deepseek-ai/deepseek-v3 pricing
deepseek-ai/deepseek-v3, Mid-tier from Replicate, costs $1.45 per 1M input tokens and $1.45 per 1M output tokens.
Input$1.45per 1M tokens
Output$1.45per 1M tokens
Context window—tokens
TierMidReplicate
Price your own workload against deepseek-ai/deepseek-v3 in the calculator →
Specs and pricing
| Provider | Replicate |
| Tier | Mid |
| Context window | — |
| Max output | — |
| Input price | $1.45 / 1M tokens |
| Output price | $1.45 / 1M tokens |
| Modalities | text |
Note. Replicate quotes a flat $1.45 per million tokens for both input and output; no conversion needed.
What it costs at realistic volumes
Assuming a 4:1 input:output token ratio, a common shape for chat and RAG-style workloads:
| Volume (4:1 in:out ratio) | Input cost | Output cost | Total / month |
|---|---|---|---|
| 1,000,000 in / 250,000 out | $1.45 | $0.36 | $1.81 |
| 10,000,000 in / 2,500,000 out | $14.50 | $3.63 | $18.13 |
| 100,000,000 in / 25,000,000 out | $145.00 | $36.25 | $181.25 |
Cheaper alternatives
Same tier (Mid), a different provider, and a lower blended cost at the 4:1 ratio used above:
| Model | Provider | $/1M in | $/1M out | At the 4:1 ratio |
|---|---|---|---|---|
| GPT-OSS 120B | OpenRouter | $0.037 | $0.17 | 95.6% cheaper blended |
| GPT-OSS 120B | Novita AI | $0.05 | $0.25 | 93.8% cheaper blended |
| Llama-3.3-70B-Instruct-Turbo | DeepInfra | $0.10 | $0.32 | 90.1% cheaper blended |
| Nemotron 3 Super | OpenRouter | $0.085 | $0.40 | 89.8% cheaper blended |
| DeepSeek V4 Flash 0731 | Baseten | $0.13 | $0.26 | 89.2% cheaper blended |