DeepSeek V4.1 Flash API pricing

26 providers serve DeepSeek V4.1 Flash. DeepSeek V4.1 Flash is a proprietary API model, up to 1049K context. Prices below are per 1M tokens, cheapest input first.

Refreshed 2026-11-22 · list prices from provider APIs
Input floor $0.010/1M at Coralbricks Output floor $0.199/1M at OpenRouter Find your workload winner →
Provider Input $/1M Output $/1M Cache read $/1M Context
Coralbricks $0.010 $1.20 - 1049K
OpenRouter marketplace quote $0.050 $0.199output floor $0.0010 1049K Use
Sail $0.090 $0.300 $0.0060 1049K
Clf AI Gateway $0.120 $0.480 $0.0020 1049K
W&B Inference $0.130 $0.650 $0.0020 1049K Use
DeepInfra $0.140 $0.420 $0.0042 1049K Use
Scx AI $0.150 $0.600 $0.010 1000K
Prism $0.170 $0.630 $0.070 1000K
GMI Cloud $0.180 $0.720 $0.0036 1049K Use
Empiriolabs $0.200 $0.800 $0.020 1000K
Kyma $0.270 $0.810 - 1049K
Mistral AI $0.300 $1.20 $0.0070 1049K Use
Nebius $0.300 $1.20 $0.010 1049K Use
Together AI $0.300 $1.20 $0.0060 1049K Use
Streamlake $0.300 $1.20 $0.0060 1049K
Tencent $0.300 $1.20 $0.0060 1000K
Fireworks AI $0.300 $1.20 $0.0060 1049K Use
Zerogpu $0.300 $1.20 $0.0030 1049K
Azure AI Foundry $0.300 $1.20 $0.0060 1000K Use
Aiand $0.300 $0.600 $0.020 1049K
Baseten $0.300 $1.20 $0.0070 1049K Use
Google Vertex AI $0.300 $1.20 $0.030 1049K Use
Opencode Go $0.300 $1.20 $0.0060 1000K
Databricks $0.300 $1.20 $0.030 1000K Use
Wally $0.300 $1.20 $0.0060 1049K
Inferenceapis $0.400 $1.60 $0.010 1049K

The cheapest way to run DeepSeek V4.1 Flash

On an illustrative 70M-input / 30M-output monthly workload, today's lowest listed cost is roughly $9.46/month, at OpenRouter. Input-heavy, output-heavy and cache-heavy workloads can produce different winners. Use the live mix calculator below rather than combining floors from two different providers. It is API-only, so the table above is your full set of options. Run your own numbers in the breakeven calculator, or read the breakeven math.

Your actual monthly cost

Uses today's list prices

Cache read uses the listed cache rate where available; otherwise it falls back to normal input price. Batch, write-cache, volume and negotiated discounts are excluded.

Related models

ModelCheapest in $/1MCheapest out $/1MProviders
DeepSeek V4 Flash $0.044 $0.149 31
DeepSeek V4 Pro $0.528 $1.20 24
DeepSeek R1 $0.200 $0.400 20
DeepSeek V3 $0.190 $0.200 18
DeepSeek-V3.1 $0.250 $0.950 13
DeepSeek V3.2 $0.260 $0.380 10

FAQ

What is the cheapest API for DeepSeek V4.1 Flash?

As of 2026-11-22, the lowest input price for DeepSeek V4.1 Flash is Coralbricks at $0.010 per 1M input tokens. The lowest output price is OpenRouter at $0.199 per 1M output tokens. The cheapest provider for a real workload depends on its input/output mix. The next-lowest input price is OpenRouter at $0.050, a 398% difference.

← All models · GPU rental prices · Breakeven calculator · Get this data as JSON