Monthly API cost
Enter your traffic and token sizes - see the monthly cost for every model, cheapest first.
≈ 70.0M input tokens · 35.0M output tokens per month
| Model | Cheapest via | Cost / month | vs cheapest |
|---|---|---|---|
| gpt-oss-20b | PrimeIntellect/ 10 | $1.36 | ×1.0 |
| Qwen3.6 35B A3B | PrimeIntellect/ 11 | $3.92 | ×2.9 |
| gpt-oss-120b | PrimeIntellect/ 24 | $4.72 | ×3.5 |
| GLM 5.3 Flash | Relace/ 35 | $5.23 | ×3.8 |
| Qwen3.5-9B | PrimeIntellect/ 6 | $5.56 | ×4.1 |
| Mistral Small 3 | DeepInfra | $6.30 | ×4.6 |
| Qwen3.7 Flash | Alibaba | $6.65 | ×4.9 |
| Phi 4 | DeepInfra | $7.84 | ×5.7 |
| Command R7B (12-2024) | Cohere | $7.88 | ×5.8 |
| Gemma 4 26B A4B | Darkbloom/ 15 | $8.05 | ×5.9 |
| GPT-5 Nano | OpenAI/ 2 | $8.75 | ×6.4 |
| Granite 4.2 8B | CoreWeave/ 2 | $9.45 | ×6.9 |
| Gemini 2.5 Flash Lite | Google AI Studio | $10.50 | ×7.7 |
| Gemma 3 27B | DeepInfra/ 5 | $11.20 | ×8.2 |
| DeepSeek V4 Flash 0423 | StreamLake/ 17 | $11.56 | ×8.5 |
Live prices, updated 2026-11-03. Each model is priced at its cheapest provider for your workload; cached input uses each provider's cache-read rate. Excludes batch discounts and free tiers.