About this model
Multimodal 1M-context MoE checkpoint for coding, reasoning, and tool-using agents. DeepSeek-V4.1-Flash-1017 is the October 2026 checkpoint of DeepSeek-V4.1-Flash, a multimodal mixture-of-experts model for coding, reasoning, visual understanding, and tool-using agents.
Pricing
| Rate | RODI | USD (ref.) | Unit |
|---|---|---|---|
| Text tokens | |||
| In | 113.7 | ~ 0.150 | per 1M tokens (RODI/M, USD/M) |
| Out | 454.6 | ~ 0.600 | per 1M tokens (RODI/M, USD/M) |
| Prompt caching | |||
| Cached | 7.6 | ~ 0.0100 | per 1M tokens (RODI/M, USD/M) |
RODI prices include RodiumAi markup and upstream fees. USD figures are wholesale reference rates.
Providers & pricing
| Provider | Input | Output | Cached | Free tier | Status |
|---|---|---|---|---|---|
 Runware Default All rates (3)
| 113.7 | 454.6 | 7.6 | - | No data |
Capabilities
Streaming
Tool calling
Vision
JSON mode
Reasoning
API usage
Use the canonical slug with client.chat() or chat.completions.create().
Examples
…Example response
…RodiumAi SDK
Official Python, JavaScript, and Laravel SDKs: flat API aligned with this model slug.
…Use cases
- Coding assistants and code review at a low price.
- Reasoning-heavy work: maths, logic, step-by-step analysis.
- High-volume text processing where cost per token matters.
- Agents that call tools.
Notes
- DeepSeek models answer on
POST https://api.rodiumai.io/v1/chat/completions(OpenAI format), served through RodiumAi's cloud upstreams. max_tokensandmax_completion_tokensare both accepted. Leave generous room for thinking models: a few thousand tokens.- Thinking models can return their reasoning separately. Streaming deltas may include
reasoning_contentbefore the finalcontent. - OpenAI-only fields such as
n,seedorlogit_biasare ignored. Streaming, tools and JSON mode depend on the Capabilities section.