DeepSeek V4 Flash 0423 pricing across providers
Across tracked provider offerings, input runs $0.045–$0.600 per million tokens and output $0.095–$1.32 per million tokens. The cheapest tracked provider offering for a typical agentic mix (2.5% input, 97% cached input, 0.5% output) is Avian at $0.0076 per million tokens.
Prices are USD per million tokens and reflect each provider offering — they are not a single intrinsic model price. 27 of 28 offerings publish a cache-read rate; 16 of 28 publish a 30-minute endpoint uptime figure.
Open the calculator filtered to DeepSeek V4 Flash 0423
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 Flash 0423
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) |
|---|---|---|---|---|---|---|
| Avian | — | $0.140 | $0.280 | $0.0028 | $0.0076 | — |
| Consensusprotocol | — | $0.100 | $0.200 | $0.0050 | $0.0083 | — |
| Singularity | — | $0.081 | $0.162 | $0.0070 | $0.0096 | — |
| Baidu promo | fp8 | $0.047 | $0.095 | $0.0095 | $0.011 | 100.00% |
| Ember | — | $0.065 | $0.129 | $0.013 | $0.015 | — |
| Streamlake promo | fp8 | $0.070 | $0.140 | $0.014 | $0.016 | 100.00% |
| Runware | — | $0.076 | $0.153 | $0.014 | $0.016 | — |
| GMI Cloud promo | fp8 | $0.091 | $0.182 | $0.018 | $0.021 | 100.00% |
| DeepInfra | — | $0.090 | $0.180 | $0.018 | $0.021 | — |
| Makora | — | $0.090 | $0.195 | $0.020 | $0.022 | — |
| Venice promo | unknown | $0.097 | $0.193 | $0.020 | $0.022 | 100.00% |
| Digitalocean | unknown | $0.098 | $0.196 | $0.020 | $0.022 | 100.00% |
| Fireworks | unknown | $0.105 | $0.210 | $0.021 | $0.024 | 79.31% |
| Bytedance | — | $0.440 | $1.32 | $0.014 | $0.031 | — |
| Cloudflare | unknown | $0.440 | $1.32 | $0.014 | $0.031 | 100.00% |
| SiliconFlow | fp8 | $0.130 | $0.280 | $0.028 | $0.032 | 100.00% |
| Neuralwatt | — | $0.140 | $0.280 | $0.028 | $0.032 | — |
| Ranoai | — | $0.140 | $0.280 | $0.028 | $0.032 | — |
| Atlascloud | fp4 | $0.140 | $0.280 | $0.028 | $0.032 | 100.00% |
| Canopywave | — | $0.140 | $0.280 | $0.030 | $0.034 | — |
| Crusoe | fp8 | $0.140 | $0.280 | $0.030 | $0.034 | 100.00% |
| Alibaba | fp8 | $0.150 | $0.300 | $0.030 | $0.034 | 100.00% |
| Azure | unknown | $0.210 | $0.560 | $0.031 | $0.038 | 100.00% |
| Relace | fp4 | $0.045 | $0.450 | $0.045 | $0.047 | 100.00% |
| Parasail | fp8 | $0.140 | $0.280 | $0.070 | $0.073 | 100.00% |
| Sference | — | $0.280 | $0.560 | $0.070 | $0.078 | — |
| Mancer 2 | fp8 | $0.190 | $0.500 | — | $0.192 | 100.00% |
| Wafer | mxfp4 | $0.600 | $0.170 | $0.200 | $0.210 | 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.