Experimental multimodal DeepSeek V4 Flash model for image understanding, coding, and agentic workDeepSeek V4 Flash Vision Exp is offered by 16 providers on this page. Public prices are shown for 15 of them. No official API price is listed for it; the prices below come from third-party channels. The lowest paid channel is OpenCode at $0.14 / $0.28 per 1M. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it. Prices vary about 3.1× across the providers that host it. It also has 1 free ($0) channel; free tiers usually carry rate limits, and subscription-covered access bills $0 per token only after the subscription fee.
The context window is 1,048,576 tokens at the reference host, but hosts report different limits, from 1,000,000 to 1,050,000, so the usable window depends on the provider you pick. It supports reasoning, tool use, and structured output. Accepted input modalities are Text and Image. The weights are open, so it can also be self-hosted or served through a gateway of your choice.
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| AMD DeepSeek-V4-Flash-Vision-Exp | Cloud | Free | $0 | — | 1,000,000 ⚠ | 384,000 | deprecated | |
| OpenCode | Gateway | $0.14 | $0.28 | $0.028 | — | 1,000,000 ⚠ | 384,000 | deprecated |
| CommandCode | Gateway | $0.15 | $0.60 | $0.003 | — | 1,000,000 ⚠ | 384,000 | |
| Eden AI | Gateway | $0.15 | $0.60 | $0.003 | — | 1,000,000 ⚠ | 384,000 | |
| AIHubMix | Gateway | $0.16 | $0.62 | $0.0031 | — | 1,000,000 ⚠ | 384,000 | deprecated |
| NanoGPT | Gateway | $0.22 | $0.65 | $0.0069 | — | 1,048,576 | 384,000 | |
| Vercel AI Gateway | Cloud | $0.22 | $0.65 | $0.0068 | — | 1,048,576 | 1,048,576 | |
| OrcaRouter | Gateway | $0.22 | $0.66 | $0.007 | — | 1,000,000 ⚠ | 384,000 | |
| LLM Gateway | Gateway | $0.44 | $1.32 | — | — | 1,048,576 | 262,144 | |
| DevPass (LLM Gateway) | Gateway | $0.44 | $1.32 | — | — | 1,050,000 ⚠ | 384,000 |
Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.
Interleaved thinking (reasoning between tool calls) is declared by 5 of 16 providers.
1 more channels offer $0 (AMD); free tiers usually have rate limits and no SLA, excluded from ranking.
| Name | Conditions | Score | Metric | Source |
|---|---|---|---|---|
| Terminal-Bench | harness: DeepSeek Harness minimal mode · variant: max effort · v2.1 | 83.9 | score | Source ↗ |
| NL2Repo | harness: DeepSeek Harness minimal mode · variant: max effort | 57.7 | score | Source ↗ |
| CyberGym | harness: DeepSeek Harness minimal mode · variant: max effort | 75.3 | score | Source ↗ |
| DeepSWE | harness: DeepSeek Harness minimal mode · variant: max effort | 59.3 | score | Source ↗ |
| Toolathlon-Verified | harness: DeepSeek Harness minimal mode · variant: max effort | 75.9 | score | Source ↗ |
| DSBench-Hard | harness: DeepSeek Harness minimal mode · variant: max effort · dataset: internal | 63.6 | score | Source ↗ |
| AutomationBench | harness: DeepSeek Harness minimal mode · variant: max effort · dataset: public | 25.7 | score | Source ↗ |
| ApexBench | — | 36.5 | pass@1 | Source ↗ |
| Agents' Last Exam | — | 27.3 | score | Source ↗ |
| Chartography | — | 64.3 | score | Source ↗ |
| ZeroBench | — | 35 | pass@5 | Source ↗ |
The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.