Open-model API price index · USD per 1M tokens · updated daily
Open-model API prices, compared across providers
The open-model API price index lists what every public provider charges for the open-weight models Synap serves: 6 models, 40 provider prices, each with its source and the time it was checked. Where another provider is cheaper than us, the table shows it.
| Model | Providers | Lowest input | Lowest output | Synap in / out | Synap rank (input) |
|---|---|---|---|---|---|
Qwen3 Coder 30Bqwen/qwen3-coder-30b-a3b-instruct | 3 | $0.0675 Synap | $0.27 Synap | $0.0675 / $0.27 | 1 of 3 |
gpt-oss-20bopenai/gpt-oss-20b | 11 | $0.017 Synap | $0.03 PrimeIntellect | $0.017 / $0.085 | 1 of 11 |
Gemma 4 26Bgoogle/gemma-4-26b-a4b-it | 16 | $0.013 PrimeIntellect | $0.04 PrimeIntellect | $0.04 / $0.21 | 2 of 16 |
Qwen3 VL 30Bqwen/qwen3-vl-30b-a3b-instruct | 4 | $0.14 Synap | $0.55 Synap | $0.14 / $0.55 | 1 of 4 |
Qwen3 30B A3B Instruct 2507qwen/qwen3-30b-a3b-instruct-2507 | 4 | $0.0813 Synap | $0.2438 Synap | $0.0813 / $0.2438 | 1 of 4 |
Muse Glimmer 30Bmeta/muse-glimmer-30b | 2 | $0.28 Synap | $1.10 Synap | $0.28 / $1.10 | 1 of 2 |
USD per 1M tokens. Generated 2026-11-11 18:07 UTC. Lowest input and lowest output can come from two different providers. Open a model for the full per-provider table.
How is the index built?
- Every day a job reads Synap's live /v1/models and the public OpenRouter endpoints API for each model.
- One row per provider: the cheapest endpoint that provider lists for that model.
- List prices only. Cached-input, batch and volume discounts are not compared, except Synap's batch price, which is labelled.
- If a source fails, the model keeps its last rows with their original timestamps. Nothing is re-dated.
Can I reuse the data?
Yes. price-index.json is published under CC BY 4.0. Credit “Open-model API price index, Synap (synap402.com/compare)”. Each row keeps the URL it came from.
Try the cheapest one
curl https://synap402.com/v1/chat/completions \
-H "Authorization: Bearer $SYNAP_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "gpt-oss-20b", "messages": [{"role": "user", "content": "Hello"}]}'