.28 | 0.006 | - | - | 100.00% | best uptime |
|
Relace
|
API | 0.01 | 1.28 | 0.008 | - | - | 100.00% | |
|
Reka
|
API | 0.02 | 0.53 | 0.006 | - | - | 100.00% | |
|
StreamLake
|
API | 0.04 | 0.13 | 0.001 | - | - | 100.00% | |
|
Inceptron
|
API | 0.05 | 0.65 | 0.027 | - | - | 100.00% | |
|
DeepInfra
|
API | 0.06 | 0.18 | 0.015 | - | - | 100.00% | |
|
DigitalOcean
stale
|
API | 0.08 | 0.25 | 0.025 | - | - | - | |
|
Sail Research
|
API | 0.10 | 0.30 | 0.030 | - | - | 100.00% | |
|
Nous Portal
stale
|
API | 0.11 | 0.22 | - | - | - | - | |
|
DigitalOcean
|
API | 0.12 | 0.24 | 0.024 | - | - | 100.00% | |
|
Wafer
|
API | 0.13 | 0.23 | 0.120 | - | - | 100.00% | |
|
BaseTen
|
API | 0.13 | 0.26 | 0.028 | - | - | 100.00% | |
|
CoreWeave
|
API | 0.13 | 0.28 | 0.070 | - | - | 100.00% | |
|
Venice
|
API | 0.13 | 0.26 | 0.028 | - | - | 100.00% | |
|
Together
|
API | 0.14 | 0.28 | 0.030 | - | - | 100.00% | |
|
Parasail
|
API | 0.14 | 0.28 | 0.050 | - | - | 100.00% | |
|
Cohere
|
API | 0.14 | 0.28 | 0.070 | - | - | 100.00% | |
|
Mancer 2
|
API | 0.20 | 0.60 | 0.008 | - | - | 100.00% | |
|
SiliconFlow
|
API | 0.22 | 0.66 | 0.028 | - | - | 100.00% | |
|
GMICloud
|
API | 0.29 | 0.86 | 0.009 | - | - | 100.00% | |
|
Alibaba
|
API | 0.35 | 1.06 | 0.035 | - | - | 100.00% | |
|
Novita
|
API | 0.41 | 1.23 | 0.026 | - | - | 100.00% | |
|
Baidu
|
API | 0.44 | 1.32 | 0.014 | - | - | 100.00% | |
|
Cloudflare
|
API | 0.44 | 1.32 | 0.014 | - | - | 100.00% | |
|
AtlasCloud
|
API | 0.44 | 1.32 | 0.028 | - | - | 100.00% | |
|
Phala
|
API | 0.44 | 1.32 | 0.028 | - | - | 100.00% |
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.
Get this data as JSON
Same provider table, machine-readable. No auth, no rate limit beyond the edge cache.
curl -s https://tokenstead.ai/models/deepseek-v4-flash-0731/pricing.json
JSON: model metadata, cheapest_api, providers[], subscriptions[], verified_at. Unit is USD per 1M tokens.
Estimate what DeepSeek V4 Flash 0731 costs for your workload
Paste your prompt, set requests/day, and see monthly cost against self-hosting on your own GPU.
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.