DeepSeek V4 Pro 0813

DeepSeek · On OpenRouter since August 12, 2026 · Pinned version id: deepseek/deepseek-v4-pro-20260813

Price

$1.98

mixed / 1M tokens

Mixed price per 1M tokens: 3 input tokens to 1 output token.

in $1.32 · out $3.96 · Cached input $0.044

Cheaper off-peak. This provider changes the price during the day or week. The higher rate is shown.

Price disputed

Models that think before they answer can use many more output tokens, so your real cost can be higher than the figure shown.

US dollars per million tokens, converted to your currency at the NBP rate.

Tasks, with the evidence

Each line names the measurement it rests on. A task that is not listed has no measurement or declared feature we can show.

Hard questions and reasoning

Measured by a third party

Intelligence Index: 23.1 · Rank 42 of 66, among scored models · Artificial Analysis, read November 21, 2026

Long documents

Declared, not measured

Context window: 1M tokens as declared. It says how much fits, not how well the model uses it.

Ranks are among all models we list, including older ones.

Cheaper models with a similar benchmark score

Rule: an Intelligence Index of at least 20.1, a mixed price at least 25% lower, at least the same input types, and tool support. Lower mixed price (3 input tokens to 1 output token); check the flags and your own prompt sizes.

Models that pass this rule: 18. The cheapest of them are shown: 15.

  1. Ling 3.1 Flash inclusionAI 95% cheaper $0.09 · Index 29.6 (this model: 23.1) Differences to check: No structured output; Lower max output Compare
  2. Inkling 2 Mini Thinking Machines 92% cheaper $0.1588 · Index 20.1 (this model: 23.1) Differences to check: Lower max output Compare
  3. MiMo-V2.6-Flash Xiaomi 91% cheaper $0.175 · Index 26.7 (this model: 23.1) Differences to check: Lower max output Compare
  4. Claude Haiku 5.5 Anthropic 90% cheaper $0.20 · Index 36.5 (this model: 23.1) Differences to check: Lower max output; Price rises for long prompts Compare
  5. Muse Ember Meta 90% cheaper $0.20 · Index 36.0 (this model: 23.1) Compare
Show more: 10
  1. GPT-6 Luna OpenAI 90% cheaper $0.20 · Index 27.9 (this model: 23.1) Differences to check: Lower max output; Price rises for long prompts Compare
  2. Qwen3.8 Flash Qwen 88% cheaper $0.23 · Index 28.6 (this model: 23.1) Differences to check: Lower max output Compare
  3. GLM 5.3 Flash Z.ai 88% cheaper $0.2375 · Index 27.8 (this model: 23.1) Differences to check: Lower max output Compare
  4. MiniMax M3.1 Flash MiniMax 87% cheaper $0.2625 · Index 29.1 (this model: 23.1) Compare
  5. GPT-5.6 Luna OpenAI 77% cheaper $0.45 · Index 23.8 (this model: 23.1) Differences to check: Lower max output; Price rises for long prompts Compare
  6. Inkling 2 Small Thinking Machines 76% cheaper $0.475 · Index 30.6 (this model: 23.1) Compare
  7. DeepSeek V4.1 Flash 1017 DeepSeek 73% cheaper $0.525 · Index 32.6 (this model: 23.1) Differences to check: Lower max output Compare
  8. MiMo-V2.6-Pro Xiaomi 73% cheaper $0.5438 · Index 29.9 (this model: 23.1) Differences to check: Lower max output Compare
  9. Hy4 Tencent 68% cheaper $0.6254 · Index 34.6 (this model: 23.1) Differences to check: Lower max output Compare
  10. Qwen3.8 27B Qwen 52% cheaper $0.9563 · Index 20.1 (this model: 23.1) Smaller context: 262k Differences to check: Lower max output Compare

Price by provider

The price used in the catalog is the vendor's own; when the vendor has no API of its own, it is the cheapest regular host.

ProviderInputOutputCached inputMixedNotes
Baidu $0.132$0.396 $0.0042 $0.198 90% cheaper fp8 · promo −90%
StreamLake $0.66$1.98 $0.022 $0.99 50% cheaper promo −50%
Wafer $0.111$4.44 $0.097 $1.19 40% cheaper US · mxfp4 · Numeric precision used by this host. Lower precision (fp4, int4) is cheaper and can change quality.
Wafer $0.285$4.30 $0.284 $1.29 35% cheaper mxfp4 · Numeric precision used by this host. Lower precision (fp4, int4) is cheaper and can change quality.
Novita $0.99$2.97 $0.033 $1.48 25% cheaper fp8 · promo −25%
GMICloud $1.06$3.17 $0.0352 $1.58 20% cheaper fp8 · promo −20%
Sail Research $1.35$2.40 $0.195 $1.61 19% cheaper US · fp4 · Numeric precision used by this host. Lower precision (fp4, int4) is cheaper and can change quality.
Sail Research $1.35$2.40 $0.195 $1.61 19% cheaper fp4 · Numeric precision used by this host. Lower precision (fp4, int4) is cheaper and can change quality.
Show all providers: 23
  • DeepInfra: $1.30 / $2.60 · $1.63
  • Alibaba: $1.12 / $3.37 · $1.68
  • CoreWeave: $1.31 / $3.96 · $1.97
  • DeepSeek: $1.32 / $3.96 · $1.98
  • Alibaba: $1.32 / $3.96 · $1.98
  • AtlasCloud: $1.32 / $3.96 · $1.98
  • BaseTen: $1.32 / $3.96 · $1.98
  • Cloudflare: $1.32 / $3.96 · $1.98
  • DigitalOcean: $1.32 / $3.96 · $1.98
  • Nebius: $1.32 / $3.96 · $1.98
  • Parasail: $1.32 / $3.96 · $1.98
  • SiliconFlow: $1.32 / $3.96 · $1.98
  • Together: $1.32 / $3.96 · $1.98
  • Relace: $0.0999 / $8.00 · $2.07
  • Venice: $1.65 / $4.95 · $2.47

Other pricing modes

Specifications

Context window
1M
Max output
944k
Accepts
text
Answers with
text
Tools
Yes
Structured output
Yes
Reasoning
Optional
Thinking effort levels: none, low, high, and max
Weights on Hugging Face
Hugging Face A Hugging Face repository is linked. We did not check the licence; read it before you build on it.
Knowledge cutoff
No data
On OpenRouter since
August 12, 2026
Price check
disputed

As listed by OpenRouter. "Not listed" means OpenRouter does not list it for this model.

Benchmark scores

Scores come from third parties and are relayed by OpenRouter. We do not run the tests. Higher is better.

SourceScoreRank among scored
Intelligence Index
Artificial Analysis, read November 21, 2026
23.1Rank 42 of 66, among scored models

Intelligence, Coding and Agentic indices: Artificial Analysis (artificialanalysis.ai). Design categories: Design Arena (designarena.ai). Both are relayed by the OpenRouter public model list and were read on November 21, 2026. We compute ranks, tiers and costs from these numbers; the sources have not reviewed them. Scores belong to the model, not to the route it is served on.

Artificial Analysis · Design Arena · Relayed by OpenRouter. opens in a new tab

Sources and dates

Prices: OpenRouter routes and a second price table, checked November 21, 2026. Specifications: OpenRouter, November 21, 2026. Exchange rate: NBP, November 20, 2026. Benchmarks: Artificial Analysis and Design Arena via OpenRouter.