LLMDeepSeek V4.1 Flash API pricing
DeepSeek V4.1 Flash by Morph costs $0.12 per 1M input tokens and $0.80 per 1M output tokens (1M in + 1M out = $0.92).
- API model id
morph-dsv41flash- Input / 1M
- $0.12
- Output / 1M
- $0.80
- Cached input / 1M
- $0.008
- Context window
- 1.05M
- Notes
- Morph API (OpenAI-compatible, api.morphllm.com/v1), USD per 1M tokens from Morph's public models JSON; pay as you go (usage billed monthly in arrears) or monthly credit plans; free tier 200 requests/month.
- Source
- https://www.morphllm.com/api/models/json?prices=list
- Provider type
- Inference host (HQ: US)
- Regions
- US
- EU data residency
- unknown — Morph's public models JSON lists US datacenters for every model. The pricing page says data residency is available on Enterprise plans; no public EU option is described.
- Last verified
- 2026-11-12
Cost estimate
| Provider | Model | Cost |
|---|---|---|
| Morph | DeepSeek V4.1 Flash | $0.32 |
Uses standard list prices (no caching, batch or off-peak discounts). €, CHF and ₹ rows are priced in that currency by the provider and not converted, so compare them with care. ₹ rows also show ≈ USD at the RBI reference rate of ₹93.8579 per USD (2026-11-09).
Other Morph models
- GLM-5.3: $1.19 / $6.00
- GLM-5.2: $1.19 / $6.00
- GLM-5.3 Flash: $0.20 / $0.70
- DeepSeek V4.1 Flash 1017: $0.12 / $0.80
- DeepSeek V4 Flash 0731: $0.142 / $0.40
- Kimi K3: $2.50 / $14.00
- Kimi K3 Fast: $6.00 / $22.50
- Qwen3.8 27B: $0.289 / $2.40