Together AI
$1.50 / month- Input cost
- $0.50
- Output cost
- $1.00
- Per 1,000 calls
- $0.15
- Cache pricing
- Not published
Same model, different API route
GPT-OSS 20B: Together AI or OpenRouter for lower API cost?
Compare Together AI's fixed serverless endpoint with OpenRouter's current catalog floor for GPT-OSS 20B. This comparison holds the model and token workload constant; it does not assume identical infrastructure, latency, or service limits.
Official route fields
Provider pricing and route limits
Prices are USD per 1M tokens. “Not published” means the official tracked source does not expose that field.
| Field | Together AI | OpenRouter |
|---|---|---|
| Pricing basis | Fixed provider endpoint | Current catalog floor |
| API model ID | openai/gpt-oss-20b | openai/gpt-oss-20b |
| Input / 1M | $0.05 | $0.03 |
| Cached input / 1M | Not published | $0.03 / 1M |
| Output / 1M | $0.20 | $0.13 |
| Published route context | 128,000 tokens | 131,072 tokens |
| Published maximum output | Not published | Not published |
Editable workload
GPT-OSS 20B monthly API cost
Token inference only. Provider payment, BYOK, tool, storage, and untracked request fees are excluded.
OpenRouter
$0.95 / month- Input cost
- $0.30
- Output cost
- $0.65
- Per 1,000 calls
- $0.095
- Cache pricing
- $0.03 / 1M
OpenRouter is $0.55 lower per month for the default workload. This is a route-price result, not a service-quality ranking.
Additional fee boundary: OpenRouter credit purchases currently carry a separate 5.5% fee with a minimum charge. The token estimate below does not add payment or BYOK fees.
What to test before switching routes
- Together AI exposes a direct serverless model route; OpenRouter can select among underlying providers.
- The token estimate excludes OpenRouter credit-purchase and BYOK fees.
- Compare operational controls and observed request behavior as well as list price.
What this comparison controls
Both routes call OpenAI's GPT-OSS 20B using the published API model string. Provider infrastructure, quantization, request limits, routing, retention controls, and operational behavior can still differ.
Related provider routes
Continue comparing GPT-OSS 20B
Keep the model constant and compare the remaining provider pair.