LLM API Pricing Comparison (2026)
Compare 9 listed models using the same workload. Prices depend on provider, region, billing mode and date.
Verified November 9, 2026. USD per million tokens. Direct-provider API prices; taxes, storage, cache writes and tool fees excluded.
Published prices and conditions
Sorted using 1,000 input and 500 output tokens per request, without caching. This order is a cost comparison, not a quality ranking.
| Model / API ID | Input $/1M | Output $/1M | Cached input $/1M | Conditions |
|---|---|---|---|---|
DeepSeek V4.1-Flashdeepseek-flash | 0.15 | 0.6 | 0.003 | Provider direct USD API; standard routing. Off-peak base prices. Peak input, cache reads and output cost 2×. Weekdays 01:00–04:00 and 06:00–10:00 UTC, excluding Chinese public holidays. Verified 2026-11-09. Official price ↗ |
MiniMax M3.1-FlashMiniMax-M3.1-Flash | 0.15 | 0.6 | 0.015 | Provider direct USD API; standard routing. Direct API standard rate; priority service excluded. Verified 2026-11-09. Official price ↗ |
GPT-5.6 Lunagpt-5.6-luna | 0.2 | 1.2 | 0.02 | Provider direct USD API; standard routing. Current official API rate. Above 272K input tokens: input ×2, output ×1.5; cache-write premiums excluded. Verified 2026-11-09. Official price ↗ |
Qwen 3.7 Plusqwen3.7-plus | 0.32 | 1.28 | — | Alibaba Cloud US (Virginia), US deployment. US deployment; current 20% discounted rate, up to 256K input. Above 256K: input/output ×3. Other regions differ; cache not modeled. Verified 2026-11-09. Official price ↗ |
GLM-5glm-5 | 1 | 3.2 | 0.2 | Provider direct USD API; standard routing. Direct Z.ai API; cache storage fees excluded. Verified 2026-11-09. Official price ↗ |
GPT-5.6 Terragpt-5.6-terra | 2 | 12 | 0.2 | Provider direct USD API; standard routing. Current official API rate. Above 272K input tokens: input ×2, output ×1.5; cache-write premiums excluded. Verified 2026-11-09. Official price ↗ |
Claude Opus 5.5claude-opus-5-5 | 4 | 20 | 0.2 | Claude first-party API, global routing. Global routing; US-only residency and fast mode excluded. Batch is asynchronous; this calculator does not combine batch with cache discounts. Verified 2026-11-09. Official price ↗ |
GPT-5.6 Solgpt-5.6-sol | 4 | 20 | 0.4 | Provider direct USD API; standard routing. Current official API rate. Above 272K input tokens: input ×2, output ×1.5; cache-write premiums excluded. Promotional rate through November 30, 2026; recheck before budgeting later months. Verified 2026-11-09. Official price ↗ |
Claude Fable 5claude-fable-5 | 10 | 50 | 1 | Claude first-party API, global routing. Global routing; US-only residency and fast mode excluded. Batch is asynchronous; this calculator does not combine batch with cache discounts. Verified 2026-11-09. Official price ↗ |
The same workload, different bills
100,000 requests/month × 1,000 input and 500 output tokens = 100M input and 50M output tokens. DeepSeek uses off-peak rates; other conditions appear above.
| Model | Input cost | Output cost | Total / month |
|---|---|---|---|
| DeepSeek V4.1-Flash | $15 | $30 | $45 |
| MiniMax M3.1-Flash | $15 | $30 | $45 |
| GPT-5.6 Luna | $20 | $60 | $80 |
| Qwen 3.7 Plus | $32 | $64 | $96 |
| GLM-5 | $100 | $160 | $260 |
| GPT-5.6 Terra | $200 | $600 | $800 |
| Claude Opus 5.5 | $400 | $1,000 | $1,400 |
| GPT-5.6 Sol | $400 | $1,000 | $1,400 |
| Claude Fable 5 | $1,000 | $2,500 | $3,500 |
What changes your bill?
- Cache hits reduce input costs; cache writes and storage can add costs.
- DeepSeek peak rates affect input, cached input and output.
- Verified batch models can be compared in batch mode. Batch jobs are asynchronous; this calculator excludes combined batch/cache discounts.
- Long-input tiers, routing region and current promotions can change the price. Compare quality, latency and reliability on your own tasks before switching.