DeepSeek V4.1 Flash pricing across providers
Across tracked provider offerings, input runs $0.030–$0.600 per million tokens and output $0.120–$1.50 per million tokens. The cheapest tracked provider offering for a typical agentic mix (2.5% input, 97% cached input, 0.5% output) is Baidu at $0.0029 per million tokens.
Prices are USD per million tokens and reflect each provider offering — they are not a single intrinsic model price. 48 of 49 offerings publish a cache-read rate; 30 of 49 publish a 30-minute endpoint uptime figure.
Open the calculator filtered to DeepSeek V4.1 Flash
Is this the right model for your workload? Compare open-weight picks and providers for your use case →
Daily price history
Loading price history…
Daily snapshots are retained for up to 90 days; history begins with the first recorded snapshot.
Provider offerings for DeepSeek V4.1 Flash
Ranked by effective cost at a typical agentic mix. Quantized and tier variants stay separate rows.
| Provider | Quant | Input $/M | Output $/M | Cache $/M | Blended $/M | Uptime (30m) |
|---|---|---|---|---|---|---|
| Baidu promo | fp8 | $0.045 | $0.179 | $0.0009 | $0.0029 | 100.00% |
| Openscale | — | $0.060 | $0.240 | $0.0030 | $0.0056 | — |
| Morph | fp8 | $0.044 | $0.383 | $0.0040 | $0.0069 | 100.00% |
| Engy | — | $0.030 | $0.120 | $0.0060 | $0.0072 | — |
| Avian | — | $0.128 | $0.510 | $0.0026 | $0.0082 | — |
| Coreweave | fp8 | $0.130 | $0.650 | $0.0020 | $0.0084 | 100.00% |
| Singularity | — | $0.130 | $0.500 | $0.0030 | $0.0087 | — |
| Luminal | — | $0.135 | $0.540 | $0.0027 | $0.0087 | — |
| Sail Research | fp4 | $0.090 | $0.250 | $0.0060 | $0.0093 | 100.00% |
| Streamlake promo | fp8 | $0.147 | $0.588 | $0.0029 | $0.0095 | 100.00% |
| Consensusprotocol | — | $0.150 | $0.550 | $0.0050 | $0.011 | — |
| GMI Cloud promo | fp8 | $0.180 | $0.720 | $0.0036 | $0.012 | 100.00% |
| Relace | unknown | $0.070 | $0.500 | $0.0080 | $0.012 | 100.00% |
| Novita promo | fp8 | $0.195 | $0.780 | $0.0039 | $0.013 | 100.00% |
| Inferencenet | fp8 | $0.103 | $0.600 | $0.0080 | $0.013 | 100.00% |
| Fireworks | unknown | $0.210 | $0.840 | $0.0042 | $0.014 | 100.00% |
| Phala promo | unknown | $0.210 | $0.840 | $0.0042 | $0.014 | 100.00% |
| Reka promo | unknown | $0.105 | $0.840 | $0.0070 | $0.014 | 100.00% |
| DeepInfra | — | $0.200 | $0.600 | $0.0060 | $0.014 | — |
| Reka Ai | — | $0.150 | $0.600 | $0.0090 | $0.015 | — |
| Coralbricks | — | $0.190 | $0.600 | $0.0080 | $0.016 | — |
| Digitalocean | unknown | $0.225 | $0.900 | $0.0060 | $0.016 | 100.00% |
| Cohere | unknown | $0.300 | $1.20 | $0.0030 | $0.016 | 100.00% |
| Scx Ai Gp | — | $0.150 | $0.600 | $0.010 | $0.016 | — |
| Runware | — | $0.150 | $0.600 | $0.010 | $0.016 | — |
| Wafer | — | $0.190 | $0.650 | $0.010 | $0.018 | — |
| Makora | fp8 | $0.260 | $1.17 | $0.0058 | $0.018 | 100.00% |
| Atlascloud | fp8 | $0.135 | $0.540 | $0.013 | $0.019 | 100.00% |
| Runanywhere | fp8 | $0.300 | $1.20 | $0.0060 | $0.019 | — |
| Primeintellect | unknown | $0.300 | $1.20 | $0.0060 | $0.019 | 100.00% |
| Together | unknown | $0.300 | $1.20 | $0.0060 | $0.019 | 100.00% |
| SiliconFlow | fp8 | $0.300 | $1.20 | $0.0060 | $0.019 | 100.00% |
| Parasail | fp8 | $0.300 | $1.20 | $0.0060 | $0.019 | 100.00% |
| Arilo | mxfp4 | $0.280 | $0.600 | $0.010 | $0.020 | — |
| Crusoe | fp8 | $0.290 | $1.20 | $0.0070 | $0.020 | 100.00% |
| Baseten | unknown | $0.300 | $1.20 | $0.0070 | $0.020 | 96.67% |
| Decart | fp4 | $0.090 | $0.180 | $0.018 | $0.021 | 100.00% |
| Venice | fp8 | $0.300 | $1.20 | $0.0075 | $0.021 | 96.67% |
| Neuralwatt | — | $0.150 | $0.600 | $0.015 | $0.021 | — |
| Zro | — | $0.300 | $1.10 | $0.010 | $0.023 | — |
| Nebius | fp8 | $0.300 | $1.20 | $0.010 | $0.023 | 100.00% |
| Alibaba | unknown | $0.165 | $0.660 | $0.016 | $0.023 | 100.00% |
| Openinference | fp4 | $0.030 | $1.37 | $0.027 | $0.034 | 100.00% |
| unknown | $0.300 | $1.20 | $0.030 | $0.043 | 100.00% | |
| Modal | unknown | $0.300 | $1.20 | $0.030 | $0.043 | 100.00% |
| Hyper | — | $0.330 | $1.31 | $0.030 | $0.044 | — |
| Sference | — | $0.500 | $1.50 | $0.050 | $0.069 | — |
| Synthetic | — | $0.600 | $1.20 | $0.120 | $0.137 | — |
| Mancer 2 | fp8 | $0.200 | $1.00 | — | $0.204 | 100.00% |
Provider-offering pricing refreshed 2026-10-29. Uptime is the 30-minute endpoint metric where a provider publishes it. Verify rates on the provider's official pricing page before committing spend.