Compare AI models
| Specifications | ||
ParametersThe learned values that shape how a model responds. B means billion and T means trillion. For mixture-of-experts models, the total count is larger than the number active for each token. Parameter count alone does not measure quality. | 284B | — |
Context windowHow much information the model can work with in one request, measured in tokens — pieces of words or other data. This includes your question, attachments, conversation and reply. Limits can vary by model variant and provider. | 1M | — |
| API pricingUSD per 1M tokens · lower wins · base tier | ||
Input priceWhat you pay for everything you send the model — your question, plus any documents or earlier conversation you include with it. | — | $1.25 |
Output priceWhat you pay for the text the model writes back. It is normally the dearer half: producing an answer costs more than reading one. | — | $2.50 |
Cached input priceA reduced rate for text you send over and over. If every request starts with the same instructions or the same document, the provider keeps a copy ready and charges less to read it again. | — | $0.20 |
Cheapest inputLowest input rate across every provider on OpenRouter, the lab included. The cheapest endpoint may run a quantised build or a shorter context — see "Available from" on the model page. | $0.0379Relace | — |
Cheapest outputLowest output rate across every provider on OpenRouter, the lab included. May come from a different provider than the cheapest input. | $0.0798StreamLake | — |
| $11.97StreamLake · fp8 | $375SpaceXSI list price | |
| Benchmarks | ||
BullshitBench v2Nonsense detection — Given a confidently-worded but nonsensical prompt, does the AI spot that it makes no sense and push back — instead of playing along and inventing an answer? The score is how often it clearly called out the nonsense. Higher is better. | 18% | 56% |
SWE-Bench VerifiedCoding — Real coding tasks pulled from open-source projects — the AI has to find and fix actual bugs. A human-checked version of the original SWE-Bench. Higher is better. | — | 76.7% |
LiveCodeBenchCompetitive coding — Coding problems published so recently the AI can't have seen them in training — a contamination-free test of raw programming skill. Higher is better. | 91.6% | — |
ARC-AGI-2Abstract reasoning — Puzzle-style tests of abstract reasoning and pattern-finding — the kind of thing people find easy but AIs often struggle with. Higher is better. | — | 53.3% |
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 88.1% | — |
| Overview | ||
| Company | DeepSeek | SpaceXSI |
| Release date | Apr 24 2026 | Feb 17 2026 |
| Access | Open Weight | Closed |
| Model details | View model | View model |
Other comparisons
DeepSeek-V4-FlashvsClaude Haiku 5.5Grok 4.20 BetavsClaude Haiku 5.5DeepSeek-V4-FlashvsGPT-6.1 TerraGrok 4.20 BetavsGPT-6.1 TerraDeepSeek-V4-FlashvsGemini 4 CarbonGrok 4.20 BetavsGemini 4 CarbonDeepSeek-V4-FlashvsMuse Spark OpenGrok 4.20 BetavsMuse Spark OpenDeepSeek-V4-FlashvsMistral Large 4Grok 4.20 BetavsMistral Large 4DeepSeek-V4-FlashvsKimi K3.1 ProGrok 4.20 BetavsKimi K3.1 ProFrequently asked questions
Grok 4.20 Beta leads DeepSeek-V4-Flash on 1 of the 1 benchmark they both report (BullshitBench v2). Only Grok 4.20 Beta has a verified first-party price for an available API: $1.25 per million input tokens and $2.50 per million output tokens. No currently available pay-as-you-go API rate is tracked for DeepSeek-V4-Flash. Grok 4.20 Beta shipped 66 days before DeepSeek-V4-Flash, so benchmark comparisons should account for the intervening progress.
DeepSeek-V4-Flash is open weight, while Grok 4.20 Beta is closed.
On BullshitBench v2, Grok 4.20 Beta leads at 56% vs DeepSeek-V4-Flash at 18%.