Overview

Chat models are the foundation of conversational AI. They are designed to understand and generate human-like text, making them perfect for a wide range of applications including chatbots, content creation, summarization, and question-answering systems. When making a request to the /v1/chat endpoint, you must specify one of the following Model IDs.

Available Chat Models

Model NameContext LengthInput Cost ($/M tokens)Output Cost ($/M tokens)
Cypher Alpha (free)1M tokens$0.00$0.00
Baidu: ERNIE 4.5 300B A47B123K tokens$0.28$1.10
TheDrummer: Anubis 70B V1.1131K tokens$0.30$0.80
Inception: Mercury32K tokens$0.25$1.00
Morph: Fast Apply32K tokens$1.20$2.70
Mistral: Mistral Small 3.2 24B (free)96K tokens$0.00$0.00
Mistral: Mistral Small 3.2 24B128K tokens$0.05$0.10
MiniMax: MiniMax M11M tokens$0.30$1.65
Google: Gemini 2.5 Flash Lite Preview 06-171M tokens$0.10$0.40
Google: Gemini 2.5 Flash1M tokens$0.30$2.50
Google: Gemini 2.5 Pro1M tokens$1.25$10.00
Kimi Dev 72b (free)131K tokens$0.00$0.00
OpenAI: o3 Pro200K tokens$20.00$80.00
xAI: Grok 3 Mini131K tokens$0.30$0.50
xAI: Grok 3131K tokens$3.00$15.00
Mistral: Magistral Small 250640K tokens$0.50$1.50
Mistral: Magistral Medium 250640K tokens$2.00$5.00
Mistral: Magistral Medium 2506 (thinking)40K tokens$2.00$5.00
Google: Gemini 2.5 Pro Preview 06-051M tokens$1.25$10.00
DeepSeek: R1 Distill Qwen 7B131K tokens$0.10$0.20
DeepSeek: Deepseek R1 0528 Qwen3 8B (free)131K tokens$0.00$0.00
DeepSeek: Deepseek R1 0528 Qwen3 8B32K tokens$0.01$0.02
DeepSeek: R1 0528 (free)163K tokens$0.00$0.00
DeepSeek: R1 0528128K tokens$0.50$2.15
Sarvam AI: Sarvam-M (free)32K tokens$0.00$0.00
TheDrummer: Valkyrie 49B V1131K tokens$0.50$0.80
Anthropic: Claude Opus 4200K tokens$15.00$75.00
Anthropic: Claude Sonnet 4200K tokens$3.00$15.00
Mistral: Devstral Small (free)32K tokens$0.00$0.00
Mistral: Devstral Small128K tokens$0.06$0.12
Google: Gemma 3n 4B (free)8K tokens$0.00$0.00
Google: Gemma 3n 4B32K tokens$0.02$0.04
Google: Gemini 2.5 Flash Preview 05-201M tokens$0.15$0.60
Google: Gemini 2.5 Flash Preview 05-20 (thinking)1M tokens$0.15$3.50
OpenAI: Codex Mini200K tokens$1.50$6.00
Mistral: Mistral Medium 3131K tokens$0.40$2.00
Google: Gemini 2.5 Pro Preview 05-061M tokens$1.25$10.00
Arcee AI: Caller Large32K tokens$0.55$0.85
Arcee AI: Spotlight131K tokens$0.18$0.18
Arcee AI: Maestro Reasoning131K tokens$0.90$3.30
Arcee AI: Virtuoso Large131K tokens$0.75$1.20
Arcee AI: Coder Large32K tokens$0.50$0.80
Arcee AI: Virtuoso Medium V2131K tokens$0.50$0.80
Arcee AI: Arcee Blitz32K tokens$0.45$0.75
Microsoft: Phi 4 Reasoning Plus32K tokens$0.07$0.35
Inception: Mercury Coder32K tokens$0.25$1.00
OpenGVLab: InternVL3 14B12K tokens$0.20$0.40
OpenGVLab: InternVL3 2B12K tokens$0.05$0.10
DeepSeek: DeepSeek Prover V2131K tokens$0.50$2.18
Meta: Llama Guard 4 12B163K tokens$0.05$0.05
Qwen: Qwen3 30B A3B (free)40K tokens$0.00$0.00
Qwen: Qwen3 30B A3B40K tokens$0.08$0.29
Qwen: Qwen3 8B (free)40K tokens$0.00$0.00
Qwen: Qwen3 8B128K tokens$0.04$0.14
Qwen: Qwen3 14B (free)40K tokens$0.00$0.00
Qwen: Qwen3 14B40K tokens$0.06$0.24
Qwen: Qwen3 32B (free)40K tokens$0.00$0.00
Qwen: Qwen3 32B40K tokens$0.10$0.30
Qwen: Qwen3 235B A22B (free)40K tokens$0.00$0.00
Qwen: Qwen3 235B A22B40K tokens$0.13$0.60
TNG: DeepSeek R1T Chimera (free)163K tokens$0.00$0.00
THUDM: GLM Z1 Rumination 32B32K tokens$0.24$0.24
Microsoft: MAI DS R1 (free)163K tokens$0.00$0.00
THUDM: GLM Z1 32B (free)32K tokens$0.00$0.00
THUDM: GLM Z1 32B32K tokens$0.24$0.24
THUDM: GLM 4 32B (free)32K tokens$0.00$0.00
THUDM: GLM 4 32B32K tokens$0.24$0.24
Google: Gemini 2.5 Flash Preview 04-171M tokens$0.15$0.60
Google: Gemini 2.5 Flash Preview 04-17 (thinking)1M tokens$0.15$3.50
OpenAI: o4 Mini High200K tokens$1.10$4.40
OpenAI: o3200K tokens$2.00$8.00
OpenAI: o4 Mini200K tokens$1.10$4.40
Shisa AI: Shisa V2 Llama 3.3 70B (free)32K tokens$0.00$0.00
OpenAI: GPT-4.11M tokens$2.00$8.00
OpenAI: GPT-4.1 Mini1M tokens$0.40$1.60
OpenAI: GPT-4.1 Nano1M tokens$0.10$0.40
EleutherAI: Llemma 7b4K tokens$0.80$1.20
AlfredPros: CodeLLaMa 7B Instruct Solidity4K tokens$0.80$1.20
ArliAI: QwQ 32B RpR v1 (free)32K tokens$0.00$0.00
Agentica: Deepcoder 14B Preview (free)96K tokens$0.00$0.00
Moonshot AI: Kimi VL A3B Thinking (free)131K tokens$0.00$0.00
xAI: Grok 3 Mini Beta131K tokens$0.30$0.50
xAI: Grok 3 Beta131K tokens$3.00$15.00
NVIDIA: Llama 3.3 Nemotron Super 49B v1 (free)131K tokens$0.00$0.00
NVIDIA: Llama 3.3 Nemotron Super 49B v1131K tokens$0.13$0.40
NVIDIA: Llama 3.1 Nemotron Ultra 253B v1 (free)131K tokens$0.00$0.00
NVIDIA: Llama 3.1 Nemotron Ultra 253B v1131K tokens$0.60$1.80
Meta: Llama 4 Maverick (free)128K tokens$0.00$0.00
Meta: Llama 4 Maverick1M tokens$0.15$0.60
Meta: Llama 4 Scout (free)64K tokens$0.00$0.00
Meta: Llama 4 Scout1M tokens$0.08$0.30
OpenHands LM 32B V0.116K tokens$2.60$3.40
DeepSeek: DeepSeek V3 Base (free)163K tokens$0.00$0.00
Typhoon2 70B Instruct8K tokens$0.88$0.88
Google: Gemini 2.5 Pro Experimental1M tokens$0.00$0.00
Qwen: Qwen2.5 VL 32B Instruct (free)8K tokens$0.00$0.00
Qwen: Qwen2.5 VL 32B Instruct128K tokens$0.90$0.90
DeepSeek: DeepSeek V3 0324 (free)16K tokens$0.00$0.00
DeepSeek: DeepSeek V3 0324163K tokens$0.28$0.88
Qwerky 72B (free)32K tokens$0.00$0.00
OpenAI: o1-pro200K tokens$150.00$600.00
Mistral: Mistral Small 3.1 24B (free)96K tokens$0.00$0.00
Mistral: Mistral Small 3.1 24B128K tokens$0.05$0.10
Google: Gemma 3 4B (free)32K tokens$0.00$0.00
Google: Gemma 3 4B131K tokens$0.02$0.04
AI21: Jamba 1.6 Large256K tokens$2.00$8.00
AI21: Jamba Mini 1.6256K tokens$0.20$0.40
Google: Gemma 3 12B (free)96K tokens$0.00$0.00
Google: Gemma 3 12B131K tokens$0.05$0.10
Cohere: Command A256K tokens$2.50$10.00
OpenAI: GPT-4o-mini Search Preview128K tokens$0.15$0.60
OpenAI: GPT-4o Search Preview128K tokens$2.50$10.00
Reka: Flash 3 (free)32K tokens$0.00$0.00
Google: Gemma 3 27B (free)96K tokens$0.00$0.00
Google: Gemma 3 27B131K tokens$0.09$0.17
TheDrummer: Anubis Pro 105B V1131K tokens$0.80$1.00
TheDrummer: Skyfall 36B V232K tokens$0.50$0.80
Microsoft: Phi 4 Multimodal Instruct131K tokens$0.05$0.10
Perplexity: Sonar Reasoning Pro128K tokens$2.00$8.00
Perplexity: Sonar Pro200K tokens$3.00$15.00
Perplexity: Sonar Deep Research128K tokens$2.00$8.00
Qwen: QwQ 32B (free)131K tokens$0.00$0.00
Qwen: QwQ 32B131K tokens$0.08$0.15
Nous: DeepHermes 3 Llama 3 8B Preview (free)131K tokens$0.00$0.00
OpenAI: GPT-4.5 (Preview)128K tokens$75.00$150.00
Google: Gemini 2.0 Flash Lite1M tokens$0.08$0.30
Anthropic: Claude 3.7 Sonnet200K tokens$3.00$15.00
Anthropic: Claude 3.7 Sonnet (thinking)200K tokens$3.00$15.00
Anthropic: Claude 3.7 Sonnet (self-moderated)200K tokens$3.00$15.00
Perplexity: R1 1776128K tokens$2.00$8.00
Mistral: Saba32K tokens$0.20$0.60
Dolphin3.0 R1 Mistral 24B (free)32K tokens$0.00$0.00
Dolphin3.0 Mistral 24B (free)32K tokens$0.00$0.00
Llama Guard 3 8B131K tokens$0.02$0.06
OpenAI: o3 Mini High200K tokens$1.10$4.40
DeepSeek: R1 Distill Llama 8B32K tokens$0.04$0.04
Google: Gemini 2.0 Flash1M tokens$0.10$0.40
Qwen: Qwen VL Plus7K tokens$0.21$0.63
AionLabs: Aion-1.0131K tokens$4.00$8.00
AionLabs: Aion-1.0-Mini131K tokens$0.70$1.40
AionLabs: Aion-RP 1.0 (8B)32K tokens$0.20$0.20
Qwen: Qwen VL Max7K tokens$0.80$3.20
Qwen: Qwen-Turbo1M tokens$0.05$0.20
Qwen: Qwen-Plus131K tokens$0.40$1.20
Qwen: Qwen-Max32K tokens$1.60$6.40
OpenAI: o3 Mini200K tokens$1.10$4.40
DeepSeek: R1 Distill Qwen 1.5B131K tokens$0.18$0.18
Mistral: Mistral Small 3 (free)32K tokens$0.00$0.00
Mistral: Mistral Small 332K tokens$0.05$0.09
DeepSeek: R1 Distill Qwen 32B131K tokens$0.08$0.15
DeepSeek: R1 Distill Qwen 14B (free)64K tokens$0.00$0.00
DeepSeek: R1 Distill Qwen 14B64K tokens$0.15$0.15
Perplexity: Sonar Reasoning127K tokens$1.00$5.00
Perplexity: Sonar127K tokens$1.00$1.00
Liquid: LFM 7B32K tokens$0.01$0.01
Liquid: LFM 3B32K tokens$0.02$0.02
DeepSeek: R1 Distill Llama 70B (free)8K tokens$0.00$0.00
DeepSeek: R1 Distill Llama 70B131K tokens$0.10$0.40
DeepSeek: R1 (free)163K tokens$0.00$0.00
DeepSeek: R1128K tokens$0.45$2.15
MiniMax: MiniMax-011M tokens$0.20$1.10
Mistral: Codestral 2501262K tokens$0.30$0.90
Microsoft: Phi 416K tokens$0.07$0.14
DeepSeek: DeepSeek V3 (free)163K tokens$0.00$0.00
DeepSeek: DeepSeek V3163K tokens$0.38$0.89
Sao10K: Llama 3.3 Euryale 70B131K tokens$0.65$0.75
OpenAI: o1200K tokens$15.00$60.00
EVA Llama 3.33 70B16K tokens$4.00$6.00
xAI: Grok 2 Vision 121232K tokens$2.00$10.00
xAI: Grok 2 1212131K tokens$2.00$10.00
Cohere: Command R7B (12-2024)128K tokens$0.04$0.15
Google: Gemini 2.0 Flash Experimental (free)1M tokens$0.00$0.00
Meta: Llama 3.3 70B Instruct (free)131K tokens$0.00$0.00
Meta: Llama 3.3 70B Instruct131K tokens$0.04$0.12
Amazon: Nova Lite 1.0300K tokens$0.06$0.24
Amazon: Nova Micro 1.0128K tokens$0.04$0.14
Amazon: Nova Pro 1.0300K tokens$0.80$3.20
Qwen: QwQ 32B Preview32K tokens$0.20$0.20
EVA Qwen2.5 72B16K tokens$4.00$6.00
OpenAI: GPT-4o (2024-11-20)128K tokens$2.50$10.00
Mistral Large 2411131K tokens$2.00$6.00
Mistral Large 2407131K tokens$2.00$6.00
Mistral: Pixtral Large 2411131K tokens$2.00$6.00
xAI: Grok Vision Beta8K tokens$5.00$15.00
Infermatic: Mistral Nemo Inferor 12B16K tokens$0.80$1.20
Qwen2.5 Coder 32B Instruct (free)32K tokens$0.00$0.00
Qwen2.5 Coder 32B Instruct32K tokens$0.06$0.15
SorcererLM 8x22B16K tokens$4.50$4.50
EVA Qwen2.5 32B16K tokens$2.60$3.40
TheDrummer: UnslopNemo 12B32K tokens$0.40$0.40
Anthropic: Claude 3.5 Haiku (self-moderated)200K tokens$0.80$4.00
Anthropic: Claude 3.5 Haiku200K tokens$0.80$4.00
Anthropic: Claude 3.5 Haiku (2024-10-22) (self-moderated)200K tokens$0.80$4.00
Anthropic: Claude 3.5 Haiku (2024-10-22)200K tokens$0.80$4.00
NeverSleep: Lumimaid v0.2 70B16K tokens$2.50$3.00
Magnum v4 72B16K tokens$2.50$3.00
Anthropic: Claude 3.5 Sonnet (self-moderated)200K tokens$3.00$15.00
Anthropic: Claude 3.5 Sonnet200K tokens$3.00$15.00
Mistral: Ministral 8B128K tokens$0.10$0.10
Mistral: Ministral 3B131K tokens$0.04$0.04
Qwen2.5 7B Instruct32K tokens$0.04$0.10
NVIDIA: Llama 3.1 Nemotron 70B Instruct131K tokens$0.12$0.30
Inflection: Inflection 3 Productivity8K tokens$2.50$10.00
Inflection: Inflection 3 Pi8K tokens$2.50$10.00
Google: Gemini 1.5 Flash 8B1M tokens$0.04$0.15
TheDrummer: Rocinante 12B32K tokens$0.20$0.50
Magnum v2 72B32K tokens$3.00$3.00
Liquid: LFM 40B MoE32K tokens$0.15$0.15
Meta: Llama 3.2 3B Instruct20K tokens$0.00$0.01
Meta: Llama 3.2 1B Instruct131K tokens$0.01$0.01
Meta: Llama 3.2 90B Vision Instruct131K tokens$1.20$1.20
Meta: Llama 3.2 11B Vision Instruct (free)131K tokens$0.00$0.00
Meta: Llama 3.2 11B Vision Instruct131K tokens$0.05$0.05
Qwen2.5 72B Instruct (free)32K tokens$0.00$0.00
Qwen2.5 72B Instruct32K tokens$0.12$0.39
NeverSleep: Lumimaid v0.2 8B32K tokens$0.20$1.25
OpenAI: o1-preview128K tokens$15.00$60.00
OpenAI: o1-preview (2024-09-12)128K tokens$15.00$60.00
OpenAI: o1-mini128K tokens$1.10$4.40
OpenAI: o1-mini (2024-09-12)128K tokens$1.10$4.40
Mistral: Pixtral 12B32K tokens$0.10$0.10
Cohere: Command R+ (08-2024)128K tokens$2.50$10.00
Cohere: Command R (08-2024)128K tokens$0.15$0.60
Qwen: Qwen2.5-VL 7B Instruct32K tokens$0.20$0.20
Sao10K: Llama 3.1 Euryale 70B v2.232K tokens$0.65$0.75
Microsoft: Phi-3.5 Mini 128K Instruct128K tokens$0.10$0.10
Nous: Hermes 3 70B Instruct131K tokens$0.10$0.28
Nous: Hermes 3 405B Instruct131K tokens$0.70$0.80
OpenAI: ChatGPT-4o128K tokens$5.00$15.00
Sao10K: Llama 3 8B Lunaris8K tokens$0.02$0.05
Aetherwiing: Starcannon 12B16K tokens$0.80$1.20
OpenAI: GPT-4o (2024-08-06)128K tokens$2.50$10.00
Meta: Llama 3.1 405B (base)32K tokens$2.00$2.00
Mistral Nemo 12B Celeste16K tokens$0.80$1.20
Perplexity: Llama 3.1 Sonar 8B Online127K tokens$0.20$0.20
Perplexity: Llama 3.1 Sonar 70B Online127K tokens$1.00$1.00
Meta: Llama 3.1 8B Instruct131K tokens$0.02$0.02
Meta: Llama 3.1 405B Instruct32K tokens$0.80$0.80
Meta: Llama 3.1 70B Instruct131K tokens$0.10$0.28
Mistral: Mistral Nemo (free)131K tokens$0.00$0.00
Mistral: Mistral Nemo131K tokens$0.01$0.00
OpenAI: GPT-4o-mini128K tokens$0.15$0.60
OpenAI: GPT-4o-mini (2024-07-18)128K tokens$0.15$0.60
Google: Gemma 2 27B8K tokens$0.80$0.80
Magnum 72B16K tokens$4.00$6.00
Google: Gemma 2 9B (free)8K tokens$0.00$0.00
Google: Gemma 2 9B8K tokens$0.20$0.20
01.AI: Yi Large32K tokens$3.00$3.00
Anthropic: Claude 3.5 Sonnet (2024-06-20) (self-moderated)200K tokens$3.00$15.00
Anthropic: Claude 3.5 Sonnet (2024-06-20)200K tokens$3.00$15.00
Sao10k: Llama 3 Euryale 70B v2.18K tokens$1.48$1.48
Dolphin 2.9.2 Mixtral 8x22B 🐬16K tokens$0.90$0.90
Qwen 2 72B Instruct32K tokens$0.90$0.90
Mistral: Mistral 7B Instruct (free)32K tokens$0.00$0.00
Mistral: Mistral 7B Instruct32K tokens$0.03$0.05
NousResearch: Hermes 2 Pro - Llama-3 8B131K tokens$0.03$0.04
Mistral: Mistral 7B Instruct v0.332K tokens$0.03$0.05
Microsoft: Phi-3 Mini 128K Instruct128K tokens$0.10$0.10
Microsoft: Phi-3 Medium 128K Instruct128K tokens$1.00$1.00
NeverSleep: Llama 3 Lumimaid 70B8K tokens$4.00$6.00
Google: Gemini 1.5 Flash1M tokens$0.08$0.30
OpenAI: GPT-4o128K tokens$2.50$10.00
OpenAI: GPT-4o (extended)128K tokens$6.00$18.00
Meta: LlamaGuard 2 8B8K tokens$0.20$0.20
OpenAI: GPT-4o (2024-05-13)128K tokens$5.00$15.00
NeverSleep: Llama 3 Lumimaid 8B24K tokens$0.20$1.25
Fimbulvetr 11B v24K tokens$0.80$1.20
Meta: Llama 3 8B Instruct8K tokens$0.03$0.06
Meta: Llama 3 70B Instruct8K tokens$0.30$0.40
Mistral: Mixtral 8x22B Instruct65K tokens$0.90$0.90
WizardLM-2 8x22B65K tokens$0.48$0.48
Google: Gemini 1.5 Pro2M tokens$1.25$5.00
OpenAI: GPT-4 Turbo128K tokens$10.00$30.00
Cohere: Command R+128K tokens$3.00$15.00
Cohere: Command R+ (04-2024)128K tokens$3.00$15.00
Midnight Rose 70B4K tokens$0.80$0.80
Cohere: Command4K tokens$1.00$2.00
Cohere: Command R128K tokens$0.50$1.50
Anthropic: Claude 3 Haiku (self-moderated)200K tokens$0.25$1.25
Anthropic: Claude 3 Haiku200K tokens$0.25$1.25
Anthropic: Claude 3 Opus (self-moderated)200K tokens$15.00$75.00
Anthropic: Claude 3 Opus200K tokens$15.00$75.00
Anthropic: Claude 3 Sonnet (self-moderated)200K tokens$3.00$15.00
Anthropic: Claude 3 Sonnet200K tokens$3.00$15.00
Cohere: Command R (03-2024)128K tokens$0.50$1.50
Mistral Large128K tokens$2.00$6.00
OpenAI: GPT-3.5 Turbo (older v0613)4K tokens$1.00$2.00
OpenAI: GPT-4 Turbo Preview128K tokens$10.00$30.00
Nous: Hermes 2 Mixtral 8x7B DPO32K tokens$0.60$0.60
Mistral Small32K tokens$0.20$0.60
Mistral Tiny32K tokens$0.25$0.25
Mistral: Mistral 7B Instruct v0.232K tokens$0.20$0.20
Mistral: Mixtral 8x7B Instruct32K tokens$0.08$0.24
Noromaid 20B8K tokens$1.25$2.00
Anthropic: Claude v2.1 (self-moderated)200K tokens$8.00$24.00
Anthropic: Claude v2.1200K tokens$8.00$24.00
Anthropic: Claude v2 (self-moderated)200K tokens$8.00$24.00
Anthropic: Claude v2.0100K tokens$8.00$24.00
ReMM SLERP 13B4K tokens$0.80$1.20
MythoMax 13B4K tokens$0.07$0.07
OpenAI: GPT-48K tokens$30.00$60.00
OpenAI: GPT-4 (older v0314)8K tokens$30.00$60.00
Meta Llama 3 70B Instruct4K tokens$50.00$500.00
Meta Llama 3 8B Instruct4K tokens$50.00$500.00
Meta Llama 3 8B4K tokens$50.00$500.00
Incredibly Fast Whisper4K tokens$50.00$500.00