DeepSeek V4 Pro 0423 pricing across providers
Across tracked provider offerings, input runs $0.280–$1.91 per million tokens and output $0.783–$3.96 per million tokens. The cheapest tracked provider offering for a typical agentic mix (2.5% input, 97% cached input, 0.5% output) is Wafer at $0.066 per million tokens.
Prices are USD per million tokens and reflect each provider offering — they are not a single intrinsic model price. 22 of 22 offerings publish a cache-read rate; 12 of 22 publish a 30-minute endpoint uptime figure.
Open the calculator filtered to DeepSeek V4 Pro 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 Pro 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) |
|---|---|---|---|---|---|---|
| Wafer | — | $0.280 | $3.96 | $0.040 | $0.066 | — |
| Canopywave | — | $1.74 | $3.48 | $0.010 | $0.071 | — |
| Bytedance | — | $1.32 | $3.96 | $0.044 | $0.095 | — |
| Baidu promo | fp8 | $0.847 | $1.69 | $0.070 | $0.098 | 100.00% |
| Streamlake promo | fp8 | $0.845 | $1.69 | $0.070 | $0.098 | 100.00% |
| Ember | — | $0.851 | $1.70 | $0.071 | $0.099 | — |
| Runware | — | $0.961 | $1.92 | $0.079 | $0.110 | — |
| GMI Cloud promo | fp8 | $0.957 | $1.91 | $0.080 | $0.111 | 100.00% |
| Singularity | — | $0.392 | $0.783 | $0.128 | $0.138 | — |
| DeepInfra | — | $1.30 | $2.60 | $0.100 | $0.143 | — |
| Avian | — | $1.30 | $2.61 | $0.109 | $0.151 | — |
| Alibaba | fp8 | $1.42 | $2.83 | $0.118 | $0.164 | 100.00% |
| SiliconFlow | fp8 | $1.00 | $3.14 | $0.135 | $0.172 | 100.00% |
| Atlascloud | fp4 | $1.68 | $3.38 | $0.130 | $0.185 | — |
| Novita | fp8 | $1.60 | $3.20 | $0.135 | $0.187 | 100.00% |
| Crusoe | fp8 | $1.74 | $3.48 | $0.150 | $0.206 | 100.00% |
| Azure | unknown | $1.91 | $3.83 | $0.160 | $0.222 | 100.00% |
| Cloudflare | unknown | $1.15 | $2.55 | $0.200 | $0.235 | 100.00% |
| Digitalocean | unknown | $1.04 | $2.09 | $0.209 | $0.239 | 100.00% |
| Relace | fp4 | $0.900 | $1.50 | $0.250 | $0.272 | 100.00% |
| Makora | — | $1.39 | $2.79 | $0.301 | $0.341 | — |
| Venice | unknown | $1.65 | $3.30 | $0.330 | $0.378 | 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.