Search a model or provider to see that exact choice's offerings. Leave it blank to browse every eligible model and compare broad options.
More filters
Your Usage
Agentic: a cache-heavy agent workload β most prompt tokens are cached reads, with a small fresh input and output share.
Assumes all fresh input is cached where a higher cache-write rate is published, unless provider-specific default billing is known. Additional cache-storage charges are excluded.
Results
Ranked by lowest estimated total cost for your workload. Total cost and blended $/M use the same token mix and fresh-input cache-write assumption; only total cost scales with volume and monthly mode.
Rules we donβt bend
- Unknown stays unknown. An unpublished price shows as βββ, never as $0. Missing privacy metadata is not a privacy claim.
- Zero is not free. Zero-priced placeholders and :free routes are dropped, never shown as a free offering.
- Promos are labelled. Discounted prices always carry a promo badge, so a sale is never mistaken for the regular rate.
- Published rates stay raw. We normalize units to $/M but never edit a providerβs rate; estimates are computed on top.
- The providerβs own price wins. A direct provider API outranks aggregators and resellers for the same offering.
- Estimates, not invoices. Costs use your stated token mix; cache-storage charges and taxes are excluded.
Frequently asked questions
Where are the full FAQ lists?
All questions β choosing a model and provider, text/token pricing, image and video generation pricing, and plain-language benchmark explainers β live on the consolidated FAQ page.
Cheapest LLM API models right now
Ranked by effective cost at a typical agentic mix (2.5% input, 97% cached input, 0.5% output). Prices are USD per million tokens. Use the calculator above to estimate your workload cost.
| Org | Provider | Model | Input $/M | Output $/M | Cache $/M | Blended $/M |
|---|---|---|---|---|---|---|
| deepseek | baidu | DeepSeek: DeepSeek V4.1 Flash | $0.045 | $0.179 | $0.0009 | $0.0029 |
| nex-agi | nex-agi | Nex AGI: Nex-N2.5-Mini | $0.025 | $0.100 | $0.0025 | $0.0036 |
| deepseek | baidu | DeepSeek: DeepSeek V4 Flash 0731 | $0.054 | $0.161 | $0.0017 | $0.0038 |
| openai | openai | OpenAI: GPT-5 Nano (flex) | $0.025 | $0.200 | $0.0025 | $0.0040 |
| openai | openai | OpenAI: GPT-5 Nano (batch) | $0.025 | $0.200 | $0.0025 | $0.0040 |
| inclusionai | novita | inclusionAI: Ling 3.0 Flash | $0.021 | $0.063 | $0.0042 | $0.0049 |
| deepseek | deepinfra | DeepSeek: DeepSeek V4.1 Flash 1017 (flex) | $0.078 | $0.235 | $0.0024 | $0.0054 |
| meta | meta-contributor | Muse Spark 1.3 Contributor | $0.100 | $0.200 | $0.0020 | $0.0054 |
| meta | meta-contributor | Muse Spark 1.2 Contributor | $0.100 | $0.200 | $0.0020 | $0.0054 |
| meta | meta | Meta: Muse Spark 1.3 Contributor | $0.100 | $0.200 | $0.0020 | $0.0054 |
| meta | meta | Meta: Muse Spark 1.2 Contributor | $0.100 | $0.200 | $0.0020 | $0.0054 |
| meta | opencode | Muse Spark 1.3 Contributor | $0.100 | $0.200 | $0.0020 | $0.0054 |
| meta | opencode | Muse Spark 1.2 Contributor | $0.100 | $0.200 | $0.0020 | $0.0054 |
| deepseek | openscale | DeepSeek: DeepSeek V4.1 Flash | $0.060 | $0.240 | $0.0030 | $0.0056 |
| deepseek | openscale | DeepSeek: DeepSeek V4.1 Flash 1017 | $0.060 | $0.240 | $0.0030 | $0.0056 |
| deepseek | openscale | DeepSeek: DeepSeek V4.1 Flash 0910 | $0.060 | $0.240 | $0.0030 | $0.0056 |
| inception | inception | Inception: Mercury 2.5 | $0.040 | $0.150 | $0.0040 | $0.0056 |
| deepseek | wafer | DeepSeek-V4.1-Flash-1017 | $0.130 | $0.500 | $0 | $0.0057 |
| deepseek | singularity | deepseek-v4.1-flash-1017 | $0.090 | $0.360 | $0.0018 | $0.0058 |
| deepseek | sail-research | DeepSeek: DeepSeek V4.1 Flash (batch) | $0.050 | $0.150 | $0.0040 | $0.0059 |
| deepseek | refuseless | DeepSeek V4.1 Flash 1017 (Safeguards) | $0.050 | $0.150 | $0.0040 | $0.0059 |
| xiaomi | makora | Xiaomi: MiMo-V2.6-Flash | $0.130 | $0.280 | $0.0020 | $0.0066 |
| xiaomi | gmicloud | Xiaomi: MiMo-V2.6-Flash | $0.119 | $0.238 | $0.0026 | $0.0066 |
| xiaomi | gmicloud | Xiaomi: MiMo-V2.5 | $0.119 | $0.238 | $0.0026 | $0.0066 |
| xiaomi | consensusprotocol | MiMo V2.6 Flash | $0.120 | $0.250 | $0.0025 | $0.0067 |
Catalog snapshot 2026-10-29 from direct-provider APIs, OpenRouter endpoint data, and maintained fallbacks. See the sources and calculation rules; verify rates on the provider's official pricing page before committing spend.
Explore TokenWatch data
Find an open model for your use case Β· Compare benchmarks by use case Β· Compare models across providers Β· Browse inference providers Β· Read the pricing methodology Β· Use the pricing API Β· Read the FAQ