Muse Spark Open API pricing
Together AI lists Muse Spark Open at $1.25 per million input tokens and $4.25 per million output tokens. The cheapest input rate need not give the cheapest total bill.
Together AI · checked 16 October 2026
| Provider / tier / region | Input / 1M | Output / 1M | Cached input / 1M | Checked |
|---|---|---|---|---|
| Together AI | $1.25 | $4.25 | $0.15 | 2026-10-16 |
| Nebius Token Factory · FP4 · us-north1 | $1.25 | $4.25 | Not published | 2026-10-16 |
Muse Spark Open usage costs
These are arithmetic examples, not measured workloads. Change the volumes in the calculator to match your use.
| Example | Provider / tier | Input tokens | Output tokens | Total |
|---|---|---|---|---|
| Short replies | Together AI | 1,000,000 | 100,000 | $1.68 |
| Short replies | Nebius Token Factory · FP4 · us-north1 | 1,000,000 | 100,000 | $1.68 |
| Equal input and output | Together AI | 1,000,000 | 1,000,000 | $5.50 |
| Equal input and output | Nebius Token Factory · FP4 · us-north1 | 1,000,000 | 1,000,000 | $5.50 |
| Document-heavy workload | Together AI | 10,000,000 | 1,000,000 | $16.75 |
| Document-heavy workload | Nebius Token Factory · FP4 · us-north1 | 10,000,000 | 1,000,000 | $16.75 |
Cost = (input tokens × input rate + output tokens × output rate) ÷ 1,000,000. Each total keeps one provider and tier's rates together. These examples exclude cached input, batch pricing, long-context changes and separately billed reasoning tokens.
Calculate API versus GPU rental costCompare other API rates
These have the nearest listed input prices in this table. Price proximity does not mean equal quality, speed or context support.
Check memory estimates for self-hosted models before assuming an API model can be replaced by a rented GPU.