DeepSeek V3.1 pricing across providers
Across tracked provider offerings, input runs $0.250–$0.650 per million tokens and output $0.950–$1.70 per million tokens. The cheapest tracked provider offering for a typical agentic mix (2.5% input, 97% cached input, 0.5% output) is DeepInfra at $0.137 per million tokens.
Prices are USD per million tokens and reflect each provider offering — they are not a single intrinsic model price. 2 of 5 offerings publish a cache-read rate; 5 of 5 publish a 30-minute endpoint uptime figure.
Open the calculator filtered to DeepSeek V3.1
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 V3.1
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) |
|---|---|---|---|---|---|---|
| DeepInfra | fp4 | $0.250 | $0.950 | $0.130 | $0.137 | 100.00% |
| SiliconFlow | fp8 | $0.270 | $1.00 | — | $0.274 | 100.00% |
| Coreweave | fp8 | $0.550 | $1.65 | $0.550 | $0.555 | 100.00% |
| Mara | unknown | $0.600 | $1.70 | — | $0.605 | 93.33% |
| SambaNova | fp8 | $0.650 | $1.50 | — | $0.654 | 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.