# Model API pricing — AI Battle

> List prices per 1M tokens, aggregated by AI Battle (https://www.aibattle.space) from the
> "Pricing: Cache Hit, Input, and Output" dataset on 2026-09-19.
> Prices are published by the providers and can change without notice.

| Model | Provider | Input / 1M | Output / 1M | Cached input / 1M |
| --- | --- | --- | --- | --- |
| GLM-5.3-Flash | Z AI | $0.15 | $0.5 | $0.026 |
| gpt-oss-120b (high) | OpenAI | $0.15 | $0.595 | $0.125 |
| GPT-5.6 Luna (max) | OpenAI | $0.2 | $1.2 | $0.02 |
| MiniMax-M3 | MiniMax | $0.3 | $1.2 | $0.06 |
| DeepSeek V4.1 Flash (Reasoning, Max Effort) | DeepSeek | $0.3 | $1.2 | $0.006 |
| Muse Glimmer (high) | Meta | $0.35 | $1.5 | $0.04 |
| Gemini 3.5 Flash-Lite | Google | $0.3 | $2.5 | $0.03 |
| Nemotron 3 Ultra 550B A55B (Reasoning) | NVIDIA | $0.6 | $2.4 | $0.2 |
| Qwen3.8 27B (xhigh) | Alibaba | $0.5 | $3 | $0.05 |
| Gemini 3.8 Flash (high) | Google | $0.75 | $3.75 | $0.075 |
| Inkling (xhigh) | Thinking Machines | $1 | $4.05 | $0.17 |
| DeepSeek V4 Pro 0813 (Reasoning, Max Effort) | DeepSeek | $1.32 | $3.96 | $0.044 |
| Muse Spark 1.3 (max) | Meta | $1.25 | $4.25 | $0.15 |
| GLM-5.3 (max) | Z AI | $1.4 | $4.4 | $0.26 |
| Qwen3.8 2.4T A95B | Alibaba | $2 | $6 | $0.25 |
| Grok 4.6 (high) | SpaceXAI | $2 | $6 | $0.5 |
| Mistral Medium 3.5 | Mistral | $1.5 | $7.5 | $0.15 |
| GPT-5.6 Terra (max) | OpenAI | $2 | $12 | $0.2 |
| Kimi K3 (max) | Kimi | $3 | $15 | $0.3 |
| GPT-5.6 Sol (max) | OpenAI | $4 | $20 | $0.4 |

Full ranking: https://www.aibattle.space/rankings/llm-models-pricing-cache-hit-input-and-output