--- title: "Muse Spark 1.2 API: facts and benchmarks | Kendr" canonical: "https://kendr.org/models/kc-muse-spark-1.2" date_modified: "2026-08-12" profile_kind: "hosted" --- # Muse Spark 1.2 API model profile Muse Spark 1.2 is a Meta model profile with a 1,048,576-token context window. The dated catalog snapshot records text, image, video, file, audio modalities and interfaces for agentic, audio input, coding, file input, prompt caching. Muse Spark 1.2 is available under the Kendr alias kc-muse-spark-1.2. Current account availability and customer credit quotes come from Kendr's live public model API and applicable account policy. Muse Spark 1.2 accepts text, image, video, file, and audio and returns text. The snapshot records agentic, audio input, coding, file input, prompt caching, reasoning, reasoning controls, structured output, text generation, tool calling, tools, video input, vision, and web search pricing as capabilities or interfaces. The dated reference snapshot lists $1.25 input and $4.25 output per million tokens. Cached input is $0.15 per million tokens. The separately published provider-route reference is Pricing review (Standard Meta Model API route). The 2026-08-12 snapshot includes 11 Design Arena categories. Publisher-reported launch results are labeled and are not presented as Kendr measurements; scores from different suites are not treated as interchangeable. Muse Spark 1.2 ranked #67 in the cited trailing-7-day third-party catalog usage dataset as of 2026-08-12. Observed within the cited trailing-7-day third-party catalog usage dataset; this is not global AI market share. Profile data was reviewed for the 2026-08-12 snapshot. Claims retain their source dates, and unavailable fields are shown as unavailable instead of estimated. ## Profile facts - **Profile type:** Kendr API model - **Kendr API alias:** kc-muse-spark-1.2 - **Model developer:** Meta - **Kendr route provider:** Meta - **Context window:** 1M - **Snapshot date:** 2026-08-12 - **Reference catalog ID:** meta/muse-spark-1.2 ## Context, modalities, and identity Muse Spark 1.2 accepts text, image, video, file, and audio and returns text. The snapshot records agentic, audio input, coding, file input, prompt caching, reasoning, reasoning controls, structured output, text generation, tool calling, tools, video input, vision, and web search pricing as capabilities or interfaces. - **Model developer:** Meta - **Kendr route provider:** Meta - **Context window:** 1M - **Maximum output:** No verified numeric limit - **Input modalities:** text, image, video, file, and audio - **Output modalities:** text - **Knowledge cutoff:** Not disclosed ## Capabilities and supported controls Capabilities and parameters are reported from the dated catalog and source records; their presence does not guarantee identical behavior across every provider route. - **Supported parameters:** include_reasoning, max_tokens, reasoning, reasoning_effort, repetition_penalty, response_format, structured_outputs, temperature, tool_choice, tools, top_k, top_p - agentic - audio input - coding - file input - prompt caching - reasoning - reasoning controls - structured output - text generation - tool calling - tools - video input - vision - web search pricing ## Dated pricing snapshot The dated reference snapshot lists $1.25 input and $4.25 output per million tokens. Cached input is $0.15 per million tokens. The separately published provider-route reference is Pricing review (Standard Meta Model API route). Reference figures are dated 2026-08-12; the live Kendr quote can differ by selected provider route, context tier, caching, tools, region, and current rate card. - **Price date:** 2026-08-12 - **Input:** $1.25 per 1M tokens - **Cached input:** $0.15 per 1M tokens - **Output:** $4.25 per 1M tokens ## Benchmark evidence and limitations The 2026-08-12 snapshot includes 11 Design Arena categories. Publisher-reported launch results are labeled and are not presented as Kendr measurements; scores from different suites are not treated as interchangeable. Third-party catalog fields normalized from the cited model dataset; benchmark methodology and coverage differ by source. | Design Arena category | Elo | Win rate | Rank | | --- | --- | --- | --- | | androidnative | 1258 | 55.6% | #5 | | fullstack | 1241 | 50.2% | #9 | | mobileapps | 1216 | 48.5% | #14 | | python-pptxslides | 1188 | 47% | #10 | | webapps | 1261 | 52.8% | #8 | | 3d | 1360 | 63.2% | #5 | | codecategories | 1348 | 59.6% | #3 | | dataviz | 1370 | 63.4% | #3 | | gamedev | 1372 | 62.1% | #3 | | uicomponent | 1347 | 57.9% | #4 | | website | 1335 | 57.6% | #3 | ## Popularity and market context Muse Spark 1.2 ranked #67 in the cited trailing-7-day third-party catalog usage dataset as of 2026-08-12. Observed within the cited trailing-7-day third-party catalog usage dataset; this is not global AI market share. - **Third-party catalog rank:** #67 - **Global market share:** Not inferred - **Observation date:** 2026-08-12 ## OpenAI-compatible API example ```bash curl https://api.kendr.org/v1/chat/completions \ -H "Authorization: Bearer $KENDR_API_KEY" \ -H "Content-Type: application/json" \ -d '{"model":"kc-muse-spark-1.2","messages":[{"role":"user","content":"Hello"}]}' ``` ## Frequently asked questions ### What is Muse Spark 1.2? Muse Spark 1.2 is a Meta model profile with a 1,048,576-token context window. The dated catalog snapshot records text, image, video, file, audio modalities and interfaces for agentic, audio input, coding, file input, prompt caching. ### What context window does Muse Spark 1.2 have? The dated profile lists 1M of context. Provider routes, variants, and runtime configuration can impose lower effective limits. ### What benchmark evidence is available for Muse Spark 1.2? The 2026-08-12 snapshot includes 11 Design Arena categories. Publisher-reported launch results are labeled and are not presented as Kendr measurements; scores from different suites are not treated as interchangeable. Third-party catalog fields normalized from the cited model dataset; benchmark methodology and coverage differ by source. ### What is the Kendr API alias for Muse Spark 1.2? Use kc-muse-spark-1.2 as the model value. The live public model API and signed-in catalog remain authoritative for route availability and customer credit quotes. ### How is Muse Spark 1.2 priced on Kendr? The dated reference snapshot lists $1.25 input and $4.25 output per million tokens. Cached input is $0.15 per million tokens. The separately published provider-route reference is Pricing review (Standard Meta Model API route). Kendr applies one 5% markup to configured provider model cost; the live quote and settled routing receipt are authoritative for a request. ## Sources and evidence dates - [Muse Spark 1.2 third-party catalog record](https://openrouter.ai/meta/muse-spark-1.2) — catalog, checked 2026-08-12 - [Third-party model catalog methodology](https://openrouter.ai/docs/guides/overview/models) — methodology, checked 2026-08-12 - [Meta official model documentation](https://github.com/meta-llama/llama-models) — primary, checked 2026-08-12 - [Design Arena leaderboard and methodology](https://www.designarena.ai/leaderboard) — benchmark, checked 2026-08-12 - [Muse Spark 1.2 provider or route reference](https://developer.meta.com/ai/models/muse-spark/) — primary, checked 2026-08-12 Live Kendr operational availability is published separately at https://api.kendr.org/api/public/models.