Fournisseur · 2026-09-28
kilo
82 modèles canoniques112 entrées au total (dérivés inclus)
| Modèle | Entrée / 1M | Sortie / 1M | Contexte | Fournisseurs | Tags |
|---|---|---|---|---|---|
| IBM: Granite 4.0 Micro | $0.017 | $0.112 | 131K | 1 | — |
| Amazon: Nova Micro 1.0 | $0.035 | $0.140 | 128K | 1 | tools |
| Inference.net: Schematron V2 Turbo | $0.030 | $0.150 | 128K | 1 | json |
| MythoMax 13B | $0.080 | $0.110 | 4K | 1 | json |
| Reka Edge | $0.100 | $0.100 | 16K | 1 | tools · json · vision |
| Tencent: Hy-MT2-1.8B | $0.044 | $0.177 | 8K | 1 | — |
| inclusionAI: Ling 3.0 Flash | $0.060 | $0.180 | 262K | 1 | tools · reasoning |
| inclusionAI: Ling 3.0 Flash Fin | $0.060 | $0.180 | 262K | 1 | tools · json · reasoning |
| Inference.net: Schematron V2 Small | $0.050 | $0.230 | 128K | 1 | json |
| inclusionAI: Ling 3.0 Flash VL | $0.075 | $0.220 | 262K | 1 | tools · json · reasoning · vision |
| Amazon: Nova Lite 1.0 | $0.060 | $0.240 | 300K | 1 | tools · vision |
| Poolside: Laguna S 2.1 | $0.100 | $0.200 | 1.05M | 1 | tools · reasoning |
| Poolside: Laguna XS 2.1 | $0.100 | $0.200 | 262K | 1 | tools · reasoning |
| Reka Flash 3 | $0.100 | $0.200 | 66K | 1 | json · reasoning |
| IBM: Granite 4.2 8B | $0.060 | $0.250 | 131K | 1 | tools · json · reasoning |
| Tencent: Hy-MT2-30B-A3B | $0.074 | $0.295 | 8K | 1 | json |
| Tencent: Hy-MT2-7B | $0.074 | $0.295 | 8K | 1 | json |
| ByteDance Seed: Seed 1.6 Flash | $0.075 | $0.300 | 262K | 1 | tools · json · reasoning · vision |
| Auto Small | $0.050 | $0.400 | 262K | 1 | tools · reasoning · vision |
| Seed 2.0 Mini | $0.100 | $0.400 | 262K | 1 | tools · json · reasoning · vision |
| PrismML: Ternary Bonsai 2 27B | $0.075 | $0.500 | 262K | 1 | tools · json · reasoning · vision |
| OpenAI: GPT Luna Latest | $0.100 | $0.500 | 1.05M | 1 | tools · json · reasoning · vision |
| Hy3 | $0.130 | $0.530 | 262K | 1 | tools · json · reasoning · open-weights |
| Tencent: Hunyuan A13B Instruct | $0.140 | $0.570 | 131K | 1 | json · reasoning |
| Hy3 preview | $0.180 | $0.600 | 262K | 1 | tools · reasoning · open-weights |
| TheDrummer: UnslopNemo 12B | $0.400 | $0.400 | 1.02M | 1 | json |
| TheDrummer: Cydonia 24B V4.1 | $0.300 | $0.500 | 131K | 1 | json |
| ReMM SLERP 13B | $0.350 | $0.650 | 6K | 1 | json |
| Trinity Large Thinking | $0.250 | $0.800 | 262K | 1 | tools · reasoning · open-weights |
| Venice: Uncensored | $0.200 | $0.900 | 128K | 1 | — |
| Mancer: Weaver (alpha) | $0.400 | $0.750 | 8K | 1 | — |
| TheDrummer: Skyfall 36B V2 | $0.550 | $0.800 | 33K | 1 | json |
| Nous: Hermes 3 70B Instruct | $0.700 | $0.700 | 131K | 1 | json |
| Perceptron: Perceptron Mk1 | $0.150 | $1.50 | 33K | 1 | json · reasoning · vision |
| Perceptron: Perceptron Mk1.5 | $0.150 | $1.50 | 37K | 1 | tools · json · reasoning · vision |
| Inkling Small | $0.450 | $1.20 | 524K | 1 | tools · reasoning · vision · open-weights |
| Nous: Hermes 3 405B Instruct | $1.00 | $1.00 | 131K | 1 | json |
| AionLabs: Aion 3.5 Mini | $0.700 | $1.40 | 262K | 1 | tools · reasoning |
| AionLabs: Aion-3.0-Mini | $0.700 | $1.40 | 131K | 1 | tools · reasoning |
| Relace: Relace Apply 3 | $0.850 | $1.25 | 256K | 1 | — |
| Seed 2.0 Lite | $0.250 | $2.00 | 262K | 1 | tools · json · reasoning · vision |
| ByteDance Seed: Seed 1.6 | $0.250 | $2.00 | 262K | 1 | tools · json · reasoning · vision |
| Auto Efficient | $0.325 | $1.95 | 1M | 1 | tools · reasoning · vision |
| Auto Balanced | $0.325 | $1.95 | 1M | 1 | tools · reasoning · vision |
| AionLabs: Aion-2.0 | $0.800 | $1.60 | 131K | 1 | tools · reasoning |
| AionLabs: Aion-RP 1.0 (8B) | $0.800 | $1.60 | 33K | 1 | — |
| Amazon: Nova 2 Lite | $0.300 | $2.50 | 1M | 1 | tools · reasoning · vision |
| ByteDance Seed: Seed 2.1 Turbo | $0.500 | $2.50 | 262K | 1 | tools · json · reasoning · vision |
| Hy4 preview | $0.834 | $2.50 | 1.05M | 1 | tools · json · reasoning · open-weights |
| Seed 2.0 Code | $0.500 | $3.00 | 262K | 1 | tools · json · reasoning · vision |
| Nous: Hermes 4 405B | $1.00 | $3.00 | 131K | 1 | reasoning |
| Amazon: Nova Pro 1.0 | $0.800 | $3.20 | 300K | 1 | tools · vision |
| Relace: Relace Search | $1.00 | $3.00 | 256K | 1 | tools |
| Sakana Namazu | $0.950 | $4.00 | 262K | 1 | tools · json · reasoning · vision |
| Inkling | $0.950 | $4.05 | 524K | 1 | tools · reasoning · vision · open-weights |
| OpenAI: GPT Mini Latest | $0.750 | $4.50 | 400K | 1 | tools · json · reasoning · vision |
| Writer: Palmyra X5 | $0.600 | $6.00 | 1.04M | 1 | — |
| Magnum v4 72B | $2.50 | $5.00 | 33K | 1 | json |
| Sakana: Fugu Max | $2.00 | $6.00 | 1M | 1 | tools · json · reasoning · vision |
| AionLabs: Aion-3.0 | $3.00 | $6.00 | 131K | 1 | tools · reasoning |
| AionLabs: Aion 3.5 | $3.00 | $6.00 | 262K | 1 | tools · reasoning |
| Pareto | $2.50 | $7.50 | 262K | 1 | tools · vision |
| OpenAI: GPT Sol Latest | $2.00 | $10.00 | 1.05M | 1 | tools · json · reasoning · vision |
| OpenAI: GPT Terra Latest | $2.00 | $12.00 | 1.05M | 1 | tools · json · reasoning · vision |
| Amazon: Nova Premier 1.0 | $2.50 | $12.50 | 1M | 1 | tools · vision |
| Fireworks: Ember-1 | $3.00 | $15.00 | 1.05M | 1 | tools · json · reasoning · vision |
| Auto Frontier | $5.00 | $25.00 | 1M | 1 | tools · reasoning · vision |
| Sakana: Fugu Ultra v2 | $5.00 | $30.00 | 1M | 1 | tools · json · reasoning · vision |
| Fugu Ultra | $5.00 | $30.00 | 1M | 1 | tools · json · reasoning · vision |
| OpenAI: GPT Astra Latest ($$$$) | $10.00 | $50.00 | 1.05M | 1 | tools · json · reasoning · vision |
| Auto Router | Inconnu | Inconnu | 2M | 1 | tools · reasoning · vision |
| Body Builder (beta) | Inconnu | Inconnu | 128K | 1 | — |
| Dots Studio: Dots3-Note Preview (free) | Inconnu | Inconnu | 512K | 1 | tools · json · reasoning · vision |
| inclusionAI: Ling 3.0 Flash Fin (free) | Inconnu | Inconnu | 262K | 1 | tools · reasoning |
| inclusionAI: Ling 3.0 Flash Sante (free) | Inconnu | Inconnu | 262K | 1 | tools · reasoning |
| LiquidAI: LFM2.5-2.6B (free) | Inconnu | Inconnu | 66K | 1 | tools · json · reasoning |
| OpenRouter Free Models Router | Inconnu | Inconnu | 200K | 2 | tools · json · reasoning · vision |
| Pareto Code Router | Inconnu | Inconnu | 200K | 1 | — |
| Poolside: Laguna S 2.1 (free) | Inconnu | Inconnu | 262K | 1 | tools · reasoning |
| Poolside: Laguna XS 2.1 (free) | Inconnu | Inconnu | 262K | 1 | tools · reasoning |
| Space Bunny Alpha (new) | Inconnu | Inconnu | 1M | 1 | tools · reasoning · vision |
| Thinking Machines: Inkling Small (free) | Inconnu | Inconnu | 1.05M | 1 | tools · reasoning · vision · open-weights |
| ByteDance: UI-TARS 7B dérivé | $0.100 | $0.200 | 128K | 1 | json · vision |
| Qwen: Qwen2.5 7B Instructdérivé | $0.100 | $0.200 | 33K | 1 | tools · json |
| Qwen: Qwen3.5-Flashdérivé | $0.065 | $0.260 | 1M | 1 | tools · json · reasoning · vision |
| Qwen: Qwen Plus 0728 (retires Oct 9)dérivé | $0.260 | $0.780 | 1M | 1 | tools · json |
| DeepSeek: DeepSeek V3.1dérivé | $0.270 | $1.00 | 164K | 1 | tools · json · reasoning |
| Google: Gemma 2 27Bdérivé | $0.650 | $0.650 | 8K | 1 | json |
| DeepSeek: DeepSeek V3 0324dérivé | $0.290 | $1.14 | 164K | 1 | tools · json |
| Qwen2.5 Coder 32B Instructdérivé | $0.660 | $1.00 | 33K | 1 | — |
| Cohere: Command A+dérivé | $0.300 | $1.50 | 192K | 1 | tools · json · reasoning · vision |
| Qwen: Qwen3.5 Plus 2026-02-15dérivé | $0.260 | $1.56 | 1M | 1 | tools · json · reasoning · vision |
| DeepSeek: DeepSeek Pro Latestdérivé | $0.128 | $1.96 | 1.05M | 1 | tools · json · reasoning |
| Qwen: Qwen3.5 Plus 2026-04-20dérivé | $0.300 | $1.80 | 1M | 1 | tools · json · reasoning · vision |
| Qwen: Qwen3 VL 8B Thinking (retires Oct 9)dérivé | $0.180 | $2.10 | 131K | 1 | tools · json · reasoning · vision |
| OpenAI: GPT Audio Minidérivé | $0.600 | $2.40 | 128K | 1 | tools · json |
| OpenAI: GPT-3.5 Turbo (older v0613)dérivé | $1.00 | $2.00 | 4K | 1 | tools · json |
| OpenAI: GPT-5 Image Minidérivé | $2.50 | $2.00 | 400K | 1 | json · reasoning · vision |
| OpenAI: GPT-3.5 Turbo 16kdérivé | $3.00 | $4.00 | 16K | 1 | tools · json |
| Mistral Large 2407dérivé | $2.00 | $6.00 | 131K | 1 | tools · json |
| Google: Gemini 2.5 Pro Preview 06-05dérivé | $1.25 | $10.00 | 1.05M | 1 | tools · json · reasoning · vision |
| Z.ai: GLM 5.3 Primedérivé | $2.80 | $8.80 | 1M | 1 | tools · reasoning |
| OpenAI: GPT Audiodérivé | $2.50 | $10.00 | 128K | 1 | tools · json |
| OpenAI: GPT-5.2 Chatdérivé | $1.75 | $14.00 | 128K | 1 | tools · json · vision |
| Perplexity: Sonar Pro Searchdérivé | $3.00 | $15.00 | 200K | 1 | json · reasoning · vision |
| OpenAI: GPT-5 Image ($$$$)dérivé | $10.00 | $10.00 | 400K | 1 | json · reasoning · vision |
| OpenAI: GPT-5.4 Image 2dérivé | $8.00 | $15.00 | 272K | 1 | json · reasoning · vision |
| Cohere: North Mini Code (free)dérivé | Inconnu | Inconnu | 256K | 1 | tools · reasoning |
| NVIDIA: Nemotron 3 Nano Omni (free)dérivé | Inconnu | Inconnu | 256K | 1 | tools · reasoning · vision · open-weights |
| NVIDIA: Nemotron 3.5 Content Safety (free)dérivé | Inconnu | Inconnu | 128K | 1 | reasoning · vision · open-weights |
| Qwen: Qwen3.8 27B (free)dérivé | Inconnu | Inconnu | 262K | 1 | tools · json · reasoning · vision · open-weights |
| StepFun: Step 3.7 Flash (free)dérivé | Inconnu | Inconnu | 262K | 1 | tools · reasoning · vision · open-weights |
Frequently asked questions
How many AI models does kilo offer?
We track 82 canonical kilo models plus 30 community fine-tunes / derivatives (excluded from the main table). The list is recomputed daily.
Which kilo model is the cheapest?
IBM: Granite 4.0 Micro is currently the lowest-priced kilo model, at $0.017 per 1M input tokens and $0.112 per 1M output tokens. For the full apples-to-apples list, see /pricing/cheapest-llm-api.
Which kilo model has the largest context window?
Auto Router leads at 2M tokens. This is the total of prompt + completion.
Which kilo models support tool calling?
Multiple kilo models support tool calling, with Amazon: Nova Micro 1.0 being a popular pick. The capability column in the table above marks every model with kilo tool-calling support.
Which kilo models accept image input?
Reka Edge accepts image input. Other vision-capable kilo models are tagged 'vision' in the table above. See /capabilities/vision for a cross-vendor comparison.
What are the best alternatives to kilo?
Depends on the use case. For raw cost savings, look at /pricing/cheapest-llm-api. For agent-oriented workloads, /best/best-ai-model-for-agents. For long-document workflows, /best/best-long-context-llm.
How fresh is this kilo pricing data?
Daily. Our pipeline syncs every morning and rebuilds these pages on data change, so list-price moves and new model releases land within roughly 24 hours.
Explore more
Top kilo models
- OpenRouter Free Models RouterUnknown pricing
- IBM: Granite 4.0 Micro$0.02 in / $0.11 out
- Amazon: Nova Micro 1.0$0.04 in / $0.14 out
- Inference.net: Schematron V2 Turbo$0.03 in / $0.15 out
- MythoMax 13B$0.08 in / $0.11 out
Browse by use case
Browse by capability
Dernière mise à jour :
Prices in USD per 1M tokens. Unknown means the provider does not publish per-token pricing.
Pricing and capabilities are refreshed daily and reconciled against each provider's official documentation. Always verify critical production decisions with the provider directly.