Models
Browse available AI models that you can use with characters.
Free Models
Name | Context Length | Input ($/1M Tokens) | Output ($/1M Tokens) |
---|---|---|---|
Moonshot AI: Kimi VL A3B Thinking (free)m:moonshotai/kimi-vl-a3b-thinking:free | 131,072 | Free | Free |
NVIDIA: Llama 3.1 Nemotron Nano 8B v1 (free)m:nvidia/llama-3.1-nemotron-nano-8b-v1:free | 131,072 | Free | Free |
NVIDIA: Llama 3.3 Nemotron Super 49B v1 (free)m:nvidia/llama-3.3-nemotron-super-49b-v1:free | 131,072 | Free | Free |
NVIDIA: Llama 3.1 Nemotron Ultra 253B v1 (free)m:nvidia/llama-3.1-nemotron-ultra-253b-v1:free | 131,072 | Free | Free |
Meta: Llama 4 Maverick (free)m:meta-llama/llama-4-maverick:free | 256,000 | Free | Free |
Meta: Llama 4 Scout (free)m:meta-llama/llama-4-scout:free | 512,000 | Free | Free |
DeepSeek: DeepSeek V3 Base (free)m:deepseek/deepseek-v3-base:free | 131,072 | Free | Free |
AllenAI: Molmo 7B D (free)m:allenai/molmo-7b-d:free | 4,096 | Free | Free |
Bytedance: UI-TARS 72B (free)m:bytedance-research/ui-tars-72b:free | 32,768 | Free | Free |
Qwen: Qwen2.5 VL 3B Instruct (free)m:qwen/qwen2.5-vl-3b-instruct:free | 64,000 | Free | Free |
Google: Gemini 2.5 Pro Experimental (free)m:google/gemini-2.5-pro-exp-03-25:free | 1,000,000 | Free | Free |
Qwen: Qwen2.5 VL 32B Instruct (free)m:qwen/qwen2.5-vl-32b-instruct:free | 8,192 | Free | Free |
DeepSeek: DeepSeek V3 0324 (free)m:deepseek/deepseek-chat-v3-0324:free | 131,072 | Free | Free |
Qwerky 72B (free)m:featherless/qwerky-72b:free | 32,768 | Free | Free |
Mistral: Mistral Small 3.1 24B (free)m:mistralai/mistral-small-3.1-24b-instruct:free | 96,000 | Free | Free |
OlympicCoder 7B (free)m:open-r1/olympiccoder-7b:free | 32,768 | Free | Free |
OlympicCoder 32B (free)m:open-r1/olympiccoder-32b:free | 32,768 | Free | Free |
Google: Gemma 3 1B (free)m:google/gemma-3-1b-it:free | 32,768 | Free | Free |
Google: Gemma 3 4B (free)m:google/gemma-3-4b-it:free | 131,072 | Free | Free |
Google: Gemma 3 12B (free)m:google/gemma-3-12b-it:free | 131,072 | Free | Free |
Reka: Flash 3 (free)m:rekaai/reka-flash-3:free | 32,768 | Free | Free |
Google: Gemma 3 27B (free)m:google/gemma-3-27b-it:free | 96,000 | Free | Free |
DeepSeek: DeepSeek R1 Zero (free)m:deepseek/deepseek-r1-zero:free | 163,840 | Free | Free |
Qwen: QwQ 32B (free)m:qwen/qwq-32b:free | 40,000 | Free | Free |
Moonshot AI: Moonlight 16B A3B Instruct (free)m:moonshotai/moonlight-16b-a3b-instruct:free | 8,192 | Free | Free |
Nous: DeepHermes 3 Llama 3 8B Preview (free)m:nousresearch/deephermes-3-llama-3-8b-preview:free | 131,072 | Free | Free |
Dolphin3.0 R1 Mistral 24B (free)m:cognitivecomputations/dolphin3.0-r1-mistral-24b:free | 32,768 | Free | Free |
Dolphin3.0 Mistral 24B (free)m:cognitivecomputations/dolphin3.0-mistral-24b:free | 32,768 | Free | Free |
Qwen: Qwen2.5 VL 72B Instruct (free)m:qwen/qwen2.5-vl-72b-instruct:free | 131,072 | Free | Free |
Mistral: Mistral Small 3 (free)m:mistralai/mistral-small-24b-instruct-2501:free | 32,768 | Free | Free |
DeepSeek: R1 Distill Qwen 32B (free)m:deepseek/deepseek-r1-distill-qwen-32b:free | 16,000 | Free | Free |
DeepSeek: R1 Distill Qwen 14B (free)m:deepseek/deepseek-r1-distill-qwen-14b:free | 64,000 | Free | Free |
DeepSeek: R1 Distill Llama 70B (free)m:deepseek/deepseek-r1-distill-llama-70b:free | 128,000 | Free | Free |
Google: Gemini 2.0 Flash Thinking Experimental 01-21 (free)m:google/gemini-2.0-flash-thinking-exp:free | 1,048,576 | Free | Free |
DeepSeek: R1 (free)m:deepseek/deepseek-r1:free | 163,840 | Free | Free |
Rogue Rose 103B v0.2 (free)m:sophosympatheia/rogue-rose-103b-v0.2:free | 4,096 | Free | Free |
DeepSeek: DeepSeek V3 (free)m:deepseek/deepseek-chat:free | 131,072 | Free | Free |
Google: Gemini 2.0 Flash Thinking Experimental (free)m:google/gemini-2.0-flash-thinking-exp-1219:free | 40,000 | Free | Free |
Google: Gemini 2.0 Flash Experimental (free)m:google/gemini-2.0-flash-exp:free | 1,048,576 | Free | Free |
Meta: Llama 3.3 70B Instruct (free)m:meta-llama/llama-3.3-70b-instruct:free | 8,000 | Free | Free |
Qwen: QwQ 32B Preview (free)m:qwen/qwq-32b-preview:free | 16,384 | Free | Free |
Google: LearnLM 1.5 Pro Experimental (free)m:google/learnlm-1.5-pro-experimental:free | 40,960 | Free | Free |
Qwen2.5 Coder 32B Instruct (free)m:qwen/qwen-2.5-coder-32b-instruct:free | 32,768 | Free | Free |
Qwen2.5 7B Instruct (free)m:qwen/qwen-2.5-7b-instruct:free | 32,768 | Free | Free |
NVIDIA: Llama 3.1 Nemotron 70B Instruct (free)m:nvidia/llama-3.1-nemotron-70b-instruct:free | 131,072 | Free | Free |
Meta: Llama 3.2 1B Instruct (free)m:meta-llama/llama-3.2-1b-instruct:free | 131,072 | Free | Free |
Meta: Llama 3.2 11B Vision Instruct (free)m:meta-llama/llama-3.2-11b-vision-instruct:free | 131,072 | Free | Free |
Meta: Llama 3.2 3B Instruct (free)m:meta-llama/llama-3.2-3b-instruct:free | 20,000 | Free | Free |
Qwen2.5 72B Instruct (free)m:qwen/qwen-2.5-72b-instruct:free | 32,768 | Free | Free |
Qwen: Qwen2.5-VL 7B Instruct (free)m:qwen/qwen-2.5-vl-7b-instruct:free | 64,000 | Free | Free |
Meta: Llama 3.1 8B Instruct (free)m:meta-llama/llama-3.1-8b-instruct:free | 131,072 | Free | Free |
Mistral: Mistral Nemo (free)m:mistralai/mistral-nemo:free | 128,000 | Free | Free |
Google: Gemma 2 9B (free)m:google/gemma-2-9b-it:free | 8,192 | Free | Free |
Mistral: Mistral 7B Instruct (free)m:mistralai/mistral-7b-instruct:free | 8,192 | Free | Free |
Hugging Face: Zephyr 7B (free)m:huggingfaceh4/zephyr-7b-beta:free | 4,096 | Free | Free |
Cheap Models
Name | Context Length | Input ($/1M Tokens) | Output ($/1M Tokens) |
---|---|---|---|
Optimus Alpham:openrouter/optimus-alpha | 1,000,000 | Free | Free |
xAI: Grok 3 Mini Betam:x-ai/grok-3-mini-beta | 131,072 | 0.300 | 0.500 |
Swallow: Llama 3.1 Swallow 8B Instruct V0.3m:tokyotech-llm/llama-3.1-swallow-8b-instruct-v0.3 | 16,384 | 0.099 | 0.199 |
Meta: Llama 4 Maverickm:meta-llama/llama-4-maverick | 1,048,576 | 0.190 | 0.850 |
Meta: Llama 4 Scoutm:meta-llama/llama-4-scout | 131,072 | 0.080 | 0.449 |
Quasar Alpham:openrouter/quasar-alpha | 1,000,000 | Free | Free |
Mistral: Ministral 8Bm:mistral/ministral-8b | 131,072 | 0.099 | 0.099 |
Typhoon2 8B Instructm:scb10x/llama3.1-typhoon2-8b-instruct | 8,192 | 0.180 | 0.180 |
Typhoon2 70B Instructm:scb10x/llama3.1-typhoon2-70b-instruct | 8,192 | 0.880 | 0.880 |
Qwen: Qwen2.5 VL 32B Instructm:qwen/qwen2.5-vl-32b-instruct | 128,000 | 0.899 | 0.899 |
DeepSeek: DeepSeek V3 0324m:deepseek/deepseek-chat-v3-0324 | 64,000 | 0.270 | 1.100 |
Mistral: Mistral Small 3.1 24Bm:mistralai/mistral-small-3.1-24b-instruct | 32,768 | 0.099 | 0.300 |
SteelSkull: L3.3 Electra R1 70Bm:steelskull/l3.3-electra-r1-70b | 131,072 | 0.700 | 0.950 |
AllenAI: Olmo 2 32B Instructm:allenai/olmo-2-0325-32b-instruct | 4,096 | 1.000 | 1.500 |
Google: Gemma 3 4Bm:google/gemma-3-4b-it | 131,072 | 0.020 | 0.040 |
AI21: Jamba Mini 1.6m:ai21/jamba-1.6-mini | 256,000 | 0.199 | 0.399 |
Google: Gemma 3 12Bm:google/gemma-3-12b-it | 131,072 | 0.049 | 0.099 |
OpenAI: GPT-4o-mini Search Previewm:openai/gpt-4o-mini-search-preview | 128,000 | 0.150 | 0.600 |
Swallow: Llama 3.1 Swallow 70B Instruct V0.3m:tokyotech-llm/llama-3.1-swallow-70b-instruct-v0.3 | 16,384 | 0.600 | 1.200 |
Google: Gemma 3 27Bm:google/gemma-3-27b-it | 131,072 | 0.099 | 0.199 |
TheDrummer: Anubis Pro 105B V1m:thedrummer/anubis-pro-105b-v1 | 131,072 | 0.799 | 1.000 |
LatitudeGames: Wayfarer Large 70B Llama 3.3m:latitudegames/wayfarer-large-70b-llama-3.3 | 131,072 | 0.799 | 0.899 |
TheDrummer: Skyfall 36B V2m:thedrummer/skyfall-36b-v2 | 32,768 | 0.500 | 0.799 |
Microsoft: Phi 4 Multimodal Instructm:microsoft/phi-4-multimodal-instruct | 131,072 | 0.049 | 0.099 |
Qwen: QwQ 32Bm:qwen/qwq-32b | 131,072 | 0.150 | 0.199 |
Qwen: Qwen2.5 32B Instructm:qwen/qwen2.5-32b-instruct | 131,072 | 0.789 | 0.789 |
Google: Gemini 2.0 Flash Litem:google/gemini-2.0-flash-lite-001 | 1,048,576 | 0.075 | 0.300 |
Mistral: Sabam:mistralai/mistral-saba | 32,768 | 0.199 | 0.600 |
Llama Guard 3 8Bm:meta-llama/llama-guard-3-8b | 8,192 | 0.199 | 0.199 |
DeepSeek: R1 Distill Llama 8Bm:deepseek/deepseek-r1-distill-llama-8b | 32,000 | 0.040 | 0.040 |
Google: Gemini 2.0 Flashm:google/gemini-2.0-flash-001 | 1,000,000 | 0.099 | 0.399 |
Qwen: Qwen VL Plusm:qwen/qwen-vl-plus | 7,500 | 0.210 | 0.630 |
AionLabs: Aion-1.0-Minim:aion-labs/aion-1.0-mini | 131,072 | 0.700 | 1.400 |
AionLabs: Aion-RP 1.0 (8B)m:aion-labs/aion-rp-llama-3.1-8b | 32,768 | 0.199 | 0.199 |
Qwen: Qwen-Turbom:qwen/qwen-turbo | 1,000,000 | 0.049 | 0.199 |
Qwen: Qwen2.5 VL 72B Instructm:qwen/qwen2.5-vl-72b-instruct | 128,000 | 0.700 | 0.700 |
Qwen: Qwen-Plusm:qwen/qwen-plus | 131,072 | 0.399 | 1.200 |
DeepSeek: R1 Distill Qwen 1.5Bm:deepseek/deepseek-r1-distill-qwen-1.5b | 131,072 | 0.180 | 0.180 |
Mistral: Mistral Small 3m:mistralai/mistral-small-24b-instruct-2501 | 32,768 | 0.070 | 0.140 |
DeepSeek: R1 Distill Qwen 32Bm:deepseek/deepseek-r1-distill-qwen-32b | 131,072 | 0.120 | 0.180 |
DeepSeek: R1 Distill Qwen 14Bm:deepseek/deepseek-r1-distill-qwen-14b | 64,000 | 0.150 | 0.150 |
Perplexity: Sonarm:perplexity/sonar | 127,072 | 1.000 | 1.000 |
Liquid: LFM 7Bm:liquid/lfm-7b | 32,768 | 0.010 | 0.010 |
Liquid: LFM 3Bm:liquid/lfm-3b | 32,768 | 0.020 | 0.020 |
DeepSeek: R1 Distill Llama 70Bm:deepseek/deepseek-r1-distill-llama-70b | 131,072 | 0.199 | 0.600 |
DeepSeek: R1m:deepseek/deepseek-r1 | 163,840 | 0.540 | 2.179 |
MiniMax: MiniMax-01m:minimax/minimax-01 | 1,000,192 | 0.199 | 1.100 |
Mistral: Codestral 2501m:mistralai/codestral-2501 | 262,144 | 0.300 | 0.899 |
Microsoft: Phi 4m:microsoft/phi-4 | 16,384 | 0.070 | 0.140 |
DeepSeek: DeepSeek V3m:deepseek/deepseek-chat | 163,840 | 0.380 | 0.889 |
Sao10K: Llama 3.3 Euryale 70Bm:sao10k/l3.3-euryale-70b | 131,072 | 0.700 | 0.799 |
Cohere: Command R7B (12-2024)m:cohere/command-r7b-12-2024 | 128,000 | 0.037 | 0.150 |
Meta: Llama 3.3 70B Instructm:meta-llama/llama-3.3-70b-instruct | 131,072 | 0.120 | 0.300 |
Amazon: Nova Lite 1.0m:amazon/nova-lite-v1 | 300,000 | 0.060 | 0.240 |
Amazon: Nova Micro 1.0m:amazon/nova-micro-v1 | 128,000 | 0.035 | 0.140 |
Qwen: QwQ 32B Previewm:qwen/qwq-32b-preview | 32,768 | 0.199 | 0.199 |
EVA Qwen2.5 72Bm:eva-unit-01/eva-qwen-2.5-72b | 131,072 | 0.899 | 1.200 |
Infermatic: Mistral Nemo Inferor 12Bm:infermatic/mn-inferor-12b | 16,384 | 0.799 | 1.200 |
Qwen2.5 Coder 32B Instructm:qwen/qwen-2.5-coder-32b-instruct | 33,000 | 0.070 | 0.160 |
Unslopnemo 12Bm:thedrummer/unslopnemo-12b | 32,000 | 0.500 | 0.500 |
Magnum v4 72Bm:anthracite-org/magnum-v4-72b | 16,384 | 1.500 | 2.250 |
NeverSleep: Lumimaid v0.2 70Bm:neversleep/llama-3.1-lumimaid-70b | 16,384 | 1.500 | 2.250 |
Mistral: Ministral 3Bm:mistralai/ministral-3b | 131,072 | 0.040 | 0.040 |
Mistral: Ministral 8Bm:mistralai/ministral-8b | 128,000 | 0.099 | 0.099 |
Qwen2.5 7B Instructm:qwen/qwen-2.5-7b-instruct | 32,768 | 0.049 | 0.099 |
NVIDIA: Llama 3.1 Nemotron 70B Instructm:nvidia/llama-3.1-nemotron-70b-instruct | 131,000 | 0.120 | 0.300 |
Google: Gemini 1.5 Flash 8Bm:google/gemini-flash-1.5-8b | 1,000,000 | 0.037 | 0.150 |
Liquid: LFM 40B MoEm:liquid/lfm-40b | 32,768 | 0.150 | 0.150 |
Rocinante 12Bm:thedrummer/rocinante-12b | 32,768 | 0.250 | 0.500 |
Meta: Llama 3.2 1B Instructm:meta-llama/llama-3.2-1b-instruct | 131,072 | 0.010 | 0.010 |
Meta: Llama 3.2 11B Vision Instructm:meta-llama/llama-3.2-11b-vision-instruct | 131,072 | 0.049 | 0.049 |
Meta: Llama 3.2 90B Vision Instructm:meta-llama/llama-3.2-90b-vision-instruct | 4,096 | 0.799 | 1.599 |
Meta: Llama 3.2 3B Instructm:meta-llama/llama-3.2-3b-instruct | 131,000 | 0.015 | 0.024 |
Qwen2.5 72B Instructm:qwen/qwen-2.5-72b-instruct | 131,072 | 0.130 | 0.399 |
Qwen: Qwen2.5-VL 72B Instructm:qwen/qwen-2.5-vl-72b-instruct | 32,768 | 0.600 | 0.600 |
NeverSleep: Lumimaid v0.2 8Bm:neversleep/llama-3.1-lumimaid-8b | 32,768 | 0.093 | 0.750 |
Mistral: Pixtral 12Bm:mistralai/pixtral-12b | 32,768 | 0.099 | 0.099 |
Cohere: Command R (08-2024)m:cohere/command-r-08-2024 | 128,000 | 0.150 | 0.600 |
Qwen: Qwen2.5-VL 7B Instructm:qwen/qwen-2.5-vl-7b-instruct | 32,768 | 0.199 | 0.199 |
Sao10K: Llama 3.1 Euryale 70B v2.2m:sao10k/l3.1-euryale-70b | 131,072 | 0.700 | 0.799 |
Google: Gemini 1.5 Flash 8B Experimentalm:google/gemini-flash-1.5-8b-exp | 1,000,000 | Free | Free |
AI21: Jamba 1.5 Minim:ai21/jamba-1-5-mini | 256,000 | 0.199 | 0.399 |
Microsoft: Phi-3.5 Mini 128K Instructm:microsoft/phi-3.5-mini-128k-instruct | 128,000 | 0.099 | 0.099 |
Nous: Hermes 3 70B Instructm:nousresearch/hermes-3-llama-3.1-70b | 131,000 | 0.120 | 0.300 |
Nous: Hermes 3 405B Instructm:nousresearch/hermes-3-llama-3.1-405b | 131,000 | 0.799 | 0.799 |
Aetherwiing: Starcannon 12Bm:aetherwiing/mn-starcannon-12b | 16,384 | 0.799 | 1.200 |
Sao10K: Llama 3 8B Lunarism:sao10k/l3-lunaris-8b | 8,192 | 0.049 | 0.049 |
Meta: Llama 3.1 405B (base)m:meta-llama/llama-3.1-405b | 32,768 | 2.000 | 2.000 |
Mistral Nemo 12B Celestem:nothingiisreal/mn-celeste-12b | 16,384 | 0.799 | 1.200 |
Perplexity: Llama 3.1 Sonar 8B Onlinem:perplexity/llama-3.1-sonar-small-128k-online | 127,072 | 0.199 | 0.199 |
Perplexity: Llama 3.1 Sonar 70B Onlinem:perplexity/llama-3.1-sonar-large-128k-online | 127,072 | 1.000 | 1.000 |
Meta: Llama 3.1 405B Instructm:meta-llama/llama-3.1-405b-instruct | 32,768 | 0.799 | 0.799 |
Meta: Llama 3.1 70B Instructm:meta-llama/llama-3.1-70b-instruct | 131,072 | 0.120 | 0.300 |
Meta: Llama 3.1 8B Instructm:meta-llama/llama-3.1-8b-instruct | 131,072 | 0.020 | 0.049 |
Mistral: Codestral Mambam:mistralai/codestral-mamba | 262,144 | 0.250 | 0.250 |
Mistral: Mistral Nemom:mistralai/mistral-nemo | 131,072 | 0.035 | 0.080 |
OpenAI: GPT-4o-mini (2024-07-18)m:openai/gpt-4o-mini-2024-07-18 | 128,000 | 0.150 | 0.600 |
OpenAI: GPT-4o-minim:openai/gpt-4o-mini | 128,000 | 0.150 | 0.600 |
Google: Gemma 2 27Bm:google/gemma-2-27b-it | 8,192 | 0.799 | 0.799 |
Magnum 72Bm:alpindale/magnum-72b | 16,384 | 1.500 | 2.250 |
Google: Gemma 2 9Bm:google/gemma-2-9b-it | 8,192 | 0.070 | 0.070 |
AI21: Jamba Instructm:ai21/jamba-instruct | 256,000 | 0.500 | 0.700 |
Sao10k: Llama 3 Euryale 70B v2.1m:sao10k/l3-euryale-70b | 8,192 | 1.480 | 1.480 |
Dolphin 2.9.2 Mixtral 8x22B 🐬m:cognitivecomputations/dolphin-mixtral-8x22b | 16,000 | 0.899 | 0.899 |
Qwen 2 72B Instructm:qwen/qwen-2-72b-instruct | 32,768 | 0.899 | 0.899 |
NousResearch: Hermes 2 Pro - Llama-3 8Bm:nousresearch/hermes-2-pro-llama-3-8b | 131,000 | 0.024 | 0.040 |
Mistral: Mistral 7B Instruct v0.3m:mistralai/mistral-7b-instruct-v0.3 | 32,768 | 0.030 | 0.055 |
Mistral: Mistral 7B Instructm:mistralai/mistral-7b-instruct | 32,768 | 0.030 | 0.055 |
Microsoft: Phi-3 Mini 128K Instructm:microsoft/phi-3-mini-128k-instruct | 128,000 | 0.099 | 0.099 |
Microsoft: Phi-3 Medium 128K Instructm:microsoft/phi-3-medium-128k-instruct | 128,000 | 1.000 | 1.000 |
Google: Gemini 1.5 Flash m:google/gemini-flash-1.5 | 1,000,000 | 0.075 | 0.300 |
Meta: LlamaGuard 2 8Bm:meta-llama/llama-guard-2-8b | 8,192 | 0.199 | 0.199 |
NeverSleep: Llama 3 Lumimaid 8B (extended)m:neversleep/llama-3-lumimaid-8b:extended | 24,576 | 0.093 | 0.750 |
NeverSleep: Llama 3 Lumimaid 8Bm:neversleep/llama-3-lumimaid-8b | 24,576 | 0.093 | 0.750 |
Fimbulvetr 11B v2m:sao10k/fimbulvetr-11b-v2 | 4,096 | 0.799 | 1.200 |
Meta: Llama 3 8B Instructm:meta-llama/llama-3-8b-instruct | 8,192 | 0.030 | 0.060 |
Meta: Llama 3 70B Instructm:meta-llama/llama-3-70b-instruct | 8,192 | 0.229 | 0.399 |
Mistral: Mixtral 8x22B Instructm:mistralai/mixtral-8x22b-instruct | 65,536 | 0.899 | 0.899 |
WizardLM-2 7Bm:microsoft/wizardlm-2-7b | 32,000 | 0.070 | 0.070 |
WizardLM-2 8x22Bm:microsoft/wizardlm-2-8x22b | 65,536 | 0.500 | 0.500 |
Midnight Rose 70Bm:sophosympatheia/midnight-rose-70b | 4,096 | 0.799 | 0.799 |
Cohere: Commandm:cohere/command | 4,096 | 1.000 | 2.000 |
Cohere: Command Rm:cohere/command-r | 128,000 | 0.500 | 1.500 |
Anthropic: Claude 3 Haiku (self-moderated)m:anthropic/claude-3-haiku:beta | 200,000 | 0.250 | 1.250 |
Anthropic: Claude 3 Haikum:anthropic/claude-3-haiku | 200,000 | 0.250 | 1.250 |
Cohere: Command R (03-2024)m:cohere/command-r-03-2024 | 128,000 | 0.500 | 1.500 |
OpenAI: GPT-3.5 Turbo (older v0613)m:openai/gpt-3.5-turbo-0613 | 4,095 | 1.000 | 2.000 |
Nous: Hermes 2 Mixtral 8x7B DPOm:nousresearch/nous-hermes-2-mixtral-8x7b-dpo | 32,768 | 0.600 | 0.600 |
Mistral Tinym:mistralai/mistral-tiny | 32,768 | 0.250 | 0.250 |
Mistral Smallm:mistralai/mistral-small | 32,768 | 0.199 | 0.600 |
Mistral: Mistral 7B Instruct v0.2m:mistralai/mistral-7b-instruct-v0.2 | 32,768 | 0.199 | 0.199 |
Dolphin 2.6 Mixtral 8x7B 🐬m:cognitivecomputations/dolphin-mixtral-8x7b | 32,768 | 0.500 | 0.500 |
Google: Gemini Pro 1.0m:google/gemini-pro | 32,760 | 0.500 | 1.500 |
Google: Gemini Pro Vision 1.0m:google/gemini-pro-vision | 16,384 | 0.500 | 1.500 |
Mistral: Mixtral 8x7B Instructm:mistralai/mixtral-8x7b-instruct | 32,768 | 0.240 | 0.240 |
Mistral: Mixtral 8x7B (base)m:mistralai/mixtral-8x7b | 32,768 | 0.600 | 0.600 |
OpenChat 3.5 7Bm:openchat/openchat-7b | 8,192 | 0.070 | 0.070 |
Noromaid 20Bm:neversleep/noromaid-20b | 8,192 | 0.750 | 1.500 |
Toppy M 7Bm:undi95/toppy-m-7b | 4,096 | 0.070 | 0.070 |
OpenAI: GPT-3.5 Turbo 16k (older v1106)m:openai/gpt-3.5-turbo-1106 | 16,385 | 1.000 | 2.000 |
Google: PaLM 2 Chat 32km:google/palm-2-chat-bison-32k | 32,768 | 1.000 | 2.000 |
Google: PaLM 2 Code Chat 32km:google/palm-2-codechat-bison-32k | 32,768 | 1.000 | 2.000 |
Airoboros 70Bm:jondurbin/airoboros-l2-70b | 4,096 | 0.500 | 0.500 |
OpenAI: GPT-3.5 Turbo Instructm:openai/gpt-3.5-turbo-instruct | 4,095 | 1.500 | 2.000 |
Mistral: Mistral 7B Instruct v0.1m:mistralai/mistral-7b-instruct-v0.1 | 32,768 | 0.199 | 0.199 |
Pygmalion: Mythalion 13Bm:pygmalionai/mythalion-13b | 8,192 | 0.562 | 1.125 |
Nous: Hermes 13Bm:nousresearch/nous-hermes-llama2-13b | 4,096 | 0.180 | 0.180 |
Mancer: Weaver (alpha)m:mancer/weaver | 8,000 | 1.125 | 1.125 |
ReMM SLERP 13Bm:undi95/remm-slerp-l2-13b | 6,144 | 0.562 | 1.125 |
Google: PaLM 2 Chatm:google/palm-2-chat-bison | 9,216 | 1.000 | 2.000 |
Google: PaLM 2 Code Chatm:google/palm-2-codechat-bison | 7,168 | 1.000 | 2.000 |
MythoMax 13Bm:gryphe/mythomax-l2-13b | 4,096 | 0.065 | 0.065 |
Meta: Llama 2 70B Chatm:meta-llama/llama-2-70b-chat | 4,096 | 0.899 | 0.899 |
Meta: Llama 2 13B Chatm:meta-llama/llama-2-13b-chat | 4,096 | 0.220 | 0.220 |
OpenAI: GPT-3.5 Turbom:openai/gpt-3.5-turbo | 16,385 | 0.500 | 1.500 |
OpenAI: GPT-3.5 Turbo 16km:openai/gpt-3.5-turbo-0125 | 16,385 | 0.500 | 1.500 |
Medium Class Models
Name | Context Length | Input ($/1M Tokens) | Output ($/1M Tokens) |
---|---|---|---|
Google: Gemini 2.5 Pro Previewm:google/gemini-2.5-pro-preview-03-25 | 1,000,000 | 1.250 | 10.000 |
OpenHands LM 32B V0.1m:all-hands/openhands-lm-32b-v0.1 | 16,384 | 2.600 | 3.400 |
AI21: Jamba 1.6 Largem:ai21/jamba-1.6-large | 256,000 | 2.000 | 8.000 |
Cohere: Command Am:cohere/command-a | 256,000 | 2.500 | 10.000 |
OpenAI: GPT-4o Search Previewm:openai/gpt-4o-search-preview | 128,000 | 2.500 | 10.000 |
Perplexity: Sonar Reasoning Prom:perplexity/sonar-reasoning-pro | 128,000 | 2.000 | 8.000 |
Perplexity: Sonar Deep Researchm:perplexity/sonar-deep-research | 128,000 | 2.000 | 8.000 |
Perplexity: R1 1776m:perplexity/r1-1776 | 128,000 | 2.000 | 8.000 |
OpenAI: o3 Mini Highm:openai/o3-mini-high | 200,000 | 1.100 | 4.400 |
AionLabs: Aion-1.0m:aion-labs/aion-1.0 | 131,072 | 4.000 | 8.000 |
Qwen: Qwen VL Maxm:qwen/qwen-vl-max | 7,500 | 0.799 | 3.199 |
Qwen: Qwen-Max m:qwen/qwen-max | 32,768 | 1.599 | 6.399 |
OpenAI: o3 Minim:openai/o3-mini | 200,000 | 1.100 | 4.400 |
Perplexity: Sonar Reasoningm:perplexity/sonar-reasoning | 127,000 | 1.000 | 5.000 |
Sao10K: Llama 3.1 70B Hanami x1m:sao10k/l3.1-70b-hanami-x1 | 16,000 | 3.000 | 3.000 |
EVA Llama 3.33 70Bm:eva-unit-01/eva-llama-3.33-70b | 16,384 | 4.000 | 6.000 |
xAI: Grok 2 Vision 1212m:x-ai/grok-2-vision-1212 | 32,768 | 2.000 | 10.000 |
xAI: Grok 2 1212m:x-ai/grok-2-1212 | 131,072 | 2.000 | 10.000 |
Amazon: Nova Pro 1.0m:amazon/nova-pro-v1 | 300,000 | 0.799 | 3.199 |
OpenAI: GPT-4o (2024-11-20)m:openai/gpt-4o-2024-11-20 | 128,000 | 2.500 | 10.000 |
Mistral Large 2411m:mistralai/mistral-large-2411 | 131,072 | 2.000 | 6.000 |
Mistral Large 2407m:mistralai/mistral-large-2407 | 131,072 | 2.000 | 6.000 |
Mistral: Pixtral Large 2411m:mistralai/pixtral-large-2411 | 131,072 | 2.000 | 6.000 |
SorcererLM 8x22Bm:raifle/sorcererlm-8x22b | 16,000 | 4.500 | 4.500 |
EVA Qwen2.5 32Bm:eva-unit-01/eva-qwen-2.5-32b | 16,384 | 2.600 | 3.400 |
Anthropic: Claude 3.5 Haiku (2024-10-22) (self-moderated)m:anthropic/claude-3.5-haiku-20241022:beta | 200,000 | 0.799 | 4.000 |
Anthropic: Claude 3.5 Haiku (self-moderated)m:anthropic/claude-3.5-haiku:beta | 200,000 | 0.799 | 4.000 |
Anthropic: Claude 3.5 Haikum:anthropic/claude-3.5-haiku | 200,000 | 0.799 | 4.000 |
Anthropic: Claude 3.5 Haiku (2024-10-22)m:anthropic/claude-3.5-haiku-20241022 | 200,000 | 0.799 | 4.000 |
Inflection: Inflection 3 Productivitym:inflection/inflection-3-productivity | 8,000 | 2.500 | 10.000 |
Inflection: Inflection 3 Pim:inflection/inflection-3-pi | 8,000 | 2.500 | 10.000 |
Magnum v2 72Bm:anthracite-org/magnum-v2-72b | 32,768 | 3.000 | 3.000 |
OpenAI: o1-minim:openai/o1-mini | 128,000 | 1.100 | 4.400 |
OpenAI: o1-mini (2024-09-12)m:openai/o1-mini-2024-09-12 | 128,000 | 1.100 | 4.400 |
Cohere: Command R+ (08-2024)m:cohere/command-r-plus-08-2024 | 128,000 | 2.500 | 10.000 |
AI21: Jamba 1.5 Largem:ai21/jamba-1-5-large | 256,000 | 2.000 | 8.000 |
OpenAI: GPT-4o (2024-08-06)m:openai/gpt-4o-2024-08-06 | 128,000 | 2.500 | 10.000 |
01.AI: Yi Largem:01-ai/yi-large | 32,768 | 3.000 | 3.000 |
NeverSleep: Llama 3 Lumimaid 70Bm:neversleep/llama-3-lumimaid-70b | 8,192 | 3.375 | 4.500 |
OpenAI: GPT-4om:openai/gpt-4o | 128,000 | 2.500 | 10.000 |
Google: Gemini 1.5 Prom:google/gemini-pro-1.5 | 2,000,000 | 1.250 | 5.000 |
Mistral Largem:mistralai/mistral-large | 128,000 | 2.000 | 6.000 |
Mistral Mediumm:mistralai/mistral-medium | 32,768 | 2.750 | 8.100 |
Goliath 120Bm:alpindale/goliath-120b | 6,144 | 6.562 | 9.375 |
Xwin 70Bm:xwin-lm/xwin-lm-70b | 8,192 | 3.750 | 3.750 |
OpenAI: GPT-3.5 Turbo 16km:openai/gpt-3.5-turbo-16k | 16,385 | 3.000 | 4.000 |
Premium Models
Name | Context Length | Input ($/1M Tokens) | Output ($/1M Tokens) |
---|---|---|---|
xAI: Grok 3 Betam:x-ai/grok-3-beta | 131,072 | 3.000 | 15.000 |
OpenAI: o1-prom:openai/o1-pro | 200,000 | 150.000 | 600.000 |
Perplexity: Sonar Prom:perplexity/sonar-pro | 200,000 | 3.000 | 15.000 |
OpenAI: GPT-4.5 (Preview)m:openai/gpt-4.5-preview | 128,000 | 75.000 | 150.000 |
Anthropic: Claude 3.7 Sonnet (thinking)m:anthropic/claude-3.7-sonnet:thinking | 200,000 | 3.000 | 15.000 |
Anthropic: Claude 3.7 Sonnetm:anthropic/claude-3.7-sonnet | 200,000 | 3.000 | 15.000 |
Anthropic: Claude 3.7 Sonnet (self-moderated)m:anthropic/claude-3.7-sonnet:beta | 200,000 | 3.000 | 15.000 |
OpenAI: o1m:openai/o1 | 200,000 | 15.000 | 60.000 |
xAI: Grok Vision Betam:x-ai/grok-vision-beta | 8,192 | 5.000 | 15.000 |
Anthropic: Claude 3.5 Sonnetm:anthropic/claude-3.5-sonnet | 200,000 | 3.000 | 15.000 |
Anthropic: Claude 3.5 Sonnet (self-moderated)m:anthropic/claude-3.5-sonnet:beta | 200,000 | 3.000 | 15.000 |
xAI: Grok Betam:x-ai/grok-beta | 131,072 | 5.000 | 15.000 |
OpenAI: o1-previewm:openai/o1-preview | 128,000 | 15.000 | 60.000 |
OpenAI: o1-preview (2024-09-12)m:openai/o1-preview-2024-09-12 | 128,000 | 15.000 | 60.000 |
OpenAI: ChatGPT-4om:openai/chatgpt-4o-latest | 128,000 | 5.000 | 15.000 |
Anthropic: Claude 3.5 Sonnet (2024-06-20) (self-moderated)m:anthropic/claude-3.5-sonnet-20240620:beta | 200,000 | 3.000 | 15.000 |
Anthropic: Claude 3.5 Sonnet (2024-06-20)m:anthropic/claude-3.5-sonnet-20240620 | 200,000 | 3.000 | 15.000 |
OpenAI: GPT-4o (extended)m:openai/gpt-4o:extended | 128,000 | 6.000 | 18.000 |
OpenAI: GPT-4o (2024-05-13)m:openai/gpt-4o-2024-05-13 | 128,000 | 5.000 | 15.000 |
OpenAI: GPT-4 Turbom:openai/gpt-4-turbo | 128,000 | 10.000 | 30.000 |
Cohere: Command R+m:cohere/command-r-plus | 128,000 | 3.000 | 15.000 |
Cohere: Command R+ (04-2024)m:cohere/command-r-plus-04-2024 | 128,000 | 3.000 | 15.000 |
Anthropic: Claude 3 Opusm:anthropic/claude-3-opus | 200,000 | 15.000 | 75.000 |
Anthropic: Claude 3 Sonnet (self-moderated)m:anthropic/claude-3-sonnet:beta | 200,000 | 3.000 | 15.000 |
Anthropic: Claude 3 Sonnetm:anthropic/claude-3-sonnet | 200,000 | 3.000 | 15.000 |
Anthropic: Claude 3 Opus (self-moderated)m:anthropic/claude-3-opus:beta | 200,000 | 15.000 | 75.000 |
OpenAI: GPT-4 Turbo Previewm:openai/gpt-4-turbo-preview | 128,000 | 10.000 | 30.000 |
Anthropic: Claude v2m:anthropic/claude-2 | 200,000 | 8.000 | 24.000 |
Anthropic: Claude v2.1m:anthropic/claude-2.1 | 200,000 | 8.000 | 24.000 |
Anthropic: Claude v2.1 (self-moderated)m:anthropic/claude-2.1:beta | 200,000 | 8.000 | 24.000 |
Anthropic: Claude v2 (self-moderated)m:anthropic/claude-2:beta | 200,000 | 8.000 | 24.000 |
OpenAI: GPT-4 Turbo (older v1106)m:openai/gpt-4-1106-preview | 128,000 | 10.000 | 30.000 |
OpenAI: GPT-4 32k (older v0314)m:openai/gpt-4-32k-0314 | 32,767 | 60.000 | 120.000 |
OpenAI: GPT-4 32km:openai/gpt-4-32k | 32,767 | 60.000 | 120.000 |
Anthropic: Claude v2.0 (self-moderated)m:anthropic/claude-2.0:beta | 100,000 | 8.000 | 24.000 |
Anthropic: Claude v2.0m:anthropic/claude-2.0 | 100,000 | 8.000 | 24.000 |
OpenAI: GPT-4m:openai/gpt-4 | 8,191 | 30.000 | 60.000 |
OpenAI: GPT-4 (older v0314)m:openai/gpt-4-0314 | 8,191 | 30.000 | 60.000 |