Model rankings
Cost leaderboard
Ranked by documented input price per million tokens, lowest first.
Top models
Cost ranking
| Rank | Model | Creator | Input / 1M | Context | Last verified |
|---|---|---|---|---|---|
| 1 | accounts/fireworks/models/flux-1-dev-controlnet-union | Fireworks_Ai | $0.001 | 4.096K | Jul 31, 2026 |
| 2 | Whisper 3 Large | OpenAI | $0.002 | 448 | Sep 11, 2026 |
| 3 | Whisper Large v3 Turbo | OpenAI | $0.002 | 448 | Sep 11, 2026 |
| 4 | fireworks-ai-embedding-up-to-150m | Fireworks_Ai Embedding Models | $0.008 | Not documented | Jul 31, 2026 |
| 5 | Qwen/Qwen2.5-Coder-3B-Instruct | Nscale | $0.01 | Not documented | Jul 31, 2026 |
| 6 | inclusionAI: Ling-2.6-flash | Inclusionai | $0.01 | 262.144K | Aug 24, 2026 |
| 7 | Qwen/Qwen2.5-Coder-7B-Instruct | Nscale | $0.01 | Not documented | Jul 31, 2026 |
| 8 | Qwen/Qwen2.5-Coder-7B | Nebius | $0.01 | 32.768K | Jul 31, 2026 |
| 9 | gpt-oss-20b | Darkbloom | $0.015 | 131.072K | Jul 31, 2026 |
| 10 | llama3.2-11b-vision-instruct | Lambda_Ai | $0.015 | 131.072K | Jul 31, 2026 |
| 11 | llama3.2-3b-instruct | Lambda_Ai | $0.015 | 131.072K | Jul 31, 2026 |
| 12 | fireworks-ai-embedding-150m-to-350m | Fireworks_Ai Embedding Models | $0.016 | Not documented | Jul 31, 2026 |
| 13 | IBM: Granite 4.0 Micro | IBM | $0.017 | 131K | Sep 11, 2026 |
| 14 | @cf/ibm-granite/granite-4.0-h-micro | Cloudflare | $0.017 | 131K | Jul 31, 2026 |
| 15 | Mistral: Mistral Nemo | Mistral AI | $0.019 | 131.072K | Sep 11, 2026 |
| 16 | mistralai/mistral-nemo | Openrouter | $0.019 | 131.072K | Sep 05, 2026 |
| 17 | meta-llama/Meta-Llama-3.1-8B-Instruct | Nebius | $0.02 | 128K | Jul 31, 2026 |
| 18 | openai/gpt-oss-20b | Openrouter | $0.02 | 131.072K | Jul 31, 2026 |
| 19 | meta-llama/Llama-3.2-3B-Instruct | Deepinfra | $0.02 | 131.072K | Jul 31, 2026 |
| 20 | paddlepaddle/paddleocr-vl | Novita | $0.02 | 16.384K | Jul 31, 2026 |
| 21 | Qwen/Qwen2-VL-7B-Instruct | Nebius | $0.02 | 131.072K | Jul 31, 2026 |
| 22 | amazon/titan-embed-text-v2 | Vercel_Ai_Gateway | $0.02 | Not documented | Jul 31, 2026 |
| 23 | Llama-3.1-8B-Instruct | Meta | $0.02 | 128K | Sep 11, 2026 |
| 24 | meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo | Deepinfra | $0.02 | 131.072K | Jul 31, 2026 |
| 25 | meta-llama/Llama-Guard-3-8B | Nebius | $0.02 | 128K | Jul 31, 2026 |
| 26 | GPT OSS 20B | OpenAI | $0.02 | 131.072K | Sep 11, 2026 |
| 27 | meta-llama/llama-3.1-8b-instruct | Novita | $0.02 | 16.384K | Jul 31, 2026 |
| 28 | google/gemma-4-E4B-it | Deepinfra | $0.02 | 131.072K | Aug 28, 2026 |
| 29 | Gemma 4 E4B IT | $0.02 | 131.072K | Sep 11, 2026 | |
| 30 | meta-llama/llama-3.2-1b-instruct | Novita | $0.02 | 131K | Aug 28, 2026 |
| 31 | Sarvam 30B | Sarvam | $0.02 | 128K | Sep 11, 2026 |
| 32 | mistralai/Mistral-Nemo-Instruct-2407 | Deepinfra | $0.02 | 131.072K | Jul 31, 2026 |
| 33 | inclusionAI: Ling 3.0 Flash | Inclusionai | $0.021 | 262.144K | Sep 11, 2026 |
| 34 | Seed 1.6 Flash | Bytedance Seed | $0.022 | 256K | Sep 11, 2026 |
| 35 | hermes3-8b | Lambda_Ai | $0.025 | 131.072K | Jul 31, 2026 |
| 36 | llama3.1-8b-instruct | Lambda_Ai | $0.025 | 131.072K | Jul 31, 2026 |
| 37 | Nex AGI: Nex-N2-Mini | Nex Agi | $0.025 | 262.144K | Sep 08, 2026 |
| 38 | OpenAI: GPT-5 Nano (batch) | OpenAI | $0.025 | 400K | Sep 11, 2026 |
| 39 | lfm-7b | Lambda_Ai | $0.025 | 131.072K | Jul 31, 2026 |
| 40 | deepseek-ai/DeepSeek-R1-Distill-Llama-8B | Nscale | $0.025 | Not documented | Jul 31, 2026 |
| 41 | @cf/meta/llama-3.2-1b-instruct | Cloudflare | $0.027 | 60K | Jul 31, 2026 |
| 42 | meta-llama/llama-3.2-1b-instruct | Openrouter | $0.027 | 60K | Sep 05, 2026 |
| 43 | Meta: Llama 3.2 1B Instruct | Meta | $0.027 | 60K | Sep 11, 2026 |
| 44 | Qwen3.7 Flash | Alibaba Qwen | $0.028 | 1M | Sep 11, 2026 |
| 45 | Qwen3.5 Flash | Alibaba Qwen | $0.029 | 1M | Sep 11, 2026 |
| 46 | Seed 2.0 Mini | Bytedance Seed | $0.03 | 256K | Sep 11, 2026 |
| 47 | gemma3-4b | Llamagate | $0.03 | 128K | Jul 31, 2026 |
| 48 | meta-llama/llama-3.2-3b-instruct | Novita | $0.03 | 32.768K | Jul 31, 2026 |
| 49 | qwen/qwen3-4b-fp8 | Novita | $0.03 | 128K | Jul 31, 2026 |
| 50 | llama-3.1-8b | Llamagate | $0.03 | 131.072K | Jul 31, 2026 |
| 51 | DeepSeek OCR 2 | DeepSeek | $0.03 | 8.192K | Sep 11, 2026 |
| 52 | deepseek/deepseek-ocr-2 | Novita | $0.03 | 8.192K | Aug 28, 2026 |
| 53 | deepseek/deepseek-ocr | Novita | $0.03 | 8.192K | Jul 31, 2026 |
| 54 | GPT OSS 120B | OpenAI | $0.03 | 131.072K | Sep 11, 2026 |
| 55 | ibm-granite/granite-3.3-8b-instruct | Replicate | $0.03 | Not documented | Jul 31, 2026 |
| 56 | meta-llama/Meta-Llama-3.1-8B-Instruct | Deepinfra | $0.03 | 131.072K | Jul 31, 2026 |
| 57 | gemma-4-26b | Darkbloom | $0.03 | 131.072K | Jul 31, 2026 |
| 58 | meta-llama/llama-prompt-guard-2-22m | Groq | $0.03 | 512 | Aug 13, 2026 |
| 59 | qwen/qwen3.7-flash | Openrouter | $0.03 | 1M | Sep 05, 2026 |
| 60 | meta-llama/Llama-3.1-8B-Instruct | Nscale | $0.03 | Not documented | Jul 31, 2026 |
| 61 | meta-llama/Meta-Llama-3-8B-Instruct | Deepinfra | $0.03 | 8.192K | Jul 31, 2026 |
| 62 | Qwen: Qwen3.7 Flash | Alibaba Qwen | $0.03 | 1M | Sep 11, 2026 |
| 63 | qwen/qwen3-8b-fp8 | Novita | $0.035 | 128K | Jul 31, 2026 |
| 64 | amazon.nova-micro-v1:0 | Bedrock_Converse | $0.035 | 128K | Jul 31, 2026 |
| 65 | zai-org/autoglm-phone-9b-multilingual | Novita | $0.035 | 65.536K | Jul 31, 2026 |
| 66 | Amazon: Nova Micro 1.0 | Amazon | $0.035 | 128K | Sep 11, 2026 |
| 67 | nova-micro-v1 | Amazon_Nova | $0.035 | 128K | Jul 31, 2026 |
| 68 | us.amazon.nova-micro-v1:0 | Bedrock_Converse | $0.035 | 128K | Jul 31, 2026 |
| 69 | Nova Micro | Amazon | $0.035 | 128K | Sep 11, 2026 |
| 70 | amazon/nova-micro | Vercel_Ai_Gateway | $0.035 | 128K | Jul 31, 2026 |
| 71 | apac.amazon.nova-micro-v1:0 | Bedrock_Converse | $0.037 | 128K | Jul 31, 2026 |
| 72 | command-r7b-12-2024 | Cohere_Chat | $0.037 | 128K | Jul 31, 2026 |
| 73 | Command R7B | Cohere | $0.037 | 128K | Sep 11, 2026 |
| 74 | Command R7B Arabic | Cohere | $0.037 | 128K | Sep 11, 2026 |
| 75 | llama-3.2-3b | Llamagate | $0.04 | 131.072K | Jul 31, 2026 |
| 76 | qwen3-8b | Llamagate | $0.04 | 32.768K | Jul 31, 2026 |
| 77 | meta-llama/llama-prompt-guard-2-86m | Groq | $0.04 | 512 | Aug 13, 2026 |
| 78 | google.gemma-3-4b-it | Bedrock_Converse | $0.04 | 128K | Jul 31, 2026 |
| 79 | google.gemma-4-e2b | Bedrock_Mantle | $0.04 | 128K | Jul 31, 2026 |
| 80 | openai/gpt-oss-20b | Deepinfra | $0.04 | 131.072K | Jul 31, 2026 |
| 81 | openai/gpt-oss-20b | Novita | $0.04 | 131.072K | Jul 31, 2026 |
| 82 | mistralai/mistral-nemo | Novita | $0.04 | 60.288K | Jul 31, 2026 |
| 83 | meta-llama/llama-3-8b-instruct | Novita | $0.04 | 8.192K | Jul 31, 2026 |
| 84 | Gemma 3 4B IT | $0.04 | 131.072K | Sep 11, 2026 | |
| 85 | Qwen/Qwen2.5-7B-Instruct | Deepinfra | $0.04 | 32.768K | Jul 31, 2026 |
| 86 | Meta-Llama-3.2-1B-Instruct | Sambanova | $0.04 | 16.384K | Jul 31, 2026 |
| 87 | ministral-3b | Azure_Ai | $0.04 | 128K | Jul 31, 2026 |
| 88 | Sao10K: Llama 3 8B Lunaris | Sao10K | $0.04 | 8.192K | Sep 11, 2026 |
| 89 | gpt-oss-20b | Ovhcloud | $0.04 | 131K | Jul 31, 2026 |
| 90 | nvidia/NVIDIA-Nemotron-Nano-9B-v2 | Deepinfra | $0.04 | 131.072K | Jul 31, 2026 |
| 91 | Qwen3.5 9B | Alibaba Qwen | $0.04 | 262.144K | Sep 11, 2026 |
| 92 | mistralai/Mistral-Nemo-Instruct-2407 | Nebius | $0.04 | 128K | Jul 31, 2026 |
| 93 | Inception: Mercury 2.5 | Inception | $0.04 | 260K | Sep 11, 2026 |
| 94 | mistral/ministral-3b | Vercel_Ai_Gateway | $0.04 | 128K | Jul 31, 2026 |
| 95 | Gemma 4 E2B IT | $0.04 | 131.072K | Sep 11, 2026 | |
| 96 | Sao10K/L3-8B-Lunaris-v1-Turbo | Deepinfra | $0.04 | 8.192K | Jul 31, 2026 |
| 97 | Sarvam 105B | Sarvam | $0.04 | 131.072K | Sep 11, 2026 |
| 98 | google/gemma-3-4b-it | Deepinfra | $0.04 | 131.072K | Jul 31, 2026 |
| 99 | mistral.voxtral-mini-3b-2507 | Bedrock_Converse | $0.04 | 128K | Jul 31, 2026 |
| 100 | us-gov-west-1/amazon.nova-micro-v1:0 | Bedrock | $0.042 | 128K | Sep 09, 2026 |