DeepSeek V4.1 Flash 1017 (Max)
Output 156 tokens/sFirst token 0.9 sContext 1M tokens
Top 5 cheapest providers (Adjusted $/task)
The same list price can give a different adjusted $/task (caching, token efficiency) — click a price for its inputs.
Within the active global provider, residency and confidentiality filters.
| # | Provider | Price channel | Raw input $/1M | Raw output $/1M | Adjusted $/task |
|---|---|---|---|---|---|
| 1 | Morphvia OpenRouter — Price via OpenRouter: OpenRouter's price for Morph's endpoint (https://openrouter.ai/deepseek/deepseek-v4.1-flash-1017/providers), collected 2026-11-03. | via OpenRouter — Price via OpenRouter: OpenRouter's price for Morph's endpoint (https://openrouter.ai/deepseek/deepseek-v4.1-flash-1017/providers), collected 2026-11-03. | $0.035 | $0.315 | |
| 2 | Relacevia OpenRouter — Price via OpenRouter: OpenRouter's price for Relace's endpoint (https://openrouter.ai/deepseek/deepseek-v4.1-flash-1017/providers), collected 2026-11-03. | via OpenRouter — Price via OpenRouter: OpenRouter's price for Relace's endpoint (https://openrouter.ai/deepseek/deepseek-v4.1-flash-1017/providers), collected 2026-11-03. | $0.035 | $0.500 | |
| 3 | OpenInferencevia OpenRouter — Price via OpenRouter: OpenRouter's price for OpenInference's endpoint (https://openrouter.ai/deepseek/deepseek-v4.1-flash-1017/providers), collected 2026-11-03. | via OpenRouter — Price via OpenRouter: OpenRouter's price for OpenInference's endpoint (https://openrouter.ai/deepseek/deepseek-v4.1-flash-1017/providers), collected 2026-11-03. | $0.035 | $0.500 | |
| 4 | Wafervia OpenRouter — Price via OpenRouter: OpenRouter's price for Wafer's endpoint (https://openrouter.ai/deepseek/deepseek-v4.1-flash-1017/providers), collected 2026-11-03. | via OpenRouter — Price via OpenRouter: OpenRouter's price for Wafer's endpoint (https://openrouter.ai/deepseek/deepseek-v4.1-flash-1017/providers), collected 2026-11-03. | $0.038 | $0.500 | |
| 5 | Particle AIvia OpenRouter — Price via OpenRouter: OpenRouter's price for Particle AI's endpoint (https://openrouter.ai/deepseek/deepseek-v4.1-flash-1017/providers), collected 2026-11-03. | via OpenRouter — Price via OpenRouter: OpenRouter's price for Particle AI's endpoint (https://openrouter.ai/deepseek/deepseek-v4.1-flash-1017/providers), collected 2026-11-03. | $0.050 | $0.500 |
Composite
2 of 7 inputs · 1 from the model family6 radar axes: DesignArena's two boards share one71.9
Thin data · 2/7Based on only 2 of 7 Composite inputs — treat this rank as uncertainAA Coding v4.x —Coding Agent v1.4 —AA Intelligence 32.5AA Agentic —Epoch ECI 158.8Software ECI —DesignArena —/—
Radar: percentile among all models measured on each input; a gap means not measured.
Benchmark sheet
1 of 319 registered benchmark versions · bars show the percentile among all models measured on each benchmark.
- Epoch ECI · attached
Coding
Artificial Analysis Coding Agent Index v2.0no percentile46.3%
Artificial Analysis Coding Agent Index v2.0 v2.0 → · DeepSeek Harness — Measures coding-agent systems on FrontierCode v1.1 Main, Terminal-Bench 4.0 and SWE-Atlas-QnA-AA.
Reasoning
AA Intelligence Index v5.0 · snapshot-2026-11-035732.5
AA Intelligence Index v5.0 · snapshot-2026-11-03 → · Published board — Artificial Analysis Intelligence Index v5.0. Models AA has not rescored on v5.0 are listed as estimates from their frozen v4.x value (isotonic fit over the models measured on both versions), never as measurements.
Missing coverage · 318 benchmark versions
No result does not mean a zero, or that the model was never tested. Collection failures and disputed versions retain their distinct status.
Variants / reasoning settings
Artificial Analysis snapshot 2026-11-03 · Intelligence Index v5.0 (est. = estimated from v4, not measured) · Coding Index v4.x frozen 2026-10-27 · Data: Artificial Analysis · Data: Epoch AI (CC BY)
| Variant | AA Coding | AA Intelligence |
|---|---|---|
| DeepSeek V4.1 Flash 1017 (Max) | — | 32.5 |
| DeepSeek V4.1 Flash 1017 (High) | — | 28.5 |
| DeepSeek V4.1 Flash 1017 (Non-reasoning) | — | 18.5 |
Token offers by platform · 37 offers (Adjusted $/task)
Click any underlined price to see how it is estimated and where each input comes from. How we calculate adjusted cost.
37 offers within the active global filters, 10 more outside them; “price n/a” means the provider serves the model but publishes no direct token price we could collect — no other channel's price is shown in its place.
OpenRouter (33)
Prices via OpenRouter — what OpenRouter charges for each provider's endpoint, not the provider's own direct price. Source: openrouter.ai/deepseek/deepseek-v4.1-flash-1017/providers, collected 2026-11-03.
| Morph | globalmorph/fp8 | $0.035 raw in $/1M | $0.315 raw out $/1M | |
| Relace | globalrelace/fp4 | $0.035 raw in $/1M | $0.500 raw out $/1M | |
| Wafer | globalwafer/us | $0.038 raw in $/1M | $0.500 raw out $/1M | |
| Particle AI | globalparticle-ai/us | $0.050 raw in $/1M | $0.500 raw out $/1M | |
| Sail Research | globalsail-research/fp4/us | $0.101 raw in $/1M | $0.150 raw out $/1M | |
| Sail Research | globalsail-research/fp4 | $0.101 raw in $/1M | $0.150 raw out $/1M | |
| DeepInfra | globaldeepinfra/fp8 | $0.098 raw in $/1M | $0.294 raw out $/1M | |
| InferenceNet | globalinference-net/us | $0.080 raw in $/1M | $0.550 raw out $/1M | |
| InferenceNet | globalinference-net/fp8 | $0.080 raw in $/1M | $0.550 raw out $/1M | |
| Cloudflare | globalcloudflare | $0.100 raw in $/1M | $0.600 raw out $/1M | |
| Decart | globaldecart/fp4 | $0.123 raw in $/1M | $0.492 raw out $/1M | |
| Wafer | globalwafer/mxfp4 | $0.160 raw in $/1M | $0.500 raw out $/1M | |
| ModelRun | globalmodelrun/fp4 | $0.170 raw in $/1M | $0.670 raw out $/1M | |
| DigitalOcean | globaldigitalocean | $0.180 raw in $/1M | $0.720 raw out $/1M | |
| Novita | globalnovita/fp8 | $0.195 raw in $/1M | $0.780 raw out $/1M | |
| PrimeIntellect | globalprimeintellect | $0.156 raw in $/1M | $1.20 raw out $/1M | |
| Reka | globalreka | $0.160 raw in $/1M | $1.10 raw out $/1M | |
| Phala | globalphalaTEE | $0.200 raw in $/1M | $1.20 raw out $/1M | |
| Modal | globalmodal | $0.250 raw in $/1M | $1.00 raw out $/1M | |
| Relace | globalrelace/fast | $0.300 raw in $/1M | $0.900 raw out $/1M | |
| Crusoe | globalcrusoe/fp8 | $0.290 raw in $/1M | $1.20 raw out $/1M | |
| Near AI | globalnear-ai | $0.300 raw in $/1M | $1.20 raw out $/1M | |
| SiliconFlow | globalsiliconflow/fp8 | $0.300 raw in $/1M | $1.20 raw out $/1M | |
| Together | globaltogether | $0.300 raw in $/1M | $1.20 raw out $/1M | |
| Parasail | globalparasail/fp8 | $0.300 raw in $/1M | $1.20 raw out $/1M | |
| BaseTen | globalbaseten | $0.300 raw in $/1M | $1.20 raw out $/1M | |
| Venice | globalvenice/fp8 | $0.300 raw in $/1M | $1.20 raw out $/1M | |
| Fireworks | globalfireworks/us | $0.450 raw in $/1M | $1.80 raw out $/1M | |
| Ionstream | globalionstream | $0.165 raw in $/1M | $0.495 raw out $/1M | |
| Nebius | globalnebius/fp8 | $0.300 raw in $/1M | $1.20 raw out $/1M | |
| Fireworks | globalfireworks | $0.300 raw in $/1M | $1.20 raw out $/1M | |
| OpenInference | globalopen-inference/fp4 | $0.035 raw in $/1M | $0.500 raw out $/1M | |
| Fireworks | globalfireworks/spot | $0.210 raw in $/1M | $0.840 raw out $/1M |
TrustedTokens (1)
Direct prices from TrustedTokens's own price list. Source: trustedtokens.eu/api/public/models, collected 2026-11-03.
| TrustedTokens | euEU | $0.340 raw in $/1M | $0.670 raw out $/1M |
TensorX (1)
Direct prices from TensorX's own price list. Source: tensorx.ai/pricing/, collected 2026-11-03.
| TensorX | euEU | $0.500 raw in $/1M | $1.50 raw out $/1M |
Nebius (1)
Direct prices from Nebius's own price list. Source: tokenfactory.nebius.com/models, collected 2026-11-03.
| Nebius | us | $0.300 raw in $/1M | $1.20 raw out $/1M |
Scaleway (1)
Direct prices from Scaleway's own price list. Source: scaleway.com/en/pricing/model-as-a-service, collected 2026-11-03.
| Scaleway | euEU | $0.670 raw in $/1M | $2.02 raw out $/1M |