Search models/

Model catalog

306 models · live pricing · modeled monthly cost · 10 first-party tested · one OpenAI-compatible key. Verified July 2026.

AI21 1AionLabs 4AllenAI 1Amazon 5Anthracite-org 1Anthropic 15Arcee AI 4Baidu 1ByteDance 1ByteDance Seed 4Cohere 5Deep Cogito 1DeepSeek 13Google 24Gryphe 1IBM 2Inception 1inclusionAI 3Inflection 2Kwaipilot 1LiquidAI 1Mancer 1Meta 10Microsoft 3MiniMax 8Mistral 20MoonshotAI 6Morph 2Nex AGI 1Nous 4NVIDIA 5OpenAI 62Perceptron 1Perplexity 5Poolside 2Qwen 46Rekaai 2Relace 2Sakana 1Sao10K 4StepFun 2Switchpoint 1Tencent 2TheDrummer 4Undi95 1Upstage 1Writer 1xAI 4Xiaomi 2Z.ai 12

First-party tested models

We ran these on our executed 9-task coding benchmark — scores are measured, not vendor-reported. Methodology.

Kimi K2.7 Code
MoonshotAI · scored 9/9 · $3.50/1M out
Qwen3 Coder Next
Qwen · scored 9/9 · $0.80/1M out
DeepSeek V4 Flash
DeepSeek · scored 9/9 · $0.18/1M out
Claude Opus 4.8
Anthropic · scored 9/9 · $25.00/1M out
Nemotron 3 Ultra
NVIDIA · scored 8/9 · $2.20/1M out
GLM 5.2
Z.ai · scored 8/9 · $3.00/1M out
MiniMax M3
MiniMax · scored 8/9 · $1.20/1M out
DeepSeek V4 Pro
DeepSeek · scored 8/9 · $0.87/1M out

AI21 (1)

ModelInput / 1MOutput / 1MContextTested
Jamba Large 1.7$2.00$8.00256K—

AionLabs (4)

ModelInput / 1MOutput / 1MContextTested
Aion-1.0$4.00$8.00131K—
Aion-1.0-Mini$0.70$1.40131K—
Aion-2.0$0.80$1.60131K—
Aion-RP 1.0 (8B)$0.80$1.6033K—

AllenAI (1)

ModelInput / 1MOutput / 1MContextTested
Olmo 3 32B Think$0.15$0.5066K—

Amazon (5)

ModelInput / 1MOutput / 1MContextTested
Nova 2 Lite$0.30$2.501M—
Nova Lite 1.0$0.06$0.24300K—
Nova Micro 1.0$0.04$0.14128K—
Nova Premier 1.0$2.50$12.501M—
Nova Pro 1.0$0.80$3.20300K—

Anthracite-org (1)

ModelInput / 1MOutput / 1MContextTested
Magnum v4 72B$3.00$5.0033K—

Anthropic (15)

ModelInput / 1MOutput / 1MContextTested
Claude 3 Haiku$0.25$1.25200K—
Claude Fable 5$10.00$50.001M—
Claude Haiku 4.5$1.00$5.00200K—
Claude Opus 4$15.00$75.00200K—
Claude Opus 4.1$15.00$75.00200K—
Claude Opus 4.5$5.00$25.00200K—
Claude Opus 4.6$5.00$25.001M—
Claude Opus 4.7$5.00$25.001M—
Claude Opus 4.7 (Fast)$30.00$1501M—
Claude Opus 4.8$5.00$25.001M9/9
Claude Opus 4.8 (Fast)$10.00$50.001M—
Claude Sonnet 4$3.00$15.001M—
Claude Sonnet 4.5$3.00$15.001M—
Claude Sonnet 4.6$3.00$15.001M—
Claude Sonnet 5$2.00$10.001M—

Arcee AI (4)

ModelInput / 1MOutput / 1MContextTested
Coder Large$0.50$0.8033K—
Trinity Large Thinking$0.25$0.80262K—
Trinity Mini$0.04$0.15131K—
Virtuoso Large$0.75$1.20131K—

Baidu (1)

ModelInput / 1MOutput / 1MContextTested
ERNIE 4.5 VL 424B A47B $0.42$1.25131K—

ByteDance (1)

ModelInput / 1MOutput / 1MContextTested
UI-TARS 7B $0.10$0.20128K—

ByteDance Seed (4)

ModelInput / 1MOutput / 1MContextTested
Seed 1.6$0.25$2.00262K—
Seed 1.6 Flash$0.07$0.30262K—
Seed-2.0-Lite$0.25$2.00262K—
Seed-2.0-Mini$0.10$0.40262K—

Cohere (5)

ModelInput / 1MOutput / 1MContextTested
Command A$2.50$10.00256K—
Command R (08-2024)$0.15$0.60128K—
Command R+ (08-2024)$2.50$10.00128K—
Command R7B (12-2024)$0.04$0.15128K—
North Mini Code (free)FreeFree256K6/9

Deep Cogito (1)

ModelInput / 1MOutput / 1MContextTested
Cogito v2.1 671B$1.25$1.25128K—

DeepSeek (13)

ModelInput / 1MOutput / 1MContextTested
DeepSeek V3$0.20$0.80131K—
DeepSeek V3 0324$0.24$0.90164K—
DeepSeek V3.1$0.21$0.79164K—
R1$0.70$2.50164K—
R1 0528$0.50$2.15164K—
R1 Distill Llama 70B$0.80$0.80128K—
R1$0.70$2.50164K—
DeepSeek V3.1 Terminus$0.27$0.95164K—
DeepSeek V3.2$0.23$0.34131K—
DeepSeek V3.2 Exp$0.27$0.41164K—
DeepSeek V3.2$0.23$0.34131K—
DeepSeek V4 Flash$0.09$0.181M9/9
DeepSeek V4 Pro$0.43$0.871M8/9

Google (24)

ModelInput / 1MOutput / 1MContextTested
Gemini 2.5 Flash$0.30$2.501M—
Nano Banana (Gemini 2.5 Flash Image)$0.30$2.5033K—
Gemini 2.5 Flash Lite$0.10$0.401M—
Gemini 2.5 Flash Lite Preview 09-2025$0.10$0.401M—
Gemini 2.5 Pro$1.25$10.001M—
Gemini 2.5 Pro Preview 06-05$1.25$10.001M—
Gemini 2.5 Pro Preview 05-06$1.25$10.001M—
Gemini 3 Flash Preview$0.50$3.001M—
Nano Banana Pro (Gemini 3 Pro Image Preview)$2.00$12.0066K—
Nano Banana 2 (Gemini 3.1 Flash Image Preview)$0.50$3.00131K—
Gemini 3.1 Flash Lite$0.25$1.501M—
Gemini 3.1 Flash Lite Preview$0.25$1.501M—
Gemini 3.1 Pro Preview$2.00$12.001M—
Gemini 3.1 Pro Preview Custom Tools$2.00$12.001M—
Gemini 3.5 Flash$1.50$9.001M—
Gemma 2 27B$0.65$0.658K—
Gemma 3 12B$0.05$0.15131K—
Gemma 3 27B$0.08$0.16131K—
Gemma 3 4B$0.05$0.10131K—
Gemma 3n 4B$0.06$0.1233K—
Gemma 4 26B A4B $0.06$0.33262K—
Gemma 4 31B$0.12$0.35262K—
Lyria 3 Clip PreviewFreeFree1M—
Lyria 3 Pro PreviewFreeFree1M—

Gryphe (1)

ModelInput / 1MOutput / 1MContextTested
MythoMax 13B$0.06$0.064K—

IBM (2)

ModelInput / 1MOutput / 1MContextTested
Granite 4.0 Micro$0.02$0.11131K—
Granite 4.1 8B$0.05$0.10131K—

Inception (1)

ModelInput / 1MOutput / 1MContextTested
Mercury 2$0.25$0.75128K—

inclusionAI (3)

ModelInput / 1MOutput / 1MContextTested
Ling-2.6-1T$0.07$0.63262K—
Ling-2.6-flash$0.01$0.03262K—
Ring-2.6-1T$0.07$0.63262K—

Inflection (2)

ModelInput / 1MOutput / 1MContextTested
Inflection 3 Pi$2.50$10.008K—
Inflection 3 Productivity$2.50$10.008K—

Kwaipilot (1)

ModelInput / 1MOutput / 1MContextTested
KAT-Coder-Pro V2$0.30$1.20256K—

LiquidAI (1)

ModelInput / 1MOutput / 1MContextTested
LFM2-24B-A2B$0.03$0.12128K—

Mancer (1)

ModelInput / 1MOutput / 1MContextTested
Weaver (alpha)$0.75$1.008K—

Meta (10)

ModelInput / 1MOutput / 1MContextTested
Llama 3 8B Instruct$0.14$0.148K—
Llama 3.1 70B Instruct$0.40$0.40131K—
Llama 3.1 8B Instruct$0.02$0.03131K—
Llama 3.2 11B Vision Instruct$0.34$0.34131K—
Llama 3.2 1B Instruct$0.03$0.20131K—
Llama 3.2 3B Instruct$0.05$0.34131K—
Llama 3.3 70B Instruct$0.10$0.32131K—
Llama 4 Maverick$0.15$0.601M—
Llama 4 Scout$0.10$0.3010M—
Llama Guard 4 12B$0.18$0.18164K—

Microsoft (3)

ModelInput / 1MOutput / 1MContextTested
Phi 4$0.07$0.1416K—
Phi 4$0.07$0.1416K—
WizardLM-2 8x22B$0.62$0.6266K—

MiniMax (8)

ModelInput / 1MOutput / 1MContextTested
MiniMax-01$0.20$1.101M—
MiniMax M1$0.40$2.201M—
MiniMax M2$0.26$1.02205K—
MiniMax M2-her$0.30$1.2066K—
MiniMax M2.1$0.30$1.20205K—
MiniMax M2.5$0.12$0.48205K—
MiniMax M2.7$0.18$0.72205K—
MiniMax M3$0.30$1.201M8/9

Mistral (20)

ModelInput / 1MOutput / 1MContextTested
Codestral 2508$0.30$0.90256K—
Devstral 2 2512$0.40$2.00262K—
Ministral 3 14B 2512$0.20$0.20262K—
Ministral 3 3B 2512$0.10$0.10131K—
Ministral 3 8B 2512$0.15$0.15262K—
Mistral Large$2.00$6.00128K—
Mistral Large 2407$2.00$6.00131K—
Mistral Large$2.00$6.00128K—
Mistral Large 3 2512$0.50$1.50262K—
Mistral Medium 3$0.40$2.00131K—
Mistral Medium 3.5$1.50$7.50262K—
Mistral Medium 3.1$0.40$2.00131K—
Mistral Nemo$0.02$0.03131K—
Saba$0.20$0.6033K—
Mistral Small 3$0.05$0.0833K—
Mistral Small 4$0.15$0.60262K—
Mistral Small 3.1 24B$0.35$0.55128K—
Mistral Small 3.2 24B$0.07$0.20128K—
Mixtral 8x22B Instruct$2.00$6.0066K—
Voxtral Small 24B 2507$0.10$0.3032K—

MoonshotAI (6)

ModelInput / 1MOutput / 1MContextTested
Kimi K2 0711$0.57$2.30131K—
Kimi K2 0905$0.60$2.50262K—
Kimi K2 Thinking$0.60$2.50262K—
Kimi K2.5$0.38$2.02262K—
Kimi K2.6$0.55$3.20262K—
Kimi K2.7 Code$0.74$3.50262K9/9

Morph (2)

ModelInput / 1MOutput / 1MContextTested
Morph V3 Fast$0.80$1.2082K—
Morph V3 Large$0.90$1.90262K—

Nex AGI (1)

ModelInput / 1MOutput / 1MContextTested
Nex-N2-Pro$0.25$1.00262K—

Nous (4)

ModelInput / 1MOutput / 1MContextTested
Hermes 3 405B Instruct$1.00$1.00131K—
Hermes 3 70B Instruct$0.70$0.70131K—
Hermes 4 405B$1.00$3.00131K—
Hermes 4 70B$0.13$0.40131K—

NVIDIA (5)

ModelInput / 1MOutput / 1MContextTested
Llama 3.3 Nemotron Super 49B V1.5$0.40$0.40131K—
Nemotron 3 Nano 30B A3B$0.05$0.20262K—
Nemotron 3 Super$0.08$0.401M—
Nemotron 3 Ultra$0.50$2.201M8/9
Nemotron Nano 9B V2 (free)FreeFree128K—

OpenAI (62)

ModelInput / 1MOutput / 1MContextTested
GPT-3.5 Turbo$0.50$1.5016K—
GPT-3.5 Turbo (older v0613)$1.00$2.004K—
GPT-3.5 Turbo 16k$3.00$4.0016K—
GPT-3.5 Turbo Instruct$1.50$2.004K—
GPT-4$30.00$60.008K—
GPT-4$30.00$60.008K—
GPT-4$30.00$60.008K—
GPT-4 Turbo$10.00$30.00128K—
GPT-4 Turbo Preview$10.00$30.00128K—
GPT-4.1$2.00$8.001M—
GPT-4.1 Mini$0.40$1.601M—
GPT-4.1 Nano$0.10$0.401M—
GPT-4o$2.50$10.00128K—
GPT-4o (2024-05-13)$5.00$15.00128K—
GPT-4o (2024-08-06)$2.50$10.00128K—
GPT-4o (2024-11-20)$2.50$10.00128K—
GPT-4o-mini$0.15$0.60128K—
GPT-4o-mini (2024-07-18)$0.15$0.60128K—
GPT-4o-mini Search Preview$0.15$0.60128K—
GPT-4o Search Preview$2.50$10.00128K—
GPT-5$1.25$10.00400K—
GPT-5 Chat$1.25$10.00128K—
GPT-5 Codex$1.25$10.00400K—
GPT-5 Image$10.00$10.00400K—
GPT-5 Image Mini$2.50$2.00400K—
GPT-5 Mini$0.25$2.00400K—
GPT-5 Nano$0.05$0.40400K—
GPT-5 Pro$15.00$120400K—
GPT-5.1$1.25$10.00400K—
GPT-5.1 Chat$1.25$10.00128K—
GPT-5.1-Codex$1.25$10.00400K—
GPT-5.1-Codex-Max$1.25$10.00400K—
GPT-5.1-Codex-Mini$0.25$2.00400K—
GPT-5.2$1.75$14.00400K—
GPT-5.2 Chat$1.75$14.00128K—
GPT-5.2-Codex$1.75$14.00400K—
GPT-5.2 Pro$21.00$168400K—
GPT-5.3 Chat$1.75$14.00128K—
GPT-5.3-Codex$1.75$14.00400K—
GPT-5.4$2.50$15.001M—
GPT-5.4 Image 2$8.00$15.00272K—
GPT-5.4 Mini$0.75$4.50400K—
GPT-5.4 Nano$0.20$1.25400K—
GPT-5.4 Pro$30.00$1801M—
GPT-5.5$5.00$30.001M—
GPT-5.5 Pro$30.00$1801M—
GPT Audio$2.50$10.00128K—
GPT Audio Mini$0.60$2.40128K—
GPT Chat Latest$5.00$30.00400K—
gpt-oss-120b$0.03$0.15131K—
gpt-oss-20b$0.03$0.14131K—
gpt-oss-safeguard-20b$0.07$0.30131K—
o1$15.00$60.00200K—
o1-pro$150$600200K—
o3$2.00$8.00200K—
o3 Deep Research$10.00$40.00200K—
o3 Mini$1.10$4.40200K—
o3 Mini High$1.10$4.40200K—
o3 Pro$20.00$80.00200K—
o4 Mini$1.10$4.40200K—
o4 Mini Deep Research$2.00$8.00200K—
o4 Mini High$1.10$4.40200K—

Perceptron (1)

ModelInput / 1MOutput / 1MContextTested
Perceptron Mk1$0.15$1.5033K—

Perplexity (5)

ModelInput / 1MOutput / 1MContextTested
Sonar$1.00$1.00127K—
Sonar Deep Research$2.00$8.00128K—
Sonar Pro$3.00$15.00200K—
Sonar Pro Search$3.00$15.00200K—
Sonar Reasoning Pro$2.00$8.00128K—

Poolside (2)

ModelInput / 1MOutput / 1MContextTested
Laguna M.1$0.20$0.40262K—
Laguna XS.2$0.10$0.20262K—

Qwen (46)

ModelInput / 1MOutput / 1MContextTested
Qwen2.5 72B Instruct$0.36$0.40131K—
Qwen2.5 7B Instruct$0.04$0.10131K—
Qwen2.5 Coder 32B Instruct$0.66$1.00128K—
Qwen-Plus$0.26$0.781M—
Qwen Plus 0728$0.26$0.781M—
Qwen2.5 VL 72B Instruct$0.80$1.00131K—
Qwen3 14B$0.10$0.24132K—
Qwen3 235B A22B$0.45$1.82131K—
Qwen3 235B A22B Instruct 2507$0.09$0.10262K—
Qwen3 235B A22B Thinking 2507$0.15$1.50262K—
Qwen3 30B A3B$0.12$0.50131K—
Qwen3 30B A3B Instruct 2507$0.05$0.19131K—
Qwen3 30B A3B Thinking 2507$0.13$1.56131K—
Qwen3 32B$0.08$0.28131K—
Qwen3 8B$0.12$0.45131K—
Qwen3 Coder 480B A35B$0.22$1.801M—
Qwen3 Coder 30B A3B Instruct$0.07$0.27160K—
Qwen3 Coder Flash$0.20$0.971M—
Qwen3 Coder Next$0.11$0.80262K9/9
Qwen3 Coder Plus$0.65$3.251M—
Qwen3 Max$0.78$3.90262K—
Qwen3 Max Thinking$0.78$3.90262K—
Qwen3 Next 80B A3B Instruct$0.09$1.10262K—
Qwen3 Next 80B A3B Thinking$0.10$0.78262K—
Qwen3 VL 235B A22B Instruct$0.20$0.88262K—
Qwen3 VL 235B A22B Thinking$0.26$2.60131K—
Qwen3 VL 30B A3B Instruct$0.13$0.52262K—
Qwen3 VL 30B A3B Thinking$0.13$1.56131K—
Qwen3 VL 32B Instruct$0.10$0.42262K—
Qwen3 VL 8B Instruct$0.12$0.45256K—
Qwen3 VL 8B Thinking$0.12$1.36256K—
Qwen3.5-122B-A10B$0.26$2.08262K—
Qwen3.5-27B$0.20$1.56262K—
Qwen3.5-35B-A3B$0.14$1.00262K—
Qwen3.5 397B A17B$0.39$2.45256K—
Qwen3.5-9B$0.10$0.15262K—
Qwen3.5-Flash$0.07$0.261M—
Qwen3.5 Plus 2026-02-15$0.26$1.561M—
Qwen3.5 Plus 2026-04-20$0.30$1.801M—
Qwen3.6 27B$0.29$2.40262K—
Qwen3.6 35B A3B$0.14$1.00262K—
Qwen3.6 Flash$0.19$1.131M—
Qwen3.6 Max Preview$1.04$6.24262K—
Qwen3.6 Plus$0.33$1.951M—
Qwen3.7 Max$1.25$3.751M—
Qwen3.7 Plus$0.32$1.281M—

Rekaai (2)

ModelInput / 1MOutput / 1MContextTested
Reka Edge$0.10$0.1016K—
Reka Flash 3$0.10$0.2066K—

Relace (2)

ModelInput / 1MOutput / 1MContextTested
Relace Apply 3$0.85$1.25256K—
Relace Search$1.00$3.00256K—

Sakana (1)

ModelInput / 1MOutput / 1MContextTested
Fugu Ultra$5.00$30.001M—

Sao10K (4)

ModelInput / 1MOutput / 1MContextTested
Llama 3 8B Lunaris$0.04$0.058K—
Llama 3.1 70B Hanami x1$3.00$3.0016K—
Llama 3.1 Euryale 70B v2.2$0.85$0.85131K—
Llama 3.3 Euryale 70B$0.65$0.75131K—

StepFun (2)

ModelInput / 1MOutput / 1MContextTested
Step 3.5 Flash$0.10$0.30262K—
Step 3.7 Flash$0.20$1.15256K7/9

Switchpoint (1)

ModelInput / 1MOutput / 1MContextTested
Switchpoint Router$0.85$3.40131K—

Tencent (2)

ModelInput / 1MOutput / 1MContextTested
Hunyuan A13B Instruct$0.14$0.57131K—
Hy3 preview$0.06$0.21262K—

TheDrummer (4)

ModelInput / 1MOutput / 1MContextTested
Cydonia 24B V4.1$0.30$0.50131K—
Rocinante 12B$0.25$0.5033K—
Skyfall 36B V2$0.55$0.8033K—
UnslopNemo 12B$0.40$0.4033K—

Undi95 (1)

ModelInput / 1MOutput / 1MContextTested
ReMM SLERP 13B$0.45$0.656K—

Upstage (1)

ModelInput / 1MOutput / 1MContextTested
Solar Pro 3$0.15$0.60128K—

Writer (1)

ModelInput / 1MOutput / 1MContextTested
Palmyra X5$0.60$6.001M—

xAI (4)

ModelInput / 1MOutput / 1MContextTested
Grok 4.20$1.25$2.502M—
Grok 4.20 Multi-Agent$1.25$2.502M—
Grok 4.3$1.25$2.501M—
Grok Build 0.1$1.00$2.00256K—

Xiaomi (2)

ModelInput / 1MOutput / 1MContextTested
MiMo-V2.5$0.10$0.281M—
MiMo-V2.5-Pro$0.43$0.871M—

Z.ai (12)

ModelInput / 1MOutput / 1MContextTested
GLM 4.5$0.60$2.20131K—
GLM 4.5 Air$0.13$0.85131K—
GLM 4.5V$0.60$1.8066K—
GLM 4.6$0.43$1.74203K—
GLM 4.6V$0.30$0.90131K—
GLM 4.7$0.40$1.75203K—
GLM 4.7 Flash$0.06$0.40203K—
GLM 5$0.60$1.92203K—
GLM 5 Turbo$1.20$4.00262K—
GLM 5.1$0.97$4.30203K—
GLM 5.2$0.93$3.001M8/9
GLM 5V Turbo$1.20$4.00203K—

Retired & renamed models (34)

These model ids are no longer served in the live catalog. Each page shows its status and links to the closest current replacement.

Retired model idStatus
alfredpros/codellama-7b-instruct-solidityretired · see replacement →
alibaba/tongyi-deepresearch-30b-a3bretired · see replacement →
anthropic/claude-3.5-haikuretired · see replacement →
anthropic/claude-opus-4.6-fastretired · see replacement →
arcee-ai/maestro-reasoningretired · see replacement →
arcee-ai/spotlightretired · see replacement →
arcee-ai/trinity-large-previewretired · see replacement →
baidu/ernie-4.5-21b-a3bretired · see replacement →
baidu/ernie-4.5-21b-a3b-thinkingretired · see replacement →
baidu/ernie-4.5-300b-a47bretired · see replacement →
baidu/ernie-4.5-vl-28b-a3bretired · see replacement →
essentialai/rnj-1-instructretired · see replacement →
google/gemini-2.0-flash-001retired · see replacement →
google/gemini-2.0-flash-lite-001retired · see replacement →
meta-llama/llama-3-70b-instructretired · see replacement →
meta-llama/llama-guard-3-8bretired · see replacement →
mistralai/devstral-mediumretired · see replacement →
mistralai/devstral-smallretired · see replacement →
mistralai/mistral-7b-instruct-v0.1retired · see replacement →
mistralai/pixtral-large-2411retired · see replacement →
nex-agi/deepseek-v3.1-nex-n1retired · see replacement →
nousresearch/hermes-2-pro-llama-3-8bretired · see replacement →
openai/gpt-4o-audio-previewretired · see replacement →
prime-intellect/intellect-3retired · see replacement →
sao10k/l3-euryale-70bretired · see replacement →
x-ai/grok-3retired · see replacement →
x-ai/grok-3-betaretired · see replacement →
x-ai/grok-3-miniretired · see replacement →
x-ai/grok-3-mini-betaretired · see replacement →
x-ai/grok-4retired · see replacement →
x-ai/grok-4-fastretired · see replacement →
x-ai/grok-4.1-fastretired · see replacement →
x-ai/grok-code-fast-1retired · see replacement →
z-ai/glm-4-32bretired · see replacement →

One key for every model above

OpenAI-compatible endpoint, live price comparison, routing and failover.

Get an API keySee pricing