The model index
Every (model, provider) pair — text LLMs plus image video audio generators — with price, context and capabilities. Blended $/1M is the effective cost of a typical 3:1 input:output request (what we rank text models by). Image/video/audio models are priced per unit by the provider (per image, per second) — not per token — so their token fields read “—”. Prices are provider-declared (via models.dev); measured evals are a later step. Machine: GET /v1/models (same filters incl. kind) · MCP: find_model.
x402 Call models through jishie. Beyond indexing, jishie delivers moderated AI generation you pay for per call in USDC — no accounts, no keys. Five services live (/v1/services): POST /v1/ai/rewrite · /translate · /summarize · /extract · /classify with an X-PAYMENT header — call unpaid and you get an HTTP 402 quoting the price, then retry paid. Backed by Gemini Flash today; more models & modalities next.
| Model | Provider | Input $/1M | Output $/1M | Blended ▼ | Context | Capabilities |
|---|---|---|---|---|---|---|
| gpt-oss-20bopenai/gpt-oss-20b | CoreWeave | $0.03 | $0.13 | $0.06 | 131k | tools · reasoning |
| Llama 3.2 11B Vision Instructmeta/llama-3.2-11b-vision-instruct | Inference | $0.055 | $0.055 | $0.06 | 16k | tools · vision |
| Llama-Guard-3-8B (Deep Infra)deepinfra/meta-llama/Llama-Guard-3-8B | Eden AI | $0.055 | $0.055 | $0.06 | 131k | |
| Manta Flash 1.0meganova-ai/manta-flash-1.0 | NanoGPT | $0.02cache $0.01 | $0.16 | $0.06 | 16k | |
| Manta Mini 1.0meganova-ai/manta-mini-1.0 | NanoGPT | $0.02cache $0.01 | $0.16 | $0.06 | 8k | |
| Qwen 3.7 Flashalibaba/qwen3.7-flash | Vercel AI Gateway | $0.03cache $0.006 | $0.13 | $0.06 | 991k | tools · reasoning · vision |
| Qwen3.7 Flashqwen3-7-flash | EmpirioLabs AI | $0.03cache $0.006 | $0.13 | $0.06 | 1M | tools · reasoning · vision |
| Qwen3.7 Flashqwen/qwen3.7-flash | NanoGPT | $0.03cache $0.006 | $0.13 | $0.06 | 992k | tools · reasoning · vision |
| Qwen3.7 Flashqwen/qwen3.7-flash | Kilo Gateway | $0.03cache $0.006 | $0.13 | $0.06 | 1M | tools · reasoning · vision |
| Qwen3.7 Flashqwen/qwen3.7-flash | OpenRouter | $0.03cache $0.006 | $0.13 | $0.06 | 1M | tools · reasoning · vision |
| Qwen3.7 Flashqwen/qwen3.7-flash | OrcaRouter | $0.03cache $0.006 | $0.13 | $0.06 | 1M | tools · reasoning · vision |
| Qwen3.7 Flashqwen3.7-flash | DevPass (LLM Gateway) | $0.03cache $0.006 | $0.13 | $0.06 | 1M | tools · reasoning · vision |
| Qwen3.7 Flash (Alibaba Cloud)alibaba/qwen3.7-flash | LLM Gateway | $0.03cache $0.006 | $0.13 | $0.06 | 1M | tools · reasoning · vision |
| Qwen3.7 Flash Thinkingqwen/qwen3.7-flash:thinking | NanoGPT | $0.03cache $0.006 | $0.13 | $0.06 | 984k | tools · reasoning · vision |
| Qwen Turboqwen/qwen-turbo | Ofox | $0.043cache $0.0086 | $0.09 | $0.05 | 128k | tools |
| Qwen Turboqwen-turbo | Alibaba (China) | $0.044 | $0.087 | $0.05 | 1M | tools · reasoning |
| Mistral Nemo 12B Instructmistral/mistral-nemo-12b-instruct | Inference | $0.038 | $0.1 | $0.05 | 16k | tools |
| nvidia--llama-3.2-nv-embedqa-1bnvidia--llama-3.2-nv-embedqa-1b | SAP AI Core | $0.07 | free | $0.05 | 8k | |
| LFM2 24B A2BLiquidAI/LFM2-24B-A2B | Pioneer | $0.03 | $0.12 | $0.05 | 33k | reasoning |
| LFM2-24B-A2BLiquidAI/LFM2-24B-A2B | Together AI | $0.03 | $0.12 | $0.05 | 33k | |
| Solar Pro 4upstage/solar-pro4 | NanoGPT | $0.03cache $0.006 | $0.12 | $0.05 | 524k | tools |
| Solar Pro 4upstage/solar-pro4 | LLMTR | $0.03 | $0.12 | $0.05 | 524k | tools · reasoning |
| Solar Pro 4 Thinkingupstage/solar-pro4:thinking | NanoGPT | $0.03cache $0.006 | $0.12 | $0.05 | 524k | tools · reasoning |
| Qwen3.7 Flashqwen3.7-flash | Alibaba (China) | $0.0296cache $0.002962 | $0.1185 | $0.05 | 1M | tools · reasoning · vision |
| Qwen-VL OCRqwen-vl-ocr | Alibaba (China) | $0.043 | $0.072 | $0.05 | 34k | vision |
| Gemma 3 4Bgoogle/gemma-3-4b-it | Merge Gateway | $0.04 | $0.08 | $0.05 | 128k | vision |
| Gemma 3 4B ITgoogle.gemma-3-4b-it | Amazon Bedrock | $0.04 | $0.08 | $0.05 | 131k | vision |
| Gemma 3 4B IT (Amazon Bedrock, US)amazon/google.gemma-3-4b-it@us | Eden AI | $0.04 | $0.08 | $0.05 | 128k | tools · vision |
| Gemma 3 4B IT (Amazon Bedrock)amazon/google.gemma-3-4b-it | Eden AI | $0.04 | $0.08 | $0.05 | 128k | tools · vision |
| Gemma 4 E2B ITgoogle.gemma-4-e2b | Amazon Bedrock | $0.04 | $0.08 | $0.05 | 131k | tools · reasoning · vision |
| L3 8B Stheno V3.2sao10K/L3-8B-stheno-v3.2 | NovitaAI | $0.05 | $0.05 | $0.05 | 8k | tools |
| Qwen/Qwen2.5-7B-InstructQwen/Qwen2.5-7B-Instruct | SiliconFlow | $0.05 | $0.05 | $0.05 | 33k | tools |
| Qwen/Qwen2.5-7B-InstructQwen/Qwen2.5-7B-Instruct | SiliconFlow (China) | $0.05 | $0.05 | $0.05 | 33k | tools |
| Sao10k L3 8B Lunaris sao10K/l3-8b-lunaris | NovitaAI | $0.05 | $0.05 | $0.05 | 8k | |
| Qwen3.7 Flashqwen3.7-flash | AIHubMix | $0.0282cache $0.00564 | $0.1128 | $0.05 | 991k | tools · reasoning |
| amazon--nova-microamazon--nova-micro | SAP AI Core | $0.03 | $0.1 | $0.05 | 128k | tools |
| Qwen3.5 4Bqwen3-5-4b | EmpirioLabs AI | $0.04cache $0.02 | $0.07 | $0.05 | 262k | tools · reasoning · vision |
| Qwen2.5 Coder 7B fastqwen2.5-coder-7b-fast | Helicone | $0.03 | $0.09 | $0.04 | 32k | |
| DeepSeek V4 Flashdeepseek/deepseek-v4-flash | Merge Gateway | $0.035cache $0.007 | $0.07 | $0.04 | 1M | tools · reasoning |
| DeepSeek V4 Flash 0731deepseek/deepseek-v4-flash-0731 | Merge Gateway | $0.035cache $0.007 | $0.07 | $0.04 | 1M | tools · reasoning |
| Qwen3 Reranker 4BQwen/Qwen3-Reranker-4B | evroc | $0.0575 | free | $0.04 | 32k | |
| Mistral Nemo Instruct 2407 TEEunsloth/Mistral-Nemo-Instruct-2407-TEE | Chutes | $0.0245cache $0.00245 | $0.0978 | $0.04 | 131k | |
| Nemotron 3 Nano Omni 30B TEENemotron-3-Nano-Omni-30B-TEE | Chutes | $0.0245cache $0.00245 | $0.0978 | $0.04 | 131k | |
| Llama 3 8B Lunarissao10k/l3-lunaris-8b | OpenRouter | $0.04 | $0.05 | $0.04 | 8k | |
| Sao10K: Llama 3 8B Lunarissao10k/l3-lunaris-8b | Kilo Gateway | $0.04 | $0.05 | $0.04 | 8k | |
| Granite 4.0 H Micro@cf/ibm-granite/granite-4.0-h-micro | Cloudflare Workers AI | $0.017 | $0.112 | $0.04 | 131k | tools |
| Granite 4.0 Microibm-granite/granite-4.0-h-micro | OpenRouter | $0.017 | $0.112 | $0.04 | 131k | |
| IBM: Granite 4.0 Microibm-granite/granite-4.0-h-micro | Kilo Gateway | $0.017 | $0.112 | $0.04 | 131k | |
| Gemma 4 E4B ITgoogle/gemma-4-E4B-it | Deep Infra | $0.02 | $0.1 | $0.04 | 131k | tools · reasoning · vision |
| GPT OSS 20B (FlexAI)flexai/gpt-oss-20b | Eden AI | $0.02cache $0.003 | $0.1 | $0.04 | 131k | tools · reasoning |
| Llama 3 8B Instructmeta-llama/llama-3-8b-instruct | NovitaAI | $0.04 | $0.04 | $0.04 | 8k | |
| Ministral 3Bministral-3b | Azure | $0.04 | $0.04 | $0.04 | 128k | tools |
| Ministral 3Bministral-3b | Azure Cognitive Services | $0.04 | $0.04 | $0.04 | 128k | tools |
| Ministral 3B (latest)mistral/ministral-3b | Vercel AI Gateway | $0.04 | $0.04 | $0.04 | 128k | tools |
| Ministral 3B (latest)ministral-3b-latest | Mistral | $0.04 | $0.04 | $0.04 | 128k | tools |
| Prompt Guard 2 86Mmeta-llama/llama-prompt-guard-2-86m | Groq | $0.04 | $0.04 | $0.04 | 512 | |
| qwen3.5-2bqwen3.5-2b | Requesty | $0.02 | $0.1 | $0.04 | 262k | tools · reasoning · vision |
| Sarvam 30Bsarvam/sarvam-30b | FastRouter | $0.02 | $0.1 | $0.04 | 128k | tools · reasoning |
| Voxtral Mini 3B 2507mistral.voxtral-mini-3b-2507 | Amazon Bedrock | $0.04 | $0.04 | $0.04 | 33k | tools |
| Voxtral Mini 3B 2507 (Amazon Bedrock, US)amazon/mistral.voxtral-mini-3b-2507@us | Eden AI | $0.04 | $0.04 | $0.04 | 128k | |
| Voxtral Mini 3B 2507 (Amazon Bedrock)amazon/mistral.voxtral-mini-3b-2507 | Eden AI | $0.04 | $0.04 | $0.04 | 128k | |
| Nomic Embed Text v1.5nomic-embed-text | Tinfoil | $0.05 | free | $0.04 | 8k | |
| GPT OSS 20Bopenai/gpt-oss-20b | Kilo Gateway | $0.018 | $0.09 | $0.04 | 131k | tools · reasoning |
| GPT OSS 20Bopenai/gpt-oss-20b | OpenRouter | $0.018 | $0.09 | $0.04 | 131k | tools · reasoning |
| Llama 3.2 3b Instructmeta-llama/llama-3.2-3b-instruct | NanoGPT | $0.0306cache $0.0153 | $0.0493 | $0.04 | 131k | |
| Llama 3.2 3B Instructmeta-llama/llama-3.2-3b-instruct | NovitaAI | $0.03 | $0.05 | $0.04 | 33k | |
| Llama 3.2 3B Instructllama-3.2-3b-instruct | DevPass (LLM Gateway) | $0.03 | $0.05 | $0.04 | 33k | |
| Llama 3.2 3B Instruct (NovitaAI)novita/llama-3.2-3b-instruct | LLM Gateway | $0.03 | $0.05 | $0.04 | 33k | |
| Qwen3-ASR Flashqwen3-asr-flash | Alibaba | $0.035 | $0.035 | $0.04 | 53k | |
| Qwen3-ASR Flashqwen3-asr-flash | Alibaba (China) | $0.032 | $0.032 | $0.03 | 53k | |
| Ling 3.0 Flashinclusionai/ling-3.0-flash | OpenRouter | $0.021cache $0.0042 | $0.063 | $0.03 | 262k | tools · reasoning |
| Ling 3.0 Flashinclusionai/ling-3.0-flash | Vercel AI Gateway | $0.021cache $0.0042 | $0.063 | $0.03 | 256k | tools · reasoning |
| Ling 3.0 Flash VLinclusionai/ling-3.0-flash-vl | OpenRouter | $0.021cache $0.0042 | $0.0616 | $0.03 | 262k | tools · reasoning · vision |
| DeepSeek-OCRdeepseek/deepseek-ocr | NovitaAI | $0.03 | $0.03 | $0.03 | 8k | vision |
| deepseek/deepseek-ocr-2deepseek/deepseek-ocr-2 | NovitaAI | $0.03 | $0.03 | $0.03 | 8k | vision |
| Llama Prompt Guard 2 22Mmeta-llama/llama-prompt-guard-2-22m | Groq | $0.03 | $0.03 | $0.03 | 512 | |
| Qwen3 4Bqwen/qwen3-4b-fp8 | NovitaAI | $0.03 | $0.03 | $0.03 | 128k | reasoning |
| Qwen3 Embedding 0.6Bqwen3-embedding-0.6b | DigitalOcean | $0.04 | free | $0.03 | 8k | |
| Llama 3.1 8B Instructmeta-llama/Meta-Llama-3.1-8B-Instruct | Abacus | $0.02 | $0.05 | $0.03 | 128k | tools |
| Llama 3.1 8B Instructmeta-llama/llama-3.1-8b-instruct | NovitaAI | $0.02 | $0.05 | $0.03 | 16k | |
| Meta Llama 3.1 8B Instructllama-3.1-8b-instruct | Helicone | $0.02 | $0.05 | $0.03 | 16k | tools |
| Llama 3.1 8B Instructmeta/llama-3.1-8b-instruct | Inference | $0.025 | $0.025 | $0.03 | 16k | tools |
| Llama-3.1-8B-Instructmeta-llama/llama-3.1-8b-instruct | Kilo Gateway | $0.02 | $0.04 | $0.03 | 131k | tools |
| Mistral Nemo Instruct 2407mistralai/Mistral-Nemo-Instruct-2407 | Meganova | $0.02 | $0.04 | $0.03 | 131k | tools |
| Mistral Nemo Instruct 2407mistralai/Mistral-Nemo-Instruct-2407 | IO.NET | $0.02cache $0.01 | $0.04 | $0.03 | 128k | tools |
| GLM-5.3 Flashzai/glm-5.3-flash | Merge Gateway | $0.015cache $0.003 | $0.05 | $0.02 | 1M | tools · reasoning · vision |
| Llama 3.1 8B (decentralized)Meta-Llama-3-1-8B-Instruct-FP8 | NanoGPT | $0.02cache $0.01 | $0.03 | $0.02 | 128k | |
| Meta Llama 3.1 8B Instruct Turbollama-3.1-8b-instruct-turbo | Helicone | $0.02 | $0.03 | $0.02 | 128k | tools |
| Mistral Nemomistralai/Mistral-Nemo-Instruct-2407 | Pioneer | $0.02 | $0.03 | $0.02 | 128k | tools |
| Mistral Nemomistralai/mistral-nemo | OpenRouter | $0.019 | $0.03 | $0.02 | 131k | tools |
| E5 Mistral 7Bintfloat/e5-mistral-7b-instruct | STACKIT | $0.02 | $0.02 | $0.02 | 4k | |
| Llama 3.2 3B Instructmeta/llama-3.2-3b-instruct | Inference | $0.02 | $0.02 | $0.02 | 16k | tools |
| PaddleOCR-VLpaddlepaddle/paddleocr-vl | NovitaAI | $0.02 | $0.02 | $0.02 | 16k | vision |
| BGE M3bge-m3 | DigitalOcean | $0.02 | free | $0.01 | 8k | |
| E5 Large v2e5-large-v2 | DigitalOcean | $0.02 | free | $0.01 | 512 | |
| Google Gemma 2gemma2-9b-it | Helicone | $0.01 | $0.03 | $0.01 | 8k | |
| text-embedding-3-smalltext-embedding-3-small | Azure | $0.02 | free | $0.01 | 8k | |
| text-embedding-3-smalltext-embedding-3-small | Azure Cognitive Services | $0.02 | free | $0.01 | 8k | |
| text-embedding-3-smalltext-embedding-3-small | SAP AI Core | $0.02 | free | $0.01 | 8k | |
| text-embedding-3-smalltext-embedding-3-small | OpenAI | $0.02 | free | $0.01 | 8k | |
| Whisper large-v3whisper-large-v3 | Privatemode AI | $0.0162 | free | $0.01 | 448 | |
| Llama 3.2 1B Instructmeta/llama-3.2-1b-instruct | Inference | $0.01 | $0.01 | $0.01 | 16k | tools |
| Meta Llama Prompt Guard 2 22Mllama-prompt-guard-2-22m | Helicone | $0.01 | $0.01 | $0.01 | 512 | |
| Meta Llama Prompt Guard 2 86Mllama-prompt-guard-2-86m | Helicone | $0.01 | $0.01 | $0.01 | 512 | |
| Qwen3 Embedding 0.6BQwen/Qwen3-Embedding-0.6B | NEAR AI Cloud | $0.01 | $0.01 | $0.01 | 33k | |
| Qwen3 Reranker 0.6BQwen/Qwen3-Reranker-0.6B | NEAR AI Cloud | $0.01 | $0.01 | $0.01 | 41k | |
| Whisper Large v3openai/whisper-large-v3 | NEAR AI Cloud | $0.01 | $0.01 | $0.01 | 448 | |
| BGE Reranker v2 M3bge-reranker-v2-m3 | DigitalOcean | $0.01 | free | $0.01 | 8k | |
| Qwen 3 Embedding 4Bqwen/qwen3-embedding-4b | Inference | $0.01 | free | $0.01 | 32k | |
| Qwen 3 Embedding 4BQwen/Qwen3-Embedding-4B | Hugging Face | $0.01 | free | $0.01 | 32k | |
| Qwen 3 Embedding 8BQwen/Qwen3-Embedding-8B | Hugging Face | $0.01 | free | $0.01 | 32k | |
| Qwen3-Embedding-8BQwen/Qwen3-Embedding-8B | Nebius Token Factory | $0.01 | free | $0.01 | 41k | |
| All-MiniLM-L6-v2all-mini-lm-l6-v2 | DigitalOcean | $0.009 | free | $0.01 | 256 | |
| Multi-QA-mpnet-base-dot-v1multi-qa-mpnet-base-dot-v1 | DigitalOcean | $0.009 | free | $0.01 | 512 | |
| Voxtral Mini 3Bvoxtral-mini-3b | Privatemode AI | $0.00462 | free | $0.00 | 32k | |
| Green Sgreen-s | GreenPT | $0.00437 | free | $0.00 | 0 | |
| Green S Progreen-s-pro | GreenPT | $0.00437 | free | $0.00 | 0 | |
| KB WhisperKBLab/kb-whisper-large | evroc | $0.0023 | $0.0023 | $0.00 | 448 | |
| Voxtral Small 24Bmistralai/Voxtral-Small-24B-2507 | evroc | $0.0023 | $0.0023 | $0.00 | 32k | |
| Whisper 3 Largeopenai/whisper-large-v3 | evroc | $0.0023 | $0.0023 | $0.00 | 448 | |
| Whisper Large v3 Turboopenai/whisper-large-v3-turbo | evroc | $0.0023 | $0.0023 | $0.00 | 448 | |
| Whisper Large v3whisper-large-v3 | Scaleway | $0.003 | free | $0.00 | 0 | |
| Active Speaker Detectionnvidia/active-speaker-detection | Nvidia | free | free | free | 0 | |
| Agentic Chat (Claude Fable 5.1)duo-chat-fable-5-1 | GitLab Duo | free | free | free | 1M | tools · reasoning · vision |
| Agentic Chat (Claude Fable 5)duo-chat-fable-5 | GitLab Duo | free | free | free | 1M | tools · reasoning · vision |
| Agentic Chat (Claude Haiku 4.5)duo-chat-haiku-4-5 | GitLab Duo | free | free | free | 200k | tools · reasoning · vision |
| Agentic Chat (Claude Opus 4.5)duo-chat-opus-4-5 | GitLab Duo | free | free | free | 200k | tools · reasoning · vision |
| Agentic Chat (Claude Opus 4.6)duo-chat-opus-4-6 | GitLab Duo | free | free | free | 1M | tools · reasoning · vision |
| Agentic Chat (Claude Opus 4.7)duo-chat-opus-4-7 | GitLab Duo | free | free | free | 1M | tools · reasoning · vision |
| Agentic Chat (Claude Opus 4.8)duo-chat-opus-4-8 | GitLab Duo | free | free | free | 1M | tools · reasoning · vision |
| Agentic Chat (Claude Opus 5.5)duo-chat-opus-5-5 | GitLab Duo | free | free | free | 1M | tools · reasoning · vision |
| Agentic Chat (Claude Opus 5)duo-chat-opus-5 | GitLab Duo | free | free | free | 1M | tools · reasoning · vision |
| Agentic Chat (Claude Sonnet 4.5)duo-chat-sonnet-4-5 | GitLab Duo | free | free | free | 200k | tools · reasoning · vision |
| Agentic Chat (Claude Sonnet 4.6)duo-chat-sonnet-4-6 | GitLab Duo | free | free | free | 1M | tools · reasoning · vision |
| Agentic Chat (Claude Sonnet 5)duo-chat-sonnet-5 | GitLab Duo | free | free | free | 1M | tools · reasoning · vision |
| Agentic Chat (GPT-5 Codex)duo-chat-gpt-5-codex | GitLab Duo | free | free | free | 400k | tools · reasoning · vision |
| Agentic Chat (GPT-5 Mini)duo-chat-gpt-5-mini | GitLab Duo | free | free | free | 400k | tools · reasoning · vision |
| Agentic Chat (GPT-5.1)duo-chat-gpt-5-1 | GitLab Duo | free | free | free | 400k | tools · reasoning · vision |
| Agentic Chat (GPT-5.2 Codex)duo-chat-gpt-5-2-codex | GitLab Duo | free | free | free | 400k | tools · reasoning · vision |
| Agentic Chat (GPT-5.2)duo-chat-gpt-5-2 | GitLab Duo | free | free | free | 400k | tools · reasoning · vision |
| Agentic Chat (GPT-5.3 Codex)duo-chat-gpt-5-3-codex | GitLab Duo | free | free | free | 400k | tools · reasoning · vision |
| Agentic Chat (GPT-5.4 Mini)duo-chat-gpt-5-4-mini | GitLab Duo | free | free | free | 400k | tools · reasoning · vision |
| Agentic Chat (GPT-5.4 Nano)duo-chat-gpt-5-4-nano | GitLab Duo | free | free | free | 400k | tools · reasoning · vision |
| Agentic Chat (GPT-5.4)duo-chat-gpt-5-4 | GitLab Duo | free | free | free | 1.1M | tools · reasoning · vision |
| Agentic Chat (GPT-5.5)duo-chat-gpt-5-5 | GitLab Duo | free | free | free | 1.1M | tools · reasoning · vision |
| Agentic Chat (GPT-5.6 Luna)duo-chat-gpt-5-6-luna | GitLab Duo | free | free | free | 1.1M | tools · reasoning · vision |
| Agentic Chat (GPT-5.6 Sol)duo-chat-gpt-5-6-sol | GitLab Duo | free | free | free | 1.1M | tools · reasoning · vision |
| Agentic Chat (GPT-5.6 Terra)duo-chat-gpt-5-6-terra | GitLab Duo | free | free | free | 1.1M | tools · reasoning · vision |
| Agentic Chat (GPT-6 Astra)duo-chat-gpt-6-astra | GitLab Duo | free | free | free | 1.1M | tools · reasoning · vision |
| Agentic Chat (GPT-6 Luna)duo-chat-gpt-6-luna | GitLab Duo | free | free | free | 1.1M | tools · reasoning · vision |
| Agentic Chat (GPT-6 Sol)duo-chat-gpt-6-sol | GitLab Duo | free | free | free | 1.1M | tools · reasoning · vision |
| Agents-A1Agents-A1 | InferX | free | free | free | 262k | tools · reasoning · vision |
| Agnes 2.0 Flashagnes-2.0-flash | Agnes AI | free | free | free | 512k | tools · reasoning · vision |
| Agnes 2.5 Flashagnes-2.5-flash | Agnes AI | free | free | free | 512k | tools · reasoning · vision |
| All-MiniLM-L12-v2mini_lm_l12_v2 | Infomaniak | free | free | free | 128 | |
| ALLaM-2-7ballam-2-7b | Groq | free | free | free | 4k | |
| Atria Dawn Previewatria-dawn-preview | DevPass (LLM Gateway) | free | free | free | 262k | tools · reasoning |
| Atria Dawn Preview (Atria)atria/atria-dawn-preview | LLM Gateway | free | free | free | 262k | tools · reasoning |
| Autotc-code-latest | Tencent Coding Plan (China) | free | free | free | 131k | tools |
| Auto Freekilo-auto/free | Kilo Gateway | free | free | free | 256k | tools · reasoning |
| Auto modelauto-model | NanoGPT | free | free | free | 1M | tools |
| Auto Routeauto | DevPass (LLM Gateway) | free | free | free | 128k | tools · vision |
| Auto Routeropenrouter/auto | Kilo Gateway | free | free | free | 2M | tools · reasoning · vision |
| bevformernvidia/bevformer | Nvidia | free | free | free | 128k | |
| BGE M3baai/bge-m3 | Nvidia | free | free | free | 8k | |
| Big Picklebig-pickle | OpenCode Zen | free | free | free | 200k | tools · reasoning |
| Body Builder (beta)openrouter/bodybuilder | Kilo Gateway | free | free | free | 128k | |
| Brick v1 Betabrick-v1-beta | Regolo AI | free | free | free | 100k | tools · vision |
| ByteDance-Seed/Seed-OSS-36B-Instructbytedance/seed-oss-36b-instruct | Nvidia | free | free | free | 262k | tools |
| Cerebras-Llama-4-Maverick-17B-128E-Instructcerebras-llama-4-maverick-17b-128e-instruct | Llama | free | free | free | 128k | tools |
| Cerebras-Llama-4-Scout-17B-16E-Instructcerebras-llama-4-scout-17b-16e-instruct | Llama | free | free | free | 128k | tools |
| Claude Fable 5claude-fable-5via jishie · up to $0.280 | Kenari | free | free | free | 1M | tools · reasoning · vision |
| Claude Opus 4.7claude-opus-4-7via jishie · up to $0.140 | Kenari | free | free | free | 1M | tools · reasoning · vision |
| Claude Opus 4.8claude-opus-4-8via jishie · up to $0.140 | Kenari | free | free | free | 1M | tools · reasoning · vision |
| Claude Opus 5claude-opus-5via jishie · up to $0.140 | Kenari | free | free | free | 1M | tools · reasoning · vision |
| Claude Sonnet 4.6claude-sonnet-4-6via jishie · up to $0.084 | Kenari | free | free | free | 1M | tools · reasoning · vision |
| Claude Sonnet 5claude-sonnet-5via jishie · up to $0.056 | Kenari | free | free | free | 1M | tools · reasoning · vision |
| Claude Sonnet 5 (Free)anthropic/claude-sonnet-5-free | ZenMux | free | free | free | 1M | tools · reasoning · vision |
| Coding GLM 5.1 (free)coding-glm-5.1-free | AIHubMix | free | free | free | 200k | tools · reasoning |
| Coding MiniMax M2.7 (Free)coding-minimax-m2.7-free | AIHubMix | free | free | free | 205k | tools · reasoning |
| Cohere: North Mini Code (free)cohere/north-mini-code:free | Kilo Gateway | free | free | free | 256k | tools · reasoning |
| Cosmos Reason2 8Bnvidia/cosmos-reason2-8b | Nvidia | free | free | free | 131k | tools · reasoning · vision |
| Custom Modelcustom | DevPass (LLM Gateway) | free | free | free | 128k | tools · vision |
| DeepSeek OCR 2deepseek-ocr-2 | Regolo AI | free | free | free | 4k | vision |
| DeepSeek R1 Distill Llama 8Bdeepseek-r1-distill-llama-8b | Alibaba (China) | free | free | free | 33k | tools · reasoning |
| DeepSeek R1 Distill Qwen 1.5Bdeepseek-r1-distill-qwen-1-5b | Alibaba (China) | free | free | free | 33k | tools · reasoning |
| DeepSeek V3.2deepseek-v3.2 | Alibaba Token Plan | free | free | free | 131k | tools · reasoning |
| DeepSeek V3.2deepseek-v3.2 | Alibaba Token Plan (China) | free | free | free | 131k | tools · reasoning |
| DeepSeek V4 Flashdeepseek-v4-flash | SenseNova (China) | free | free | free | 1M | tools · reasoning |
| DeepSeek V4 Flashdeepseek-v4-flash | Alibaba Token Plan | free | free | free | 1M | tools · reasoning |
| DeepSeek V4 Flashumans-deepseek-v4-flash-0731 | Umans AI Coding Plan | free | free | free | 1M | tools · reasoning |
| DeepSeek V4 Flashdeepseek-v4-flash | Alibaba Token Plan (China) | free | free | free | 1M | tools · reasoning |
| DeepSeek V4 Flashdeepseek-v4-flash | Pendra | free | free | free | 1M | tools · reasoning |
| DeepSeek V4 Flashdeepseek-v4-flash:free | UnoRouter | free | free | free | 1M | tools · reasoning |
| DeepSeek V4 Flashdeepseek-v4-flash | Volcengine Ark Coding Plan | free | free | free | 1M | tools · reasoning |
| DeepSeek V4 FlashDeepSeek-V4-Flash | SCNet Token Plan | free | free | free | 1M | tools · reasoning |
| DeepSeek V4 Flashdeepseek-v4-flash | Kenari | free | free | free | 1M | tools · reasoning |
| DeepSeek V4 Flash (free)deepseek/deepseek-v4-flash-free | OrcaRouter | free | free | free | 1M | tools · reasoning |
| DeepSeek V4 Flash (Free)deepseek-v4-flash:free | Kenari | free | free | free | 1M | tools · reasoning |
| DeepSeek V4 Flash 0731deepseek-v4-flash-0731 | Alibaba Token Plan | free | free | free | 1M | tools · reasoning |
Source: models.dev (loaded 2026-09-26 04:00 UTC) · provider-declared pricing · this exact query as JSON: GET /v1/models?q=… · /v1/models