--- title: "Meta: Llama 4 Maverick — unrated, priced in this catalogue · Undominated.ai" canonical: https://undominated.ai/models/meta-llama__llama-4-maverick/ description: "Meta: Llama 4 Maverick: $0.270/M in, $0.850/M out. No independent quality score in this catalogue — unrated, not ranked, not scored zero." --- # Meta: Llama 4 Maverick — unrated, priced in this catalogue · Undominated.ai > Meta: Llama 4 Maverick: $0.270/M in, $0.850/M out. No independent quality score in this catalogue — unrated, not ranked, not scored zero. [Check base rates for this workload](/check/meta-llama__llama-4-maverick/) [Cheaper alternatives](/alternatives/) [Family](/families/llama/) [Compare models](https://undominated.ai/compare/?models=meta-llama%2Fllama-4-maverick) Comparison context Choose up to three standard models in Compare. Requirements and prompt length apply in Compare. This page keeps its stated price basis and workload controls. MODEL PROOF # Llama 4 Maverick Meta · 05 Apr 2025 · llama-4-community Balanced Summarise Chat Code gen Agentic NOT INDEPENDENTLY RATED ## No independent LMArena score is published for this model. **$0.415** / 1M tokens Balanced · 3 tokens in per 1 out Serving precision differs between offers. Evidence as of 06 Oct 2026 [openrouter/models](https://openrouter.ai/api/v1/models) [Vendor cross-check](https://openrouter.ai/api/v1/models) Independent LMArena score Not independently rated Context window 1.05M Maximum output 16.38K Input modalities text, image Output modalities text Published input price $0.270 / 1M tokens Published output price $0.850 / 1M tokens Pricing kind fixed Inspect [complete billing conditions](#billing-details) and endpoint terms below. Price from Novita: the cheapest offer that is serving, at standard delivery and at a declared precision that is not 4-bit (fp8), at its standard rate. The maker’s own precision is not known. Cheaper right now: $0.304/M at DigitalOcean — precision not disclosed It does not pass the like-for-like test, so it never sets a rank. Every price dimension · USD per million tokens | Input | $0.270 /M | | --- | --- | | Output | $0.850 /M | | Cached input | Unknown /M | | Cache write | Unknown /M | | Cache write 1h | Unknown /M | | Reasoning | Unknown /M | ### Who sells it The same weights, different shops. Cheapest is not like-for-like when serving precision differs. Headline cheapest is a lower precision. Like-for-like at the best declared precision is $0.270/M from Novita. 4 provider offers · rates, limits and conditions Rates are USD per million tokens. Endpoint terms can differ even when the quoted price and precision match. A listed parameter is a provider declaration, not a task-success test. | Seller | Input | Output | Precision | Uptime (1d) | | --- | --- | --- | --- | --- | | Seller DigitalOcean digitalocean Endpoint terms Cached input /M $0.050 Context limit 128,000 tokens Output limit 16,384 tokens Tools Listed by endpoint Reasoning Not listed by endpoint Promotional discount None reported Uptime · last 30 minutes 99.68% | Input $0.188 | Output $0.653 | Precision undeclared | Uptime (1d) 99.28% | | Seller Novita novita/fp8 Endpoint terms Cached input /M Unknown Context limit 1,048,576 tokens Output limit 8,192 tokens Tools Not listed by endpoint Reasoning Not listed by endpoint Promotional discount None reported Uptime · last 30 minutes 99.30% | Input $0.270 | Output $0.850 | Precision fp8 | Uptime (1d) 98.72% | | Seller Parasail parasail/fp8 Endpoint terms Cached input /M $0.170 Context limit 524,288 tokens Output limit 32,768 tokens Tools Listed by endpoint Reasoning Not listed by endpoint Promotional discount None reported Uptime · last 30 minutes 99.75% | Input $0.350 | Output $1.00 | Precision fp8 | Uptime (1d) 99.85% | | Seller Google google-vertex/us-east5 Endpoint terms Cached input /M Unknown Context limit 524,288 tokens Output limit 8,192 tokens Tools Listed by endpoint Reasoning Not listed by endpoint Promotional discount None reported Uptime · last 30 minutes Unknown | Input $0.350 | Output $1.15 | Precision undeclared | Uptime (1d) — | ### Independent scores No independent benchmark has measured this model. Unrated is not a score of zero. #### Best rankings by task - 3D #112 908 - UI components #120 906 - Data visualisation #122 889 - Code categories #124 885 - Game development #125 850 - Websites #128 877 Per-task Elo and rank from [Design Arena](https://designarena.ai), via OpenRouter’s model feed. The rank is the feed’s, and it counts models OpenRouter does not list. ### Capability | Context window | 1M | | --- | --- | | Max output | 16K | | Input modes | text, image | | Tool use | yes | | Reasoning | no | | Knowledge cutoff | 2024-08-31 | | Open weights | yes | ### Provenance | Price source | [openrouter.ai](https://openrouter.ai/api/v1/models) | | --- | --- | | Fetched | 2026-10-06 | | Quality data | unrated | | Cross-checked | [vendor page](https://openrouter.ai/api/v1/models) | ## Our take editorial — not a measurement Maverick is an open-weight candidate for text and image workloads. Review the model’s community licence for the intended deployment rather than treating open weights as unrestricted permission. Hosted sellers can quote different rates and conditions; self-hosting needs its own capacity estimate. Compare task results before assuming that a newer family is a suitable replacement. ### Strengths - Open weights and a community-licence identifier are recorded - Text and image input are listed ### Weaknesses - Check the output ceiling as well as the context window - An unlisted cache-read rate does not prove caching is unsupported ### Reach for it when - Self-hosting evaluations within licence terms - Text and image tasks with explicit output requirements ### Avoid it if - The licence does not cover the intended use - The required output exceeds the recorded ceiling Sources: [openrouter.ai](https://openrouter.ai/api/v1/models) Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward... ## Questions this page answers What does Llama 4 Maverick cost? $0.270/M in, $0.850/M out in this catalogue, as of the fetch date on this page. That is the API row, not a subscription. Does Llama 4 Maverick have an independent quality score? Llama 4 Maverick has no independent quality score in this catalogue. Unrated is not a score of zero. What beats Llama 4 Maverick? Llama 4 Maverick has no independent quality score. Unrated is not a score of zero. Does this page use Artificial Analysis scores for Llama 4 Maverick? No. Artificial Analysis figures are not published here. Quality on this page is LMArena Elo where a score exists; otherwise the row is unrated. Does a missing score mean Llama 4 Maverick scored zero? Unrated is not a score of zero. Is the cheapest Llama 4 Maverick endpoint the same product? Headline cheapest is a lower precision. Like-for-like at the best declared precision is $0.270/M from Novita. MODEL MONUMENT ## Save or share this proof Download proof card · 1200 × 630 Preview and more sharing options Meta: Llama 4 Maverick. Balanced workload. Not independently rated. Evidence as of 06 Oct 2026. Copy model link Download square card · 1080 × 1080 Copy landscape image Share landscape card ## Related No independent quality score, so there is no dominator to name. Unrated is not a clean bill of health. - Side by side [Llama 4 Scout](/compare/meta-llama__llama-4-maverick--vs--meta-llama__llama-4-scout/) - Same vendor [Muse Spark 1.3](/models/meta__muse-spark-1.3/) - Meta models [Meta](/providers/meta/) - Where this model appears [wire](/wire/) - Same vendor [Muse Spark 1.2](/models/meta__muse-spark-1.2/) - Where this model appears [self-host](/self-host/) - Same vendor [Muse Spark 1.1](/models/meta__muse-spark-1.1/) - Where this model appears [spreads](/spreads/) - Where this model appears [traps](/traps/) ## Badge The verdict as one SVG, for a README or a docs page. It states this model's dominance status at the balanced workload on the LMArena lens, with the date it was computed, and it is rebuilt with the catalogue — so it changes when the verdict changes, including to one you would rather it did not. Markdown Copy [![Llama 4 Maverick — Undominated.ai dominance verdict](https://undominated.ai/badge/meta-llama__llama-4-maverick.svg)](https://undominated.ai/models/meta-llama__llama-4-maverick/) HTML Copy Llama 4 Maverick — Undominated.ai dominance verdict Direct file: [https://undominated.ai/badge/meta-llama__llama-4-maverick.svg](https://undominated.ai/badge/meta-llama__llama-4-maverick.svg) — a static SVG, written by scripts/build-badges.mjs on every build, so the copy you embed is never older than the last deploy. ## Continue your investigation - [Explore model families](/families/) - [Compare a shortlist](/compare/) - [Check a model](/check/) - [Understand the evidence](/methodology/)