The public model catalog
Every model.
Without vendor marketing.
Search 472 publicly available models by the constraints that matter in production: price, context, modalities, tools, reasoning, and open-weight availability.
showing 472 / 472
- AionLabs: Aion 3.5aion-labs/aion-3.5-20260923262K ctx$3 in · $6 outtoolsrsn262K ctx · $3/$6 per M · tools
- AionLabs: Aion 3.5 Miniaion-labs/aion-3.5-mini-20260923262K ctx$0.70 in · $1.40 outtoolsrsn262K ctx · $0.70/$1.40 per M · tools
- AionLabs: Aion-2.0aion-labs/aion-2.0-20260223131K ctx$0.80 in · $1.60 outtoolsrsn131K ctx · $0.80/$1.60 per M · tools
- AionLabs: Aion-3.0aion-labs/aion-3.0-20260707131K ctx$3 in · $6 outtoolsrsn131K ctx · $3/$6 per M · tools
- AionLabs: Aion-3.0-Miniaion-labs/aion-3.0-mini-20260707131K ctx$0.70 in · $1.40 outtoolsrsn131K ctx · $0.70/$1.40 per M · tools
- AionLabs: Aion-RP 1.0 (8B)aion-labs/aion-rp-llama-3.1-8b33K ctx$0.80 in · $1.60 outopen-weight33K ctx · $0.80/$1.60 per M
- Amazon: Nova 2 Liteamazon/nova-2-lite-v11M ctx$0.30 in · $2.50 outtoolsvisrsn1M ctx · $0.30/$2.50 per M · tools · vis
- Amazon: Nova Lite 1.0amazon/nova-lite-v1300K ctx$0.060 in · $0.24 outtoolsvis300K ctx · $0.060/$0.24 per M · tools · vis
- Amazon: Nova Micro 1.0amazon/nova-micro-v1128K ctx$0.035 in · $0.14 outtools128K ctx · $0.035/$0.14 per M · tools
- Amazon: Nova Premier 1.0amazon/nova-premier-v11M ctx$2.50 in · $12.50 outtoolsvis1M ctx · $2.50/$12.50 per M · tools · vis
- Amazon: Nova Pro 1.0amazon/nova-pro-v1300K ctx$0.80 in · $3.20 outtoolsvis300K ctx · $0.80/$3.20 per M · tools · vis
- Anthropic: Claude Fable 5anthropic/claude-5-fable-202606091M ctx$10 in · $50 outtoolsvisrsn1M ctx · $10/$50 per M · tools · vis
- Anthropic: Claude Fable 5.1anthropic/claude-fable-5.1-202608311M ctx$10 in · $50 outtoolsvisrsn1M ctx · $10/$50 per M · tools · vis
- Anthropic: Claude Haiku 4.5anthropic/claude-4.5-haiku-20251001200K ctx$1 in · $5 outtoolsvisrsn200K ctx · $1/$5 per M · tools · vis
- Anthropic: Claude Haiku 5.5Newanthropic/claude-haiku-5.5-202610071M ctx$0.100 in · $0.50 outtoolsvisrsn1M ctx · $0.100/$0.50 per M · tools · vis
- Anthropic: Claude Opus 4.1anthropic/claude-4.1-opus-20250805200K ctx$15 in · $75 outtoolsvisrsn200K ctx · $15/$75 per M · tools · vis
- Anthropic: Claude Opus 4.5anthropic/claude-4.5-opus-20251124200K ctx$5 in · $25 outtoolsvisrsn200K ctx · $5/$25 per M · tools · vis
- Anthropic: Claude Opus 4.6anthropic/claude-4.6-opus-202602051M ctx$5 in · $25 outtoolsvisrsn1M ctx · $5/$25 per M · tools · vis
- Anthropic: Claude Opus 4.7anthropic/claude-4.7-opus-202604161M ctx$5 in · $25 outtoolsvisrsn1M ctx · $5/$25 per M · tools · vis
- Anthropic: Claude Opus 4.8anthropic/claude-4.8-opus-202605281M ctx$5 in · $25 outtoolsvisrsn1M ctx · $5/$25 per M · tools · vis
- Anthropic: Claude Opus 5anthropic/claude-opus-5-202607231M ctx$5 in · $25 outtoolsvisrsn1M ctx · $5/$25 per M · tools · vis
- Anthropic: Claude Opus 5.5anthropic/claude-opus-5.5-202609211M ctx$4 in · $20 outtoolsvisrsn1M ctx · $4/$20 per M · tools · vis
- Anthropic: Claude Sonnet 4anthropic/claude-4-sonnet-20250522200K ctx$3 in · $15 outtoolsvisrsn200K ctx · $3/$15 per M · tools · vis
- Anthropic: Claude Sonnet 4.5anthropic/claude-4.5-sonnet-202509291M ctx$3 in · $15 outtoolsvisrsn1M ctx · $3/$15 per M · tools · vis
- Anthropic: Claude Sonnet 4.6anthropic/claude-4.6-sonnet-202602171M ctx$3 in · $15 outtoolsvisrsn1M ctx · $3/$15 per M · tools · vis
- Anthropic: Claude Sonnet 5anthropic/claude-sonnet-5-202606301M ctx$2 in · $10 outtoolsvisrsn1M ctx · $2/$10 per M · tools · vis
- Anthropic: Claude Sonnet 5.5anthropic/claude-sonnet-5.5-202609281M ctx$2 in · $10 outtoolsvisrsn1M ctx · $2/$10 per M · tools · vis
- Aplomb 1 (5.3B decision model on Qwen3.5-4B, trained readout head, self-hosted)Newempiriolabsai/aplomb-1— ctx— in · — out— ctx · —/— per M
- APUS-OpenJev-v1-9B (merged bf16 checkpoint-3000 on Qwen3.5-9B, their own native runtime, full depth, self-hosted)Newapus-ailab/apus-openjev-v1-9b— ctx— in · — out— ctx · —/— per M
- Arcee AI: Trinity Large Thinkingarcee-ai/trinity-large-thinking262K ctx$0.25 in · $0.80 outtoolsrsnopen-weight262K ctx · $0.25/$0.80 per M · tools
- AutoJev-27B (denis-pplx, Qwen3.8-27B)Newdenis-pplx/autojev-27b— ctx— in · — out— ctx · —/— per M
- Bespoke Nimble 9B (Bespoke Labs)Newbespoke-labs/nimble-9b— ctx— in · — outopen-weight— ctx · —/— per M
- Bespoke Nimble 9B v3 (Qwen3.5-9B LoRA)Newbespokelabs/bespoke-nimble-9b-v3— ctx— in · — out— ctx · —/— per M
- Bev / Bonsai 27BNewreza2kn/bev— ctx— in · — outopen-weight— ctx · —/— per M
- Bobcat Flash 1.2 (Gemma-4-26B-A4B-it + two merged rank-64 LoRA adapters, typed-decision readout at the first answer position, FP8, self-hosted)Newsanghwa-na/bobcat-flash-1.2— ctx— in · — out— ctx · —/— per M
- ByteDance Seed: Seed 1.6bytedance-seed/seed-1.6-20250625262K ctx$0.25 in · $2 outtoolsvisrsn262K ctx · $0.25/$2 per M · tools · vis
- ByteDance Seed: Seed 1.6 Flashbytedance-seed/seed-1.6-flash-20250625262K ctx$0.075 in · $0.30 outtoolsvisrsn262K ctx · $0.075/$0.30 per M · tools · vis
- ByteDance Seed: Seed 2.1 Turbobytedance-seed/seed-2-1-turbo-20260810262K ctx$0.50 in · $2.50 outtoolsvisrsn262K ctx · $0.50/$2.50 per M · tools · vis
- ByteDance Seed: Seed-2.0-Codebytedance-seed/seed-2.0-code-20260730262K ctx$0.50 in · $3 outtoolsvisrsn262K ctx · $0.50/$3 per M · tools · vis
- ByteDance Seed: Seed-2.0-Litebytedance-seed/seed-2.0-lite-20260309262K ctx$0.25 in · $2 outtoolsvisrsn262K ctx · $0.25/$2 per M · tools · vis
- ByteDance Seed: Seed-2.0-Minibytedance-seed/seed-2.0-mini-20260224262K ctx$0.100 in · $0.40 outtoolsvisrsn262K ctx · $0.100/$0.40 per M · tools · vis
- ByteDance: UI-TARS 7Bbytedance/ui-tars-1.5-7b128K ctx$0.100 in · $0.20 outvis128K ctx · $0.100/$0.20 per M · vis
- Certo v1 (AltSlate Labs)Newaltslate/certo-decision-model— ctx— in · — outopen-weight— ctx · —/— per M
- ClassOne Gemma 4 E2B (Gemma-4-E2B backbone with ClassOne decision heads, schema-constrained single forward pass, self-hosted)Newdevops-thiago/classone-gemma4-e2b— ctx— in · — out— ctx · —/— per M
- ClassOne Qwen 3.5 9B (Qwen3.5-9B backbone with ClassOne decision heads, schema-constrained single forward pass, self-hosted)Newdevops-thiago/classone-qwen3.5-9b— ctx— in · — out— ctx · —/— per M
- Clef (Cloudflare, Qwen3.8-27B post-train with a joint schema head, multimodal, measured on text)Newcloudflare/clef— ctx— in · — out— ctx · —/— per M
- Clef-Flash (Cloudflare, Qwen3.5-9B post-train with a joint schema head, multimodal, measured on text)Newcloudflare/clef-flash— ctx— in · — out— ctx · —/— per M
- CLM-8B (Contrastive-LM, clm-latest)Newcontrastive-lm/clm-8b— ctx— in · — outopen-weight— ctx · —/— per M
- CoCo-Decision-4B (corners-ai, LoRA on Qwen3.5-4B, option-label logits of one pass, served by oh-my-jev)Newcorners-ai/coco-decision-4b-ko— ctx— in · — out— ctx · —/— per M
- Cohere: Command Acohere/command-a-03-2025256K ctx$2.50 in · $10 outopen-weight256K ctx · $2.50/$10 per M
- Cohere: Command A+cohere/command-a-plus-05-2026192K ctx$0.30 in · $1.50 outtoolsvisrsnopen-weight192K ctx · $0.30/$1.50 per M · tools · vis
- Cohere: Command R (08-2024)cohere/command-r-08-2024128K ctx$0.15 in · $0.60 outtoolsopen-weight128K ctx · $0.15/$0.60 per M · tools
- Cohere: Command R+ (08-2024)cohere/command-r-plus-08-2024128K ctx$2.50 in · $10 outtoolsopen-weight128K ctx · $2.50/$10 per M · tools
- Cohere: Command R7B (12-2024)cohere/command-r7b-12-2024128K ctx$0.037 in · $0.15 outopen-weight128K ctx · $0.037/$0.15 per M
- Cygnet (blockbrain, frozen Gemma-4-12B-it)Newblockbrain/cygnet— ctx— in · — outopen-weight— ctx · —/— per M
- decider chat on Gemma-4-31B-it (Mapika, frozen base, inference technique)Newmapika/decider-chat-gemma4-31b— ctx— in · — out— ctx · —/— per M
- decider-12b v2 (Mapika)Newmapika/decider-12b— ctx— in · — out— ctx · —/— per M
- decider-2b (Mapika)Newmapika/decider-2b— ctx— in · — outopen-weight— ctx · —/— per M
- decider-35b-a3b (Mapika)Newmapika/decider-35b-a3b— ctx— in · — outopen-weight— ctx · —/— per M
- decider-4b v2 (Mapika)Newmapika/decider-4b-v2— ctx— in · — outopen-weight— ctx · —/— per M
- Decision 2.0 Vega 27B (vLLM-SR, Qwen3.8-27B)Newvllm-sr/decision-2.0-vega-27b— ctx— in · — out— ctx · —/— per M
- Decision 2B (FlyMy.AI, v59)Newflymy-ai/decision-2b-preview— ctx— in · — outopen-weight— ctx · —/— per M
- Decision 4B v1.1 (FlyMyJev, Qwen3.5-4B + LoRA)Newunknown/decision-4b-v11— ctx— in · — out— ctx · —/— per M
- Decision 4B v1.2 (FlyMyJev, Qwen3.5-4B + LoRA)Newunknown/decision-4b-v12— ctx— in · — out— ctx · —/— per M
- Decision Fast (FlyMy.AI, v53a)Newflymy-ai/decision-fast-preview— ctx— in · — outopen-weight— ctx · —/— per M
- Decision-4B (Eval Engine / Chromia)Newevalengine/decision-4b-gguf— ctx— in · — out— ctx · —/— per M
- Deem 0.8B v1Newlibertaidai/deem-0.8-v1— ctx— in · — outopen-weight— ctx · —/— per M
- DeepSeek: DeepSeek V3deepseek/deepseek-chat-v3164K ctx$0.26 in · $1.03 outtools164K ctx · $0.26/$1.03 per M · tools
- DeepSeek: DeepSeek V3 0324deepseek/deepseek-chat-v3-0324164K ctx$0.29 in · $1.14 outtools164K ctx · $0.29/$1.14 per M · tools
- DeepSeek: DeepSeek V3.1deepseek/deepseek-chat-v3.1164K ctx$0.25 in · $0.95 outtoolsrsn164K ctx · $0.25/$0.95 per M · tools
- DeepSeek: DeepSeek V3.1 Terminusdeepseek/deepseek-v3.1-terminus164K ctx$0.27 in · $1 outtoolsrsnopen-weight164K ctx · $0.27/$1 per M · tools
- DeepSeek: DeepSeek V3.2deepseek/deepseek-v3.2-20251201164K ctx$0.28 in · $0.42 outtoolsrsnopen-weight164K ctx · $0.28/$0.42 per M · tools
- DeepSeek: DeepSeek V3.2 Expdeepseek/deepseek-v3.2-exp164K ctx$0.27 in · $0.41 outtoolsrsnopen-weight164K ctx · $0.27/$0.41 per M · tools
- DeepSeek: DeepSeek V4 Flash 0423deepseek/deepseek-v4-flash-202604231.0M ctx$0.091 in · $0.18 outtoolsrsnopen-weight1.0M ctx · $0.091/$0.18 per M · tools
- DeepSeek: DeepSeek V4 Flash 0731deepseek/deepseek-v4-flash-202607311.0M ctx$0.44 in · $1.32 outtoolsrsnopen-weight1.0M ctx · $0.44/$1.32 per M · tools
- DeepSeek: DeepSeek V4 Flash Vision Expdeepseek/deepseek-v4-flash-vision-exp-202608211.0M ctx$0.22 in · $0.65 outtoolsvisrsnopen-weight1.0M ctx · $0.22/$0.65 per M · tools · vis
- DeepSeek: DeepSeek V4 Pro 0423deepseek/deepseek-v4-pro-202604231.0M ctx$0.96 in · $1.91 outtoolsrsnopen-weight1.0M ctx · $0.96/$1.91 per M · tools
- DeepSeek: DeepSeek V4 Pro 0813deepseek/deepseek-v4-pro-202608131.0M ctx$0.66 in · $1.98 outtoolsrsnopen-weight1.0M ctx · $0.66/$1.98 per M · tools
- DeepSeek: DeepSeek V4.1 Flashdeepseek/deepseek-v4.1-flash-202609101.0M ctx$0.056 in · $0.12 outtoolsvisrsnopen-weight1.0M ctx · $0.056/$0.12 per M · tools · vis
- DeepSeek: DeepSeek V4.1 Flash 1017Newdeepseek/deepseek-v4.1-flash-202610171.0M ctx$0.30 in · $1.20 outtoolsvisrsnopen-weight1.0M ctx · $0.30/$1.20 per M · tools · vis
- DeepSeek: R1deepseek/deepseek-r164K ctx$0.70 in · $2.50 outtoolsrsn64K ctx · $0.70/$2.50 per M · tools
- DeepSeek: R1 0528deepseek/deepseek-r1-0528164K ctx$0.50 in · $2.15 outtoolsrsnopen-weight164K ctx · $0.50/$2.15 per M · tools
- Diffusion Jev (DiffusionGemma 26B-A4B on patched SGLang, 48-step diffusion readout, self-hosted)Newgoogle/diffusiongemma-26b-a4b-it— ctx— in · — out— ctx · —/— per M
- Eikos-27B (caiovicentino1, Qwen3.8-27B)Newcaiovicentino1/eikos-27b— ctx— in · — out— ctx · —/— per M
- Elorian: GlimpseNewawaiting resultselorian/glimpse-20261016262K ctx$0.60 in · $3 outtoolsvisrsn262K ctx · $0.60/$3 per M · tools · vis
- EXAONE-4.0-1.2B-JEV v0.3 (unofficial fine-tune of LGAI-EXAONE/EXAONE-4.0-1.2B, native option-label softmax, two reads averaged, self-hosted)Newcarrtesy/exaone-4.0-1.2b-jev— ctx— in · — out— ctx · —/— per M
- Fastino GLiNER-2.5-Decide (hosted API)Newfastino/fastino-gliner-2-5-decide— ctx— in · — out— ctx · —/— per M
- Fireworks: Ember-1fireworks/ember-1-202609231.0M ctx$3 in · $15 outtoolsvisrsn1.0M ctx · $3/$15 per M · tools · vis
- GEV-26B-Decide (AutoTrust, Gemma-4-26B-A4B + LoRA + head)Newautotrust/gev-26b-decide— ctx— in · — out— ctx · —/— per M
- Google: Gemini 2.5 Flashgoogle/gemini-2.5-flash1.0M ctx$0.30 in · $2.50 outtoolsvisrsn1.0M ctx · $0.30/$2.50 per M · tools · vis
- Google: Gemini 2.5 Flash Litegoogle/gemini-2.5-flash-lite1.0M ctx$0.100 in · $0.40 outtoolsvisrsn1.0M ctx · $0.100/$0.40 per M · tools · vis
- Google: Gemini 2.5 Progoogle/gemini-2.5-pro1.0M ctx$1.25 in · $10 outtoolsvisrsn1.0M ctx · $1.25/$10 per M · tools · vis
- Google: Gemini 2.5 Pro Preview 06-05google/gemini-2.5-pro-preview-06-051.0M ctx$1.25 in · $10 outtoolsvisrsn1.0M ctx · $1.25/$10 per M · tools · vis
- Google: Gemini 3 Flash Previewgoogle/gemini-3-flash-preview-202512171.0M ctx$0.50 in · $3 outtoolsvisrsn1.0M ctx · $0.50/$3 per M · tools · vis
- Google: Gemini 3.1 Flash Litegoogle/gemini-3.1-flash-lite-202605071.0M ctx$0.25 in · $1.50 outtoolsvisrsn1.0M ctx · $0.25/$1.50 per M · tools · vis
- Google: Gemini 3.1 Flash Lite Previewgoogle/gemini-3.1-flash-lite-preview-202603031.0M ctx$0.25 in · $1.50 outtoolsvisrsn1.0M ctx · $0.25/$1.50 per M · tools · vis
- Google: Gemini 3.1 Pro Previewgoogle/gemini-3.1-pro-preview-202602191.0M ctx$2 in · $12 outtoolsvisrsn1.0M ctx · $2/$12 per M · tools · vis
- Google: Gemini 3.1 Pro Preview Custom Toolsgoogle/gemini-3.1-pro-preview-customtools-202602191.0M ctx$2 in · $12 outtoolsvisrsn1.0M ctx · $2/$12 per M · tools · vis
- Google: Gemini 3.5 Flashgoogle/gemini-3.5-flash-202605191.0M ctx$1.50 in · $9 outtoolsvisrsn1.0M ctx · $1.50/$9 per M · tools · vis
- Google: Gemini 3.5 Flash Litegoogle/gemini-3.5-flash-lite-202607211.0M ctx$0.30 in · $2.50 outtoolsvisrsn1.0M ctx · $0.30/$2.50 per M · tools · vis
- Google: Gemini 3.6 Flashgoogle/gemini-3.6-flash-202607211.0M ctx$0.75 in · $3.75 outtoolsvisrsn1.0M ctx · $0.75/$3.75 per M · tools · vis
- Google: Gemini 3.7 Flashgoogle/gemini-3.7-flash-202608131.0M ctx$0.75 in · $3.75 outtoolsvisrsn1.0M ctx · $0.75/$3.75 per M · tools · vis
- Google: Gemini 3.8 Flashgoogle/gemini-3.8-flash-202609021.0M ctx$0.83 in · $4.13 outtoolsvisrsn1.0M ctx · $0.83/$4.13 per M · tools · vis
- Google: Gemini 4 ArgonNewgoogle/gemini-4-argon-202610131.0M ctx$2 in · $10 outtoolsvisrsn1.0M ctx · $2/$10 per M · tools · vis
- Google: Gemma 2 27Bgoogle/gemma-2-27b-it8K ctx$0.65 in · $0.65 outopen-weight8K ctx · $0.65/$0.65 per M
- Google: Gemma 3 12Bgoogle/gemma-3-12b-it131K ctx$0.050 in · $0.15 outtoolsvisopen-weight131K ctx · $0.050/$0.15 per M · tools · vis
- Google: Gemma 3 27Bgoogle/gemma-3-27b-it131K ctx$0.080 in · $0.35 outtoolsvisopen-weight131K ctx · $0.080/$0.35 per M · tools · vis
- Google: Gemma 3 4Bgoogle/gemma-3-4b-it131K ctx$0.040 in · $0.050 outvisopen-weight131K ctx · $0.040/$0.050 per M · vis
- Google: Gemma 4 26B A4Bgoogle/gemma-4-26b-a4b-it-20260403262K ctx$0.090 in · $0.30 outtoolsvisrsnopen-weight262K ctx · $0.090/$0.30 per M · tools · vis
- Google: Gemma 4 31Bgoogle/gemma-4-31b-it-20260402262K ctx$0.20 in · $0.40 outtoolsvisrsn262K ctx · $0.20/$0.40 per M · tools · vis
- Google: Lyria 3 Clip Previewgoogle/lyria-3-clip-preview-202603301.0M ctx$0 in · $0 outvis1.0M ctx · $0/$0 per M · vis
- Google: Lyria 3 Pro Previewgoogle/lyria-3-pro-preview-202603301.0M ctx$0 in · $0 outvis1.0M ctx · $0/$0 per M · vis
- Google: Nano Banana (Gemini 2.5 Flash Image)google/gemini-2.5-flash-image33K ctx$0.30 in · $2.50 outvis33K ctx · $0.30/$2.50 per M · vis
- Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview)google/gemini-3.1-flash-image-preview-2026022666K ctx$0.50 in · $3 outvisrsn66K ctx · $0.50/$3 per M · vis
- Google: Nano Banana 2 (Gemini 3.1 Flash Image)google/gemini-3.1-flash-image-20260528131K ctx$0.50 in · $3 outvisrsn131K ctx · $0.50/$3 per M · vis
- Google: Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)google/gemini-3.1-flash-lite-image-2026063066K ctx$0.25 in · $1.50 outvisrsn66K ctx · $0.25/$1.50 per M · vis
- Google: Nano Banana 2.1Newawaiting resultsgoogle/gemini-nano-banana-2.1-2026100666K ctx$1.50 in · $7.50 outtoolsvisrsn66K ctx · $1.50/$7.50 per M · tools · vis
- Google: Nano Banana Pro (Gemini 3 Pro Image Preview)google/gemini-3-pro-image-preview-2025112066K ctx$2 in · $12 outvisrsn66K ctx · $2/$12 per M · vis
- Google: Nano Banana Pro (Gemini 3 Pro Image)google/gemini-3-pro-image-20260528131K ctx$2 in · $12 outtoolsvisrsn131K ctx · $2/$12 per M · tools · vis
- H2O-Lightning-4B v1.1 (H2O.ai, Qwen3.5-4B fine-tune, stock vLLM + open shim)Newh2oai/h2o-lightning-4b— ctx— in · — out— ctx · —/— per M
- Hopper 12B trained (gemma-4-12B-it frozen + LoRA r32 unmerged, one forward pass, self-hosted)Newhopitai/hopper— ctx— in · — out— ctx · —/— per M
- IBM: Granite 4.0 Microibm-granite/granite-4.0-h-micro131K ctx$0.017 in · $0.11 outopen-weight131K ctx · $0.017/$0.11 per M
- IBM: Granite 4.2 8Bibm-granite/granite-4.2-8b-20260831131K ctx$0.060 in · $0.25 outtoolsrsnopen-weight131K ctx · $0.060/$0.25 per M · tools
- Imajev-4B (RTX 5090)Newunknown/imajev-4b-rtx5090-a2— ctx— in · — out— ctx · —/— per M
- Inception: Mercury 2inception/mercury-2-20260304128K ctx$0.25 in · $0.75 outtoolsrsn128K ctx · $0.25/$0.75 per M · tools
- Inception: Mercury 2.5inception/mercury-2.5-20260908260K ctx$0.040 in · $0.15 outtoolsrsn260K ctx · $0.040/$0.15 per M · tools
- Inception: Mercury 3Newawaiting resultsinception/mercury-3-202610191M ctx$0.100 in · $0.35 outtoolsrsn1M ctx · $0.100/$0.35 per M · tools
- inclusionAI: Ling 3.0 Flashinclusionai/ling-3.0-flash-20260723262K ctx$0.021 in · $0.063 outtoolsrsnopen-weight262K ctx · $0.021/$0.063 per M · tools
- inclusionAI: Ling 3.0 Flash Fininclusionai/ling-3.0-flash-fin-20260827262K ctx$0.042 in · $0.12 outtoolsrsn262K ctx · $0.042/$0.12 per M · tools
- inclusionAI: Ling 3.0 Flash Santeinclusionai/ling-3.0-flash-sante-20260904262K ctx$0.042 in · $0.12 outtoolsrsn262K ctx · $0.042/$0.12 per M · tools
- inclusionAI: Ling 3.0 Flash VLinclusionai/ling-3.0-flash-vl-20260910131K ctx$0.060 in · $0.18 outtoolsvisrsnopen-weight131K ctx · $0.060/$0.18 per M · tools · vis
- inclusionAI: Ling 3.1 Flashinclusionai/ling-3.1-flash-20261002262K ctx$0.075 in · $0.22 outtoolsrsnopen-weight262K ctx · $0.075/$0.22 per M · tools
- Inference.net: Schematron V2 Smallinference-net/schematron-v2-small-20260902128K ctx$0.050 in · $0.23 out128K ctx · $0.050/$0.23 per M
- Inference.net: Schematron V2 Turboinference-net/schematron-v2-turbo-20260902128K ctx$0.030 in · $0.15 out128K ctx · $0.030/$0.15 per M
- JADE (Qwen3.8-27B LoRA)Newtheunnecessarythings/jade— ctx— in · — out— ctx · —/— per M
- janus 4B (Icarus AI / cmxu, Qwen3.5-4B + LoRA r64 and pointer decision head)Newcmxu/janus-4b— ctx— in · — out— ctx · —/— per M
- Jebadiah 27B (Frontier Infra, Qwen3.8-27B LoRA)Newfrontier-infra/jebadiah-27b— ctx— in · — out— ctx · —/— per M
- Jev 1.13.0 (TypeSafe AI)Newtypesafe-ai/jev-1.13.0— ctx— in · — out— ctx · —/— per M
- JEV Qwen3.5-9B Base NVFP4Newwilflin/jev-qwen3.5-9b-base-nvfp4— ctx— in · — outopen-weight— ctx · —/— per M
- JEV-27B (AutoTrust, Qwen3.8-27B)Newautotrust/jev-27b— ctx— in · — out— ctx · —/— per M
- jev-local (Qwen3.5-9B)Newus/jev-local— ctx— in · — outopen-weight— ctx · —/— per M
- Jev-Omni (akhilaaa3, Gemma-4-12B merged)Newakhilaaa3/jev-omni— ctx— in · — outopen-weight— ctx · —/— per M
- JevK5 v0.2.0Newallebee/jevk5-v02— ctx— in · — out— ctx · —/— per M
- JevK5 v0.3 (4B)Newalibiserikbay/jevk5— ctx— in · — out— ctx · —/— per M
- JevOneNewjuspay/jev-one— ctx— in · — outopen-weight— ctx · —/— per M
- JPT-35B-A3B (Qwen3.5-35B-A3B fine-tune)Newkirp/jpt-35b-a3b— ctx— in · — out— ctx · —/— per M
- jqv (Qwen3-32B zero-shot)Newhjmurmur/jqv— ctx— in · — outopen-weight— ctx · —/— per M
- jul fast (usejul/jul-decision-minicpm5-2b: MiniCPM5-2B fine-tune with a pointer head, option probabilities from one pass, self-hosted via `jul serve`)Newusejul/jul-decision-minicpm5-2b— ctx— in · — out— ctx · —/— per M
- Kahn1 4B (Okura66, Qwen3.5-4B LoRA merge, author's sysone engine)Newokura66/kahn1-qwen3.5-4b— ctx— in · — out— ctx · —/— per M
- kev 0.5BNewjared-palmer/kev-0.5b— ctx— in · — out— ctx · —/— per M
- kev 0.6B (research preview)Newjared-palmer/kev-0.6b— ctx— in · — out— ctx · —/— per M
- Kev 27B (Kev 1.0, Qwen3.8-27B)Newjaredpalmer/kev-27b— ctx— in · — out— ctx · —/— per M
- kev 4B (research preview)Newjared-palmer/kev-4b— ctx— in · — out— ctx · —/— per M
- kev 8B (research preview)Newjared-palmer/kev-8b— ctx— in · — out— ctx · —/— per M
- Laya (Convai Innovations, ModernBERT-large 421M)Newconvaiinnovations/laya— ctx— in · — outopen-weight— ctx · —/— per M
- Laya multilingualNewconvaiinnovations/laya-multilingual— ctx— in · — outopen-weight— ctx · —/— per M
- Laya typed-decisionsNewconvaiinnovations/laya-typed-decisions— ctx— in · — outopen-weight— ctx · —/— per M
- lev (Interfaze AI, Qwen3.5-4B + LoRA r32, label-token readout + candidate-path head, per-bucket temperatures)Newinterfaze-ai/lev— ctx— in · — out— ctx · —/— per M
- lev-350m (Franck Verrot, LFM2.5-350M)Newfranck-verrot/lev-350m— ctx— in · — outopen-weight— ctx · —/— per M
- LiquidAI: LFM2.5-24B-A2BNewawaiting resultsliquid/lfm-2.5-24b-a2b-20261012128K ctx$0.050 in · $0.70 outtoolsrsn128K ctx · $0.050/$0.70 per M · tools
- LitJev (Qwen3.8-27B)Newzhengxu-yu/litjev— ctx— in · — outopen-weight— ctx · —/— per M
- local-jev Qwen3.5-4BNewamith-chandrappa/localjev-qwen3.5-4b— ctx— in · — outopen-weight— ctx · —/— per M
- Magnum v4 72Banthracite-org/magnum-v4-72b33K ctx$2.50 in · $5 outopen-weight33K ctx · $2.50/$5 per M
- Malkuth-2B (newfull5, Kev post-train)Newnewfull5/malkuth-2b— ctx— in · — outopen-weight— ctx · —/— per M
- Malkuth-4B (newfull5, Kev post-train)Newnewfull5/malkuth-4b— ctx— in · — outopen-weight— ctx · —/— per M
- Mancer: Weaver (alpha)mancer/weaver8K ctx$0.40 in · $0.75 out8K ctx · $0.40/$0.75 per M
- Manchego v2.1Neworaculumai/manchego-v21-v15— ctx— in · — outopen-weight— ctx · —/— per M
- Meituan: LongCat 2.0meituan/longcat-2.0-202607201.0M ctx$0.30 in · $1.20 outtoolsrsnopen-weight1.0M ctx · $0.30/$1.20 per M · tools
- Messier One v0.2 (Qwen3.5-4B fine-tune, one prefill, self-hosted)Newagentmessier/messier-one— ctx— in · — out— ctx · —/— per M
- Meta: Llama 3.1 70B Instructmeta-llama/llama-3.1-70b-instruct131K ctx$0.40 in · $0.40 outtoolsopen-weight131K ctx · $0.40/$0.40 per M · tools
- Meta: Llama 3.1 8B Instructmeta-llama/llama-3.1-8b-instruct131K ctx$0.050 in · $0.080 outtoolsopen-weight131K ctx · $0.050/$0.080 per M · tools
- Meta: Llama 3.2 1B Instructmeta-llama/llama-3.2-1b-instruct60K ctx$0.027 in · $0.20 outopen-weight60K ctx · $0.027/$0.20 per M
- Meta: Llama 3.2 3B Instructmeta-llama/llama-3.2-3b-instruct131K ctx$0.051 in · $0.34 outopen-weight131K ctx · $0.051/$0.34 per M
- Meta: Llama 3.3 70B Instructmeta-llama/llama-3.3-70b-instruct131K ctx$0.100 in · $0.32 outtoolsopen-weight131K ctx · $0.100/$0.32 per M · tools
- Meta: Llama 4 Maverickmeta-llama/llama-4-maverick-17b-128e-instruct524K ctx$0.19 in · $0.65 outtoolsvis524K ctx · $0.19/$0.65 per M · tools · vis
- Meta: Llama 4 Scoutmeta-llama/llama-4-scout-17b-16e-instruct1.3M ctx$0.100 in · $0.30 outtoolsvis1.3M ctx · $0.100/$0.30 per M · tools · vis
- Meta: Llama Guard 4 12Bmeta-llama/llama-guard-4-12b164K ctx$0.18 in · $0.18 outvisopen-weight164K ctx · $0.18/$0.18 per M · vis
- Meta: Muse Glimmer 30Bmeta/muse-glimmer-30b-20260810131K ctx$0.30 in · $1.20 outtoolsvisrsnopen-weight131K ctx · $0.30/$1.20 per M · tools · vis
- Meta: Muse Spark 1.1meta/muse-spark-1.1-202607091.0M ctx$1.25 in · $4.25 outtoolsvisrsn1.0M ctx · $1.25/$4.25 per M · tools · vis
- Meta: Muse Spark 1.2meta/muse-spark-1.2-202608051.0M ctx$1.25 in · $4.25 outtoolsvisrsn1.0M ctx · $1.25/$4.25 per M · tools · vis
- Meta: Muse Spark 1.2 Contributormeta/muse-spark-1.2-contributor-202608051.0M ctx$0.100 in · $0.20 outtoolsvisrsn1.0M ctx · $0.100/$0.20 per M · tools · vis
- Meta: Muse Spark 1.3meta/muse-spark-1.3-202609021.0M ctx$1.25 in · $4.25 outtoolsvisrsn1.0M ctx · $1.25/$4.25 per M · tools · vis
- Meta: Muse Spark 1.3 Contributormeta/muse-spark-1.3-contributor-202609021.0M ctx$0.100 in · $0.20 outtoolsvisrsn1.0M ctx · $0.100/$0.20 per M · tools · vis
- Meta: Muse Spark OpenNewmeta/muse-spark-open-202610151.0M ctx$1.25 in · $4.25 outtoolsvisrsnopen-weight1.0M ctx · $1.25/$4.25 per M · tools · vis
- Meta: Muse WonderNewmeta/muse-wonder-202610121.0M ctx$4 in · $20 outtoolsvisrsn1.0M ctx · $4/$20 per M · tools · vis
- metask-jev-4bNewwayfind/metask-jev-4b— ctx— in · — outopen-weight— ctx · —/— per M
- Microsoft: Phi 4microsoft/phi-416K ctx$0.070 in · $0.14 outopen-weight16K ctx · $0.070/$0.14 per M
- MiniMax: MiniMax M1minimax/minimax-m11M ctx$0.55 in · $2.20 outtoolsrsnopen-weight1M ctx · $0.55/$2.20 per M · tools
- MiniMax: MiniMax M2minimax/minimax-m2205K ctx$0.26 in · $1.02 outtoolsrsn205K ctx · $0.26/$1.02 per M · tools
- MiniMax: MiniMax M2-herminimax/minimax-m2-her-2026012366K ctx$0.30 in · $1.20 out66K ctx · $0.30/$1.20 per M
- MiniMax: MiniMax M2.1minimax/minimax-m2.1205K ctx$0.30 in · $1.20 outtoolsrsn205K ctx · $0.30/$1.20 per M · tools
- MiniMax: MiniMax M2.5minimax/minimax-m2.5-20260211205K ctx$0.27 in · $0.95 outtoolsrsn205K ctx · $0.27/$0.95 per M · tools
- MiniMax: MiniMax M2.7minimax/minimax-m2.7-20260318205K ctx$0.30 in · $1.20 outtoolsrsnopen-weight205K ctx · $0.30/$1.20 per M · tools
- MiniMax: MiniMax M3minimax/minimax-m3-202605311.0M ctx$0.30 in · $1.20 outtoolsvisrsnopen-weight1.0M ctx · $0.30/$1.20 per M · tools · vis
- MiniMax: MiniMax-01minimax/minimax-011.0M ctx$0.20 in · $1.10 outvis1.0M ctx · $0.20/$1.10 per M · vis
- MirrorNewbluusun/mirror— ctx— in · — outopen-weight— ctx · —/— per M
- Mistral Largemistralai/mistral-large128K ctx$2 in · $6 outtools128K ctx · $2/$6 per M · tools
- Mistral Large 2407mistralai/mistral-large-2407131K ctx$2 in · $6 outtools131K ctx · $2/$6 per M · tools
- Mistral: Codestral 2508mistralai/codestral-2508256K ctx$0.30 in · $0.90 outtools256K ctx · $0.30/$0.90 per M · tools
- Mistral: Devstral 2 2512mistralai/devstral-2512262K ctx$0.40 in · $2 outtoolsopen-weight262K ctx · $0.40/$2 per M · tools
- Mistral: Ministral 3 14B 2512mistralai/ministral-14b-2512262K ctx$0.20 in · $0.20 outtoolsvisopen-weight262K ctx · $0.20/$0.20 per M · tools · vis
- Mistral: Ministral 3 3B 2512mistralai/ministral-3b-2512131K ctx$0.100 in · $0.100 outtoolsvisopen-weight131K ctx · $0.100/$0.100 per M · tools · vis
- Mistral: Ministral 3 8B 2512mistralai/ministral-8b-2512262K ctx$0.15 in · $0.15 outtoolsvisopen-weight262K ctx · $0.15/$0.15 per M · tools · vis
- Mistral: Mistral Large 3 2512mistralai/mistral-large-2512262K ctx$0.50 in · $1.50 outtoolsvisopen-weight262K ctx · $0.50/$1.50 per M · tools · vis
- Mistral: Mistral Large 4Newmistralai/mistral-large-4-0-202610061.0M ctx$0.68 in · $2.09 outtoolsvisrsn1.0M ctx · $0.68/$2.09 per M · tools · vis
- Mistral: Mistral Medium 3mistralai/mistral-medium-3131K ctx$0.40 in · $2 outtoolsvis131K ctx · $0.40/$2 per M · tools · vis
- Mistral: Mistral Medium 3.1mistralai/mistral-medium-3.1131K ctx$0.40 in · $2 outtoolsvis131K ctx · $0.40/$2 per M · tools · vis
- Mistral: Mistral Medium 3.5mistralai/mistral-medium-3.5-20260430262K ctx$1.50 in · $7.50 outtoolsvisrsnopen-weight262K ctx · $1.50/$7.50 per M · tools · vis
- Mistral: Mistral Nemomistralai/mistral-nemo131K ctx$0.029 in · $0.030 outtoolsopen-weight131K ctx · $0.029/$0.030 per M · tools
- Mistral: Mistral Small 3mistralai/mistral-small-24b-instruct-250133K ctx$0.050 in · $0.080 outopen-weight33K ctx · $0.050/$0.080 per M
- Mistral: Mistral Small 3.1 24Bmistralai/mistral-small-3.1-24b-instruct-2503128K ctx$0.35 in · $0.55 outtoolsvisopen-weight128K ctx · $0.35/$0.55 per M · tools · vis
- Mistral: Mistral Small 3.2 24Bmistralai/mistral-small-3.2-24b-instruct-2506256K ctx$0.094 in · $0.25 outtoolsvisopen-weight256K ctx · $0.094/$0.25 per M · tools · vis
- Mistral: Mistral Small 4mistralai/mistral-small-2603262K ctx$0.15 in · $0.60 outtoolsvisrsnopen-weight262K ctx · $0.15/$0.60 per M · tools · vis
- Mistral: Mixtral 8x22B Instructmistralai/mixtral-8x22b-instruct66K ctx$2 in · $6 outtoolsopen-weight66K ctx · $2/$6 per M · tools
- Mistral: Sabamistralai/mistral-saba-250233K ctx$0.20 in · $0.60 outtools33K ctx · $0.20/$0.60 per M · tools
- Mistral: Voxtral Small 24B 2507mistralai/voxtral-small-24b-250733K ctx$0.100 in · $0.30 outtoolsopen-weight33K ctx · $0.100/$0.30 per M · tools
- Moondream: Moondream 3 PreviewNewawaiting resultsmoondream/moondream3-preview-2026101332K ctx$0.30 in · $2.50 outvisrsn32K ctx · $0.30/$2.50 per M · vis
- Moondream: Moondream 3.1Newawaiting resultsmoondream/moondream3.1-9b-a2b-2026101332K ctx$0.30 in · $2.50 outvisrsn32K ctx · $0.30/$2.50 per M · vis
- MoonshotAI: Kimi K2 0711moonshotai/kimi-k2131K ctx$0.57 in · $2.30 outtoolsopen-weight131K ctx · $0.57/$2.30 per M · tools
- MoonshotAI: Kimi K2 0905moonshotai/kimi-k2-0905262K ctx$0.60 in · $2.50 outtools262K ctx · $0.60/$2.50 per M · tools
- MoonshotAI: Kimi K2 Thinkingmoonshotai/kimi-k2-thinking-20251106262K ctx$0.60 in · $2.50 outtoolsrsn262K ctx · $0.60/$2.50 per M · tools
- MoonshotAI: Kimi K2.5moonshotai/kimi-k2.5-0127262K ctx$0.50 in · $2.50 outtoolsvisrsn262K ctx · $0.50/$2.50 per M · tools · vis
- MoonshotAI: Kimi K2.6moonshotai/kimi-k2.6-20260420262K ctx$0.65 in · $3.41 outtoolsvisrsn262K ctx · $0.65/$3.41 per M · tools · vis
- MoonshotAI: Kimi K2.7 Codemoonshotai/kimi-k2.7-code-20260612262K ctx$0.67 in · $3.35 outtoolsvisrsnopen-weight262K ctx · $0.67/$3.35 per M · tools · vis
- MoonshotAI: Kimi K3moonshotai/kimi-k3-202607151.0M ctx$0.24 in · $11.94 outtoolsvisrsnopen-weight1.0M ctx · $0.24/$11.94 per M · tools · vis
- Morph: Morph V3 Fastmorph/morph-v3-fast262K ctx$0.80 in · $1.20 out262K ctx · $0.80/$1.20 per M
- Morph: Morph V3 Largemorph/morph-v3-large262K ctx$0.90 in · $1.90 out262K ctx · $0.90/$1.90 per M
- MythoMax 13Bgryphe/mythomax-l2-13b8K ctx$0.080 in · $0.11 outopen-weight8K ctx · $0.080/$0.11 per M
- Nemotron Diffusion 8B (pst2154, optimized vLLM)Newpst2154/nemotron-diffusion-8b— ctx— in · — outopen-weight— ctx · —/— per M
- Nex AGI: Nex-N2.5-Mininex-agi/nex-n2.5-mini-20260908262K ctx$0.025 in · $0.100 outvisrsn262K ctx · $0.025/$0.100 per M · vis
- Nex AGI: Nex-N2.5-Pronex-agi/nex-n2.5-pro-20260907262K ctx$0.075 in · $0.25 outtoolsvisrsn262K ctx · $0.075/$0.25 per M · tools · vis
- NInfer Qwen3.8-27B NVFP4Newigor-l.-ninfer-contributors/ninfer-qwen3.8-27b— ctx— in · — outopen-weight— ctx · —/— per M
- NInfer Qwen3.8-Flash-Next mixedNewigor-l.-ninfer-contributors/ninfer-qwen3.8-flash-next— ctx— in · — outopen-weight— ctx · —/— per M
- Nous: Hermes 3 405B Instructnousresearch/hermes-3-llama-3.1-405b131K ctx$1 in · $1 outopen-weight131K ctx · $1/$1 per M
- Nous: Hermes 3 70B Instructnousresearch/hermes-3-llama-3.1-70b131K ctx$0.70 in · $0.70 outopen-weight131K ctx · $0.70/$0.70 per M
- Nous: Hermes 4 405Bnousresearch/hermes-4-405b131K ctx$1 in · $3 outrsnopen-weight131K ctx · $1/$3 per M
- NVIDIA: Nemotron 3 Nano 30B A3Bnvidia/nemotron-3-nano-30b-a3b262K ctx$0.060 in · $0.24 outtoolsrsnopen-weight262K ctx · $0.060/$0.24 per M · tools
- NVIDIA: Nemotron 3 Supernvidia/nemotron-3-super-120b-a12b-20230311262K ctx$0.080 in · $0.45 outtoolsrsnopen-weight262K ctx · $0.080/$0.45 per M · tools
- NVIDIA: Nemotron 3 Ultranvidia/nemotron-3-ultra-550b-a55b-20260604262K ctx$0.60 in · $2.40 outtoolsrsnopen-weight262K ctx · $0.60/$2.40 per M · tools
- NVIDIA: Nemotron 3.5 Content Safetynvidia/nemotron-3.5-content-safety-20260604131K ctx$0.20 in · $0.20 outvisrsnopen-weight131K ctx · $0.20/$0.20 per M · vis
- NVIDIA: Nemotron 3.5 Lightningnvidia/nemotron-3.5-lightning-20260807262K ctx$0.070 in · $0.20 outtoolsrsnopen-weight262K ctx · $0.070/$0.20 per M · tools
- NVIDIA: Nemotron 3.5 Super VLNewnvidia/nemotron-3.5-super-vl-202610151.0M ctx$0.15 in · $0.50 outtoolsvisrsnopen-weight1.0M ctx · $0.15/$0.50 per M · tools · vis
- NVIDIA: Switchyardnvidia/switchyard1M ctx$-1000000.000 in · $-1000000.000 out1M ctx · $-1000000.000/$-1000000.000 per M
- Open Jev JSON Canvas (JoshuaSP)Newjoshuasp/open-jev-json-canvas-joshuasp— ctx— in · — outopen-weight— ctx · —/— per M
- open-alternative-jev (Qwen3.5-4B, IkerMoel)Newikermoel/open-alternative-jev— ctx— in · — outopen-weight— ctx · —/— per M
- Open-Jev 27B v1.1 (Zefan Cai, LoRA + decision head on Qwen3.8-27B)Newzefancai/open-jev-27b-v1.1— ctx— in · — out— ctx · —/— per M
- Open-Jev 2B (Zefan Cai)Newzefan-cai/open-jev-zefan-2b— ctx— in · — outopen-weight— ctx · —/— per M
- Open-Jev 9B (Zefan Cai)Newzefan-cai/open-jev-zefan-9b— ctx— in · — outopen-weight— ctx · —/— per M
- open-jev-deberta-v3-large (local CPU)Newkotoba-labs/open-jev-deberta-v3-large— ctx— in · — outopen-weight— ctx · —/— per M
- OpenAI: GPT Audioopenai/gpt-audio128K ctx$2.50 in · $10 outtools128K ctx · $2.50/$10 per M · tools
- OpenAI: GPT Audio Miniopenai/gpt-audio-mini128K ctx$0.60 in · $2.40 outtools128K ctx · $0.60/$2.40 per M · tools
- OpenAI: GPT Chat Latestopenai/gpt-chat-latest-20260505400K ctx$5 in · $30 outtoolsvis400K ctx · $5/$30 per M · tools · vis
- OpenAI: GPT-3.5 Turboopenai/gpt-3.5-turbo16K ctx$0.50 in · $1.50 outtools16K ctx · $0.50/$1.50 per M · tools
- OpenAI: GPT-3.5 Turbo (older v0613)openai/gpt-3.5-turbo-06134K ctx$1 in · $2 outtools4K ctx · $1/$2 per M · tools
- OpenAI: GPT-3.5 Turbo 16kopenai/gpt-3.5-turbo-16k16K ctx$3 in · $4 outtools16K ctx · $3/$4 per M · tools
- OpenAI: GPT-3.5 Turbo Instructopenai/gpt-3.5-turbo-instruct4K ctx$1.50 in · $2 out4K ctx · $1.50/$2 per M
- OpenAI: GPT-4openai/gpt-48K ctx$30 in · $60 outtools8K ctx · $30/$60 per M · tools
- OpenAI: GPT-4 Turboopenai/gpt-4-turbo128K ctx$10 in · $30 outtoolsvis128K ctx · $10/$30 per M · tools · vis
- OpenAI: GPT-4.1openai/gpt-4.1-2025-04-141.0M ctx$2 in · $8 outtoolsvis1.0M ctx · $2/$8 per M · tools · vis
- OpenAI: GPT-4.1 Miniopenai/gpt-4.1-mini-2025-04-141.0M ctx$0.40 in · $1.60 outtoolsvis1.0M ctx · $0.40/$1.60 per M · tools · vis
- OpenAI: GPT-4.1 Nanoopenai/gpt-4.1-nano-2025-04-141.0M ctx$0.100 in · $0.40 outtoolsvis1.0M ctx · $0.100/$0.40 per M · tools · vis
- OpenAI: GPT-4oopenai/gpt-4o128K ctx$2.50 in · $10 outtoolsvis128K ctx · $2.50/$10 per M · tools · vis
- OpenAI: GPT-4o (2024-05-13)openai/gpt-4o-2024-05-13128K ctx$5 in · $15 outtoolsvis128K ctx · $5/$15 per M · tools · vis
- OpenAI: GPT-4o (2024-08-06)openai/gpt-4o-2024-08-06128K ctx$2.50 in · $10 outtoolsvis128K ctx · $2.50/$10 per M · tools · vis
- OpenAI: GPT-4o (2024-11-20)openai/gpt-4o-2024-11-20128K ctx$2.50 in · $10 outtoolsvis128K ctx · $2.50/$10 per M · tools · vis
- OpenAI: GPT-4o-miniopenai/gpt-4o-mini128K ctx$0.15 in · $0.60 outtoolsvis128K ctx · $0.15/$0.60 per M · tools · vis
- OpenAI: GPT-4o-mini (2024-07-18)openai/gpt-4o-mini-2024-07-18128K ctx$0.15 in · $0.60 outtoolsvis128K ctx · $0.15/$0.60 per M · tools · vis
- OpenAI: GPT-5 (Aug 2025)openai/gpt-5-2025-08-07400K ctx$1.25 in · $10 outtoolsvisrsn400K ctx · $1.25/$10 per M · tools · vis
- OpenAI: GPT-5 Imageopenai/gpt-5-image400K ctx$10 in · $10 outvisrsn400K ctx · $10/$10 per M · vis
- OpenAI: GPT-5 Image Miniopenai/gpt-5-image-mini400K ctx$2.50 in · $2 outvisrsn400K ctx · $2.50/$2 per M · vis
- OpenAI: GPT-5 Miniopenai/gpt-5-mini-2025-08-07400K ctx$0.25 in · $2 outtoolsvisrsn400K ctx · $0.25/$2 per M · tools · vis
- OpenAI: GPT-5 Nanoopenai/gpt-5-nano-2025-08-07400K ctx$0.050 in · $0.40 outtoolsvisrsn400K ctx · $0.050/$0.40 per M · tools · vis
- OpenAI: GPT-5 Proopenai/gpt-5-pro-2025-10-06400K ctx$15 in · $120 outtoolsvisrsn400K ctx · $15/$120 per M · tools · vis
- OpenAI: GPT-5.1openai/gpt-5.1-20251113400K ctx$1.25 in · $10 outtoolsvisrsn400K ctx · $1.25/$10 per M · tools · vis
- OpenAI: GPT-5.1-Codexopenai/gpt-5.1-codex-20251113400K ctx$1.25 in · $10 outtoolsvisrsn400K ctx · $1.25/$10 per M · tools · vis
- OpenAI: GPT-5.1-Codex-Maxopenai/gpt-5.1-codex-max-20251204400K ctx$1.25 in · $10 outtoolsvisrsn400K ctx · $1.25/$10 per M · tools · vis
- OpenAI: GPT-5.1-Codex-Miniopenai/gpt-5.1-codex-mini-20251113400K ctx$0.25 in · $2 outtoolsvisrsn400K ctx · $0.25/$2 per M · tools · vis
- OpenAI: GPT-5.2openai/gpt-5.2-20251211400K ctx$1.75 in · $14 outtoolsvisrsn400K ctx · $1.75/$14 per M · tools · vis
- OpenAI: GPT-5.2 Chatopenai/gpt-5.2-chat-20251211128K ctx$1.75 in · $14 outtoolsvis128K ctx · $1.75/$14 per M · tools · vis
- OpenAI: GPT-5.2 Proopenai/gpt-5.2-pro-20251211400K ctx$21 in · $168 outtoolsvisrsn400K ctx · $21/$168 per M · tools · vis
- OpenAI: GPT-5.2-Codexopenai/gpt-5.2-codex-20260114400K ctx$1.75 in · $14 outtoolsvisrsn400K ctx · $1.75/$14 per M · tools · vis
- OpenAI: GPT-5.3-Codexopenai/gpt-5.3-codex-20260224400K ctx$1.75 in · $14 outtoolsvisrsn400K ctx · $1.75/$14 per M · tools · vis
- OpenAI: GPT-5.4openai/gpt-5.4-202603051.1M ctx$2.50 in · $15 outtoolsvisrsn1.1M ctx · $2.50/$15 per M · tools · vis
- OpenAI: GPT-5.4 Image 2openai/gpt-5.4-image-2-20260421272K ctx$8 in · $15 outvisrsn272K ctx · $8/$15 per M · vis
- OpenAI: GPT-5.4 Miniopenai/gpt-5.4-mini-20260317400K ctx$0.75 in · $4.50 outtoolsvisrsn400K ctx · $0.75/$4.50 per M · tools · vis
- OpenAI: GPT-5.4 Nanoopenai/gpt-5.4-nano-20260317400K ctx$0.20 in · $1.25 outtoolsvisrsn400K ctx · $0.20/$1.25 per M · tools · vis
- OpenAI: GPT-5.4 Proopenai/gpt-5.4-pro-202603051.1M ctx$30 in · $180 outtoolsvisrsn1.1M ctx · $30/$180 per M · tools · vis
- OpenAI: GPT-5.5openai/gpt-5.5-202604231.1M ctx$5 in · $30 outtoolsvisrsn1.1M ctx · $5/$30 per M · tools · vis
- OpenAI: GPT-5.5 Proopenai/gpt-5.5-pro-202604231.1M ctx$30 in · $180 outtoolsvisrsn1.1M ctx · $30/$180 per M · tools · vis
- OpenAI: GPT-5.6 Lunaopenai/gpt-5.6-luna-202607091.1M ctx$0.20 in · $1.20 outtoolsvisrsn1.1M ctx · $0.20/$1.20 per M · tools · vis
- OpenAI: GPT-5.6 Luna Proopenai/gpt-5.6-luna-pro-202607091.1M ctx$0.20 in · $1.20 outtoolsvisrsn1.1M ctx · $0.20/$1.20 per M · tools · vis
- OpenAI: GPT-5.6 Solopenai/gpt-5.6-sol-202607091.1M ctx$4 in · $20 outtoolsvisrsn1.1M ctx · $4/$20 per M · tools · vis
- OpenAI: GPT-5.6 Sol Proopenai/gpt-5.6-sol-pro-202607091.1M ctx$4 in · $20 outtoolsvisrsn1.1M ctx · $4/$20 per M · tools · vis
- OpenAI: GPT-5.6 Terraopenai/gpt-5.6-terra-202607091.1M ctx$2 in · $12 outtoolsvisrsn1.1M ctx · $2/$12 per M · tools · vis
- OpenAI: GPT-5.6 Terra Proopenai/gpt-5.6-terra-pro-202607091.1M ctx$2 in · $12 outtoolsvisrsn1.1M ctx · $2/$12 per M · tools · vis
- OpenAI: GPT-6 Astraopenai/gpt-6-astra-202609031.1M ctx$10 in · $50 outtoolsvisrsn1.1M ctx · $10/$50 per M · tools · vis
- OpenAI: GPT-6 Astra Proopenai/gpt-6-astra-pro-202609031.1M ctx$10 in · $50 outtoolsvisrsn1.1M ctx · $10/$50 per M · tools · vis
- OpenAI: GPT-6 Lunaopenai/gpt-6-luna-202609221.1M ctx$0.100 in · $0.50 outtoolsvisrsn1.1M ctx · $0.100/$0.50 per M · tools · vis
- OpenAI: GPT-6 Luna Proopenai/gpt-6-luna-pro-202609221.1M ctx$0.100 in · $0.50 outtoolsvisrsn1.1M ctx · $0.100/$0.50 per M · tools · vis
- OpenAI: GPT-6 Solopenai/gpt-6-sol-202609221.1M ctx$2 in · $10 outtoolsvisrsn1.1M ctx · $2/$10 per M · tools · vis
- OpenAI: GPT-6 Sol Proopenai/gpt-6-sol-pro-202609221.1M ctx$2 in · $10 outtoolsvisrsn1.1M ctx · $2/$10 per M · tools · vis
- OpenAI: GPT-6.1 Solopenai/gpt-6.1-sol-202609291.1M ctx$2 in · $10 outtoolsvisrsn1.1M ctx · $2/$10 per M · tools · vis
- OpenAI: GPT-6.1 Sol Proopenai/gpt-6.1-sol-pro-202609291.1M ctx$2 in · $10 outtoolsvisrsn1.1M ctx · $2/$10 per M · tools · vis
- OpenAI: gpt-oss-120bopenai/gpt-oss-120b131K ctx$0.15 in · $0.60 outtoolsrsnopen-weight131K ctx · $0.15/$0.60 per M · tools
- OpenAI: gpt-oss-20bopenai/gpt-oss-20b131K ctx$0.018 in · $0.090 outtoolsrsnopen-weight131K ctx · $0.018/$0.090 per M · tools
- OpenAI: gpt-oss-safeguard-20bopenai/gpt-oss-safeguard-20b131K ctx$0.075 in · $0.30 outtoolsrsnopen-weight131K ctx · $0.075/$0.30 per M · tools
- OpenAI: o1openai/o1-2024-12-17200K ctx$15 in · $60 outtoolsvisrsn200K ctx · $15/$60 per M · tools · vis
- OpenAI: o1-proopenai/o1-pro200K ctx$150 in · $600 outvisrsn200K ctx · $150/$600 per M · vis
- OpenAI: o3openai/o3-2025-04-16200K ctx$2 in · $8 outtoolsvisrsn200K ctx · $2/$8 per M · tools · vis
- OpenAI: o3 Miniopenai/o3-mini-2025-01-31200K ctx$1.10 in · $4.40 outtoolsrsn200K ctx · $1.10/$4.40 per M · tools
- OpenAI: o3 Mini Highopenai/o3-mini-high-2025-01-31200K ctx$1.10 in · $4.40 outtoolsrsn200K ctx · $1.10/$4.40 per M · tools
- OpenAI: o3 Proopenai/o3-pro-2025-06-10200K ctx$20 in · $80 outtoolsvisrsn200K ctx · $20/$80 per M · tools · vis
- OpenAI: o4 Miniopenai/o4-mini-2025-04-16200K ctx$1.10 in · $4.40 outtoolsvisrsn200K ctx · $1.10/$4.40 per M · tools · vis
- OpenAI: o4 Mini Highopenai/o4-mini-high-2025-04-16200K ctx$1.10 in · $4.40 outtoolsvisrsn200K ctx · $1.10/$4.40 per M · tools · vis
- OpenJev (thinking, BF16)Newrazorback16/openjev-thinking— ctx— in · — outopen-weight— ctx · —/— per M
- openJev Verdict (heman10x, ModernBERT-base 151M)Newhemant/openjev-verdict— ctx— in · — outopen-weight— ctx · —/— per M
- openJev Verdict 1.4Newheman10x/rlcd-modernbert-151m— ctx— in · — outopen-weight— ctx · —/— per M
- OpenSourceJev (Qwen3.5-4B Q4_K_M, native llama.cpp)Newsabeel111/opensourcejev-qwen35-4b-q4km— ctx— in · — out— ctx · —/— per M
- Paretounbiased/pareto-20260917262K ctx$2.50 in · $7.50 outtoolsvis262K ctx · $2.50/$7.50 per M · tools · vis
- Pareto 26.10Newawaiting resultsunbiased/pareto-26.10-202610151.0M ctx$0.80 in · $3.20 outtoolsvis1.0M ctx · $0.80/$3.20 per M · tools · vis
- Pareto 26.10 PreviewNewawaiting resultsunbiased/pareto-26.10-preview-202609291.0M ctx$0.80 in · $3.20 outtoolsvis1.0M ctx · $0.80/$3.20 per M · tools · vis
- Pareto 26.9unbiased/pareto-26.9-20260917262K ctx$2.50 in · $7.50 outtoolsvis262K ctx · $2.50/$7.50 per M · tools · vis
- Perceptron: Perceptron Mk1perceptron/perceptron-mk1-2026051233K ctx$0.15 in · $1.50 outvisrsn33K ctx · $0.15/$1.50 per M · vis
- Perceptron: Perceptron Mk1.5perceptron/perceptron-mk1.5-2026092537K ctx$0.15 in · $1.50 outtoolsvisrsn37K ctx · $0.15/$1.50 per M · tools · vis
- Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout)Newperplexity-ai/pplx-decider-v1.1-27b— ctx— in · — out— ctx · —/— per M
- Perplexity: Sonarperplexity/sonar127K ctx$1 in · $1 outvis127K ctx · $1/$1 per M · vis
- Perplexity: Sonar Deep Researchperplexity/sonar-deep-research128K ctx$2 in · $8 outrsn128K ctx · $2/$8 per M
- Perplexity: Sonar Properplexity/sonar-pro200K ctx$3 in · $15 outvis200K ctx · $3/$15 per M · vis
- Perplexity: Sonar Pro Searchperplexity/sonar-pro-search200K ctx$3 in · $15 outvisrsn200K ctx · $3/$15 per M · vis
- Perplexity: Sonar Reasoning Properplexity/sonar-reasoning-pro128K ctx$2 in · $8 outvisrsn128K ctx · $2/$8 per M · vis
- Plumb-4B (crh225, JevK5 v0.2 + LoRA)Newcrh225/plumb-4b— ctx— in · — out— ctx · —/— per M
- Poolside: Laguna S 2.1poolside/laguna-s-2.1-202607201.0M ctx$0.090 in · $0.18 outtoolsrsnopen-weight1.0M ctx · $0.090/$0.18 per M · tools
- Poolside: Laguna XS 2.1poolside/laguna-xs-2.1-20260625262K ctx$0.060 in · $0.12 outtoolsrsnopen-weight262K ctx · $0.060/$0.12 per M · tools
- PrismML: Ternary Bonsai 2 27Bprism-ml/ternary-bonsai-2-27b-20260918262K ctx$0.075 in · $0.50 outtoolsvisrsn262K ctx · $0.075/$0.50 per M · tools · vis
- Quyet-1.0-Large (Chinh Nguyen, Gemma-4-31B decoder, option-letter logits)Newchinhnc/quyet-1.0-large— ctx— in · — out— ctx · —/— per M
- Quyet-1.0-Medium (Chinh Nguyen, Qwen3.5-4B decoder, option-letter logits)Newchinhnc/quyet-1.0-medium— ctx— in · — out— ctx · —/— per M
- Quyet-1.0-Small (Chinh Nguyen, SEA-LION-ModernBERT-300M encoder with fixed heads)Newchinhnc/quyet-1.0-small— ctx— in · — out— ctx · —/— per M
- Quyet-1.0-Small-EN (Chinh Nguyen, ModernBERT-base encoder with fixed heads)Newchinhnc/quyet-1.0-small-en— ctx— in · — out— ctx · —/— per M
- Quyet-1.0-Tiny (Chinh Nguyen, mmBERT-small encoder (16 layers kept) with fixed heads)Newchinhnc/quyet-1.0-tiny— ctx— in · — out— ctx · —/— per M
- Qwen: Qwen-Plusqwen/qwen-plus-2025-01-251M ctx$0.26 in · $0.78 outtools1M ctx · $0.26/$0.78 per M · tools
- Qwen: Qwen2.5 7B Instructqwen/qwen-2.5-7b-instruct33K ctx$0.100 in · $0.20 outtoolsopen-weight33K ctx · $0.100/$0.20 per M · tools
- Qwen: Qwen2.5 VL 72B Instructqwen/qwen2.5-vl-72b-instruct128K ctx$0.80 in · $1 outvisopen-weight128K ctx · $0.80/$1 per M · vis
- Qwen: Qwen3 14Bqwen/qwen3-14b-04-2841K ctx$0.12 in · $0.24 outtoolsrsnopen-weight41K ctx · $0.12/$0.24 per M · tools
- Qwen: Qwen3 235B A22B Instruct 2507qwen/qwen3-235b-a22b-07-25262K ctx$0.090 in · $0.55 outtoolsopen-weight262K ctx · $0.090/$0.55 per M · tools
- Qwen: Qwen3 235B A22B Thinking 2507qwen/qwen3-235b-a22b-thinking-2507128K ctx$0.45 in · $3.50 outtoolsrsnopen-weight128K ctx · $0.45/$3.50 per M · tools
- Qwen: Qwen3 30B A3Bqwen/qwen3-30b-a3b-04-2841K ctx$0.12 in · $0.50 outtoolsrsnopen-weight41K ctx · $0.12/$0.50 per M · tools
- Qwen: Qwen3 30B A3B Instruct 2507qwen/qwen3-30b-a3b-instruct-2507262K ctx$0.090 in · $0.30 outtoolsopen-weight262K ctx · $0.090/$0.30 per M · tools
- Qwen: Qwen3 32Bqwen/qwen3-32b-04-28131K ctx$0.080 in · $0.28 outtoolsrsnopen-weight131K ctx · $0.080/$0.28 per M · tools
- Qwen: Qwen3 Coder 30B A3B Instructqwen/qwen3-coder-30b-a3b-instruct262K ctx$0.070 in · $0.28 outtoolsopen-weight262K ctx · $0.070/$0.28 per M · tools
- Qwen: Qwen3 Coder 480B A35Bqwen/qwen3-coder-480b-a35b-07-25262K ctx$0.30 in · $1 outtoolsopen-weight262K ctx · $0.30/$1 per M · tools
- Qwen: Qwen3 Coder Flashqwen/qwen3-coder-flash1M ctx$0.20 in · $0.97 outtools1M ctx · $0.20/$0.97 per M · tools
- Qwen: Qwen3 Coder Nextqwen/qwen3-coder-next-2025-02-03262K ctx$0.12 in · $0.80 outtools262K ctx · $0.12/$0.80 per M · tools
- Qwen: Qwen3 Next 80B A3B Instructqwen/qwen3-next-80b-a3b-instruct-2509262K ctx$0.090 in · $1.10 outtools262K ctx · $0.090/$1.10 per M · tools
- Qwen: Qwen3 Next 80B A3B Thinkingqwen/qwen3-next-80b-a3b-thinking-2509262K ctx$0.15 in · $1.20 outtoolsrsnopen-weight262K ctx · $0.15/$1.20 per M · tools
- Qwen: Qwen3 VL 235B A22B Instructqwen/qwen3-vl-235b-a22b-instruct262K ctx$0.21 in · $1.90 outtoolsvisopen-weight262K ctx · $0.21/$1.90 per M · tools · vis
- Qwen: Qwen3 VL 30B A3B Instructqwen/qwen3-vl-30b-a3b-instruct262K ctx$0.15 in · $0.60 outtoolsvisopen-weight262K ctx · $0.15/$0.60 per M · tools · vis
- Qwen: Qwen3 VL 30B A3B Thinkingqwen/qwen3-vl-30b-a3b-thinking262K ctx$0.29 in · $1 outtoolsvisrsn262K ctx · $0.29/$1 per M · tools · vis
- Qwen: Qwen3 VL 8B Instructqwen/qwen3-vl-8b-instruct262K ctx$0.25 in · $0.75 outtoolsvis262K ctx · $0.25/$0.75 per M · tools · vis
- Qwen: Qwen3.5 397B A17Bqwen/qwen3.5-397b-a17b-20260216262K ctx$0.39 in · $2.34 outtoolsvisrsnopen-weight262K ctx · $0.39/$2.34 per M · tools · vis
- Qwen: Qwen3.5 Plus 2026-02-15qwen/qwen3.5-plus-202602161M ctx$0.26 in · $1.56 outtoolsvisrsn1M ctx · $0.26/$1.56 per M · tools · vis
- Qwen: Qwen3.5 Plus 2026-04-20qwen/qwen3.5-plus-202604201M ctx$0.30 in · $1.80 outtoolsvisrsn1M ctx · $0.30/$1.80 per M · tools · vis
- Qwen: Qwen3.5-122B-A10Bqwen/qwen3.5-122b-a10b-20260224262K ctx$0.26 in · $2.08 outtoolsvisrsnopen-weight262K ctx · $0.26/$2.08 per M · tools · vis
- Qwen: Qwen3.5-27Bqwen/qwen3.5-27b-20260224262K ctx$0.27 in · $2.16 outtoolsvisrsnopen-weight262K ctx · $0.27/$2.16 per M · tools · vis
- Qwen: Qwen3.5-35B-A3Bqwen/qwen3.5-35b-a3b-20260224262K ctx$0.15 in · $1 outtoolsvisrsnopen-weight262K ctx · $0.15/$1 per M · tools · vis
- Qwen: Qwen3.5-9Bqwen/qwen3.5-9b-20260310262K ctx$0.100 in · $0.15 outtoolsvisrsnopen-weight262K ctx · $0.100/$0.15 per M · tools · vis
- Qwen: Qwen3.5-Flashqwen/qwen3.5-flash-202602241M ctx$0.065 in · $0.26 outtoolsvisrsn1M ctx · $0.065/$0.26 per M · tools · vis
- Qwen: Qwen3.6 27Bqwen/qwen3.6-27b-20260422262K ctx$0.25 in · $2 outtoolsvisrsnopen-weight262K ctx · $0.25/$2 per M · tools · vis
- Qwen: Qwen3.6 35B A3Bqwen/qwen3.6-35b-a3b-20260415262K ctx$0.100 in · $0.95 outtoolsvisrsnopen-weight262K ctx · $0.100/$0.95 per M · tools · vis
- Qwen: Qwen3.6 Flashqwen/qwen3.6-flash1M ctx$0.19 in · $1.13 outtoolsvisrsn1M ctx · $0.19/$1.13 per M · tools · vis
- Qwen: Qwen3.6 Plusqwen/qwen3.6-plus-04-021M ctx$0.33 in · $1.95 outtoolsvisrsn1M ctx · $0.33/$1.95 per M · tools · vis
- Qwen: Qwen3.7 Flashqwen/qwen3.7-flash-202607271M ctx$0.030 in · $0.13 outtoolsvisrsn1M ctx · $0.030/$0.13 per M · tools · vis
- Qwen: Qwen3.7 Maxqwen/qwen3.7-max-202605201M ctx$1.48 in · $4.42 outtoolsrsn1M ctx · $1.48/$4.42 per M · tools
- Qwen: Qwen3.7 Plusqwen/qwen3.7-plus-202606021M ctx$0.32 in · $1.28 outtoolsvisrsn1M ctx · $0.32/$1.28 per M · tools · vis
- Qwen: Qwen3.8 2.4T A95Bqwen/qwen3.8-2.4t-a95b-202608121.0M ctx$2 in · $6 outtoolsrsnopen-weight1.0M ctx · $2/$6 per M · tools
- Qwen: Qwen3.8 27Bqwen/qwen3.8-27b-202608141M ctx$0.040 in · $1.35 outtoolsvisrsnopen-weight1M ctx · $0.040/$1.35 per M · tools · vis
- Qwen: Qwen3.8 Flashqwen/qwen3.8-flash-202608261M ctx$0.15 in · $0.47 outtoolsvisrsn1M ctx · $0.15/$0.47 per M · tools · vis
- Qwen: Qwen3.8 Max (0902)qwen/qwen3.8-max-202609021M ctx$2 in · $6 outtoolsvisrsn1M ctx · $2/$6 per M · tools · vis
- Qwen: Qwen3.8 Max Primeqwen/qwen3.8-max-prime-202609231M ctx$4 in · $12 outtoolsvisrsn1M ctx · $4/$12 per M · tools · vis
- Qwen: Qwen3.8 Omni Flashqwen/qwen3.8-omni-flash-202609181M ctx$0.15 in · $0.47 outtoolsvisrsn1M ctx · $0.15/$0.47 per M · tools · vis
- Qwen2.5 72B Instructqwen/qwen-2.5-72b-instruct33K ctx$0.36 in · $0.40 outtoolsopen-weight33K ctx · $0.36/$0.40 per M · tools
- Qwen2.5 Coder 32B Instructqwen/qwen-2.5-coder-32b-instruct33K ctx$0.66 in · $1 outopen-weight33K ctx · $0.66/$1 per M
- Qwen3.5-0.8B Decision Model (Mourad Ghafiri)Newmghafiri/qwen3.5-0.8b-decision-model— ctx— in · — outopen-weight— ctx · —/— per M
- Qwen3.5-9B Jev-like data-mix v2Newjsaurabh/qwen3.5-9b-jev-data-mix-v2— ctx— in · — out— ctx · —/— per M
- Reflection: Beam 1.0 501B A23BNewreflection/beam-1.0-501b-a23b-202610161.0M ctx$0.30 in · $1 outtoolsrsnopen-weight1.0M ctx · $0.30/$1 per M · tools
- reflex 4B (kshetrajna12)Newkshetrajna12/reflex-4b— ctx— in · — outopen-weight— ctx · —/— per M
- Reka Edgerekaai/reka-edge-260316K ctx$0.100 in · $0.100 outtoolsvisopen-weight16K ctx · $0.100/$0.100 per M · tools · vis
- Reka Flash 3rekaai/reka-flash-366K ctx$0.100 in · $0.20 outrsnopen-weight66K ctx · $0.100/$0.20 per M
- Relace: Relace Apply 3relace/relace-apply-3256K ctx$0.85 in · $1.25 out256K ctx · $0.85/$1.25 per M
- Relace: Relace Searchrelace/relace-search-20251208256K ctx$1 in · $3 outtools256K ctx · $1/$3 per M · tools
- ReMM SLERP 13Bundi95/remm-slerp-l2-13b6K ctx$0.35 in · $0.65 outopen-weight6K ctx · $0.35/$0.65 per M
- René-1 31B FP8 (salfatigroup, Gemma 4 31B full fine-tune, one-pass option readout)Newsalfatigroup/rene-1-31b-fp8— ctx— in · — out— ctx · —/— per M
- Sage 1.3.0 (Levanto Labs)Newlevanto-labs/sage-1.3.0— ctx— in · — out— ctx · —/— per M
- Sakana: Fugu Maxsakana/fugu-max-202609111M ctx$2 in · $6 outtoolsvisrsn1M ctx · $2/$6 per M · tools · vis
- Sakana: Fugu Ultrasakana/fugu-ultra-202606151M ctx$5 in · $30 outtoolsvisrsn1M ctx · $5/$30 per M · tools · vis
- Sakana: Fugu Ultra v2sakana/fugu-ultra-v2-202609111M ctx$5 in · $30 outtoolsvisrsn1M ctx · $5/$30 per M · tools · vis
- Sakana: Sakana Namazusakana/namazu-20260811262K ctx$0.95 in · $4 outtoolsvisrsn262K ctx · $0.95/$4 per M · tools · vis
- Sao10K: Llama 3 8B Lunarissao10k/l3-lunaris-8b8K ctx$0.040 in · $0.050 outopen-weight8K ctx · $0.040/$0.050 per M
- Sao10K: Llama 3.1 Euryale 70B v2.2sao10k/l3.1-euryale-70b131K ctx$0.85 in · $0.85 outopen-weight131K ctx · $0.85/$0.85 per M
- Sao10K: Llama 3.3 Euryale 70Bsao10k/l3.3-euryale-70b-v2.3131K ctx$0.65 in · $0.75 out131K ctx · $0.65/$0.75 per M
- ScaleDown: ExtractNewawaiting resultsscaledown/extract-202609281M ctx$0.040 in · $0 outvis1M ctx · $0.040/$0 per M · vis
- ScaleDown: SummarizeNewawaiting resultsscaledown/summarize-202609281M ctx$0.040 in · $0 outvis1M ctx · $0.040/$0 per M · vis
- SemIf, formerly OpenJev (Qwen3.5-4B, TheoLeeCJ)Newtheodore-lee/semif-qwen3.5-4b— ctx— in · — outopen-weight— ctx · —/— per M
- SimpleJev (Qwen3.5-0.8B, CPU)Newsabeel111-featherless-ai/simplejev-qwen3.5-0.8b— ctx— in · — outopen-weight— ctx · —/— per M
- SimpleJev Qwen3.8-27B (self-hosted, v1.6 pool)Newfeatherless/simplejev-qwen3.8-27b-selfhost— ctx— in · — out— ctx · —/— per M
- smalljev semantic-v9Newaditya/smalljev— ctx— in · — outopen-weight— ctx · —/— per M
- SpaceXAI: Grok 4.20x-ai/grok-4.20-202603092M ctx$1.25 in · $2.50 outtoolsvisrsn2M ctx · $1.25/$2.50 per M · tools · vis
- SpaceXAI: Grok 4.20 Multi-Agentx-ai/grok-4.20-multi-agent-202603092M ctx$1.25 in · $2.50 outvisrsn2M ctx · $1.25/$2.50 per M · vis
- SpaceXAI: Grok 4.3x-ai/grok-4.3-202604301M ctx$1.25 in · $2.50 outtoolsvisrsn1M ctx · $1.25/$2.50 per M · tools · vis
- SpaceXAI: Grok 4.5x-ai/grok-4.5-20260708500K ctx$2 in · $6 outtoolsvisrsn500K ctx · $2/$6 per M · tools · vis
- SpaceXAI: Grok 4.6x-ai/grok-4.6-20260810500K ctx$2 in · $6 outtoolsvisrsn500K ctx · $2/$6 per M · tools · vis
- SpaceXAI: Grok 4.7x-ai/grok-4.7-20260916500K ctx$2 in · $6 outtoolsvisrsn500K ctx · $2/$6 per M · tools · vis
- SpaceXAI: Grok Build 0.1x-ai/grok-build-0.1-20260520256K ctx$1 in · $2 outtoolsvisrsn256K ctx · $1/$2 per M · tools · vis
- spark-s1-4b-v6 (Open Spark Jev, abhishek085)Newabhishek-rai/spark-s1-4b-v6— ctx— in · — outopen-weight— ctx · —/— per M
- SPX-CD-Omni (SurdAI, google/gemma-4-12B-it + LoRA r32, one forward pass, self-hosted)Newsurdai/spx-cd-omni— ctx— in · — out— ctx · —/— per M
- Standard One 8B (Standard Thinking)Newstandardthinking/standardone-8b— ctx— in · — outopen-weight— ctx · —/— per M
- StepFun: Step 3.5 Flashstepfun/step-3.5-flash262K ctx$0.100 in · $0.30 outtoolsrsnopen-weight262K ctx · $0.100/$0.30 per M · tools
- StepFun: Step 3.7 Flashstepfun/step-3.7-flash-20260528262K ctx$0.20 in · $1.15 outtoolsvisrsnopen-weight262K ctx · $0.20/$1.15 per M · tools · vis
- StepFun: Step 5 Previewstepfun/step-5-preview-202610081.0M ctx$1 in · $2.70 outtoolsvisrsnopen-weight1.0M ctx · $1/$2.70 per M · tools · vis
- Surogate Rune 26B-A4B v3 (v1.6 pool)Newsurogate/rune-26b-a4b-gguf— ctx— in · — out— ctx · —/— per M
- swanOne (blockbrain, Qwen3.8-Flash-Next NVFP4)Newblockbrain/swanone— ctx— in · — outopen-weight— ctx · —/— per M
- system-one (Qwen3-8B, Sean Goedecke)Newsean-goedecke/system-one-sg— ctx— in · — outopen-weight— ctx · —/— per M
- Tacet Sonata (CodePawl, 144M packed encoder on mmBERT-small, option-marker softmax in one pass, in-process via the author's tacet package)Newcodepawl/tacet-sonata— ctx— in · — out— ctx · —/— per M
- Tencent: Hunyuan A13B Instructtencent/hunyuan-a13b-instruct131K ctx$0.14 in · $0.57 outrsn131K ctx · $0.14/$0.57 per M
- Tencent: Hy-MT2-1.8Btencent/hy-mt2-1.8b-202605218K ctx$0.044 in · $0.18 outopen-weight8K ctx · $0.044/$0.18 per M
- Tencent: Hy-MT2-30B-A3Btencent/hy-mt2-30b-a3b-202605218K ctx$0.074 in · $0.29 outopen-weight8K ctx · $0.074/$0.29 per M
- Tencent: Hy-MT2-7Btencent/hy-mt2-7b-202605218K ctx$0.074 in · $0.29 outopen-weight8K ctx · $0.074/$0.29 per M
- Tencent: Hy3tencent/hy3-20260706262K ctx$0.13 in · $0.53 outtoolsrsnopen-weight262K ctx · $0.13/$0.53 per M · tools
- Tencent: Hy3 previewtencent/hy3-preview-20260421262K ctx$0.18 in · $0.60 outtoolsrsnopen-weight262K ctx · $0.18/$0.60 per M · tools
- Tencent: Hy4 previewtencent/hy4-preview-202608271.0M ctx$0.83 in · $2.50 outtoolsrsnopen-weight1.0M ctx · $0.83/$2.50 per M · tools
- TheDrummer: Cydonia 24B V4.1thedrummer/cydonia-24b-v4.1131K ctx$0.30 in · $0.50 outopen-weight131K ctx · $0.30/$0.50 per M
- TheDrummer: Skyfall 36B V2thedrummer/skyfall-36b-v233K ctx$0.55 in · $0.80 outopen-weight33K ctx · $0.55/$0.80 per M
- TheDrummer: UnslopNemo 12Bthedrummer/unslopnemo-12b1.0M ctx$0.40 in · $0.40 outopen-weight1.0M ctx · $0.40/$0.40 per M
- Thinking Machines: Inklingthinkingmachines/inkling-20260715524K ctx$1 in · $4.05 outtoolsvisrsnopen-weight524K ctx · $1/$4.05 per M · tools · vis
- Thinking Machines: Inkling Smallthinkingmachines/inkling-small-20260730524K ctx$0.45 in · $1.20 outtoolsvisrsnopen-weight524K ctx · $0.45/$1.20 per M · tools · vis
- torchcast-decision-12b (Torchcast AI, Gemma-4-12B fine-tune, option-letter logprob readout)Newtorchcast-ai/torchcast-decision-12b— ctx— in · — out— ctx · —/— per M
- torchcast-decision-27b (Torchcast AI, Qwen3.8-27B fine-tune)Newtorchcast-ai/torchcast-decision-27b— ctx— in · — out— ctx · —/— per M
- typecastlm (Mikhail Gribov, Qwen3.5-4B computed head)Newmikhail-gribov/typecastlm— ctx— in · — outopen-weight— ctx · —/— per M
- TypeCastLM 1.4.0 (Mikhail Gribov, Qwen3.5-4B computed head)Newmihailgribov/typecastlm-qwen3.5-3.8b— ctx— in · — out— ctx · —/— per M
- TypeSafe: Jev Routertypesafe/jev-router1M ctx$-1000000.000 in · $-1000000.000 outtoolsvisrsn1M ctx · $-1000000.000/$-1000000.000 per M · tools · vis
- Upstage: Solar Mini 4upstage/solar-mini4-20260922524K ctx$0.050 in · $0.20 outtoolsrsn524K ctx · $0.050/$0.20 per M · tools
- Upstage: Solar Pro 3upstage/solar-pro-3131K ctx$0.15 in · $0.60 outtoolsrsn131K ctx · $0.15/$0.60 per M · tools
- Upstage: Solar Pro 4upstage/solar-pro4-20260810524K ctx$0.15 in · $0.60 outtoolsrsn524K ctx · $0.15/$0.60 per M · tools
- Venice: Uncensoredvenice/uncensored128K ctx$0.20 in · $0.90 outopen-weight128K ctx · $0.20/$0.90 per M
- verdict-small (Manavarya09, multilingual-e5-small 118M)Newmanavarya09/verdict-small— ctx— in · — outopen-weight— ctx · —/— per M
- WaterSheep (Samrat Dutta, ModernBERT-base encoder with calibrated heads, served by the author's own `watersheep --serve`)Newsamratduttaofficial/watersheep— ctx— in · — out— ctx · —/— per M
- watt-flash-0.1 (Zaitgeist Labs, 140M mmBERT-small encoder with an option-marker scorer, one forward pass per request, self-hosted)Newzaitlabs/watt-flash-0.1— ctx— in · — out— ctx · —/— per M
- Winnow-12B Q8Neweldanring/winnow-12b— ctx— in · — outopen-weight— ctx · —/— per M
- wity-1 (Wity, reasoning auto)Newwity/wity-1— ctx— in · — out— ctx · —/— per M
- WizardLM-2 8x22Bmicrosoft/wizardlm-2-8x22b66K ctx$0.62 in · $0.62 outopen-weight66K ctx · $0.62/$0.62 per M
- Writer: Palmyra X5writer/palmyra-x5-202504281.0M ctx$0.60 in · $6 out1.0M ctx · $0.60/$6 per M
- Xiaomi: MiMo-V2.5xiaomi/mimo-v2.5-202604221.1M ctx$0.14 in · $0.28 outtoolsvisrsnopen-weight1.1M ctx · $0.14/$0.28 per M · tools · vis
- Xiaomi: MiMo-V2.5-Proxiaomi/mimo-v2.5-pro-202604221.1M ctx$0.43 in · $0.87 outtoolsrsnopen-weight1.1M ctx · $0.43/$0.87 per M · tools
- Xiaomi: MiMo-V2.6-Flashxiaomi/mimo-v2.6-flash-202609211.1M ctx$0.14 in · $0.28 outtoolsvisrsnopen-weight1.1M ctx · $0.14/$0.28 per M · tools · vis
- Xiaomi: MiMo-V2.6-Proxiaomi/mimo-v2.6-pro-202609211.1M ctx$0.43 in · $0.87 outtoolsvisrsnopen-weight1.1M ctx · $0.43/$0.87 per M · tools · vis
- Xiaomi: MiMo-V2.6-Pro-UltraSpeedxiaomi/mimo-v2.6-pro-ultraspeed-202609211.0M ctx$4.35 in · $8.70 outtoolsvisrsnopen-weight1.0M ctx · $4.35/$8.70 per M · tools · vis
- Xor 26B-A4B (Juspay, Gemma-4-26B-A4B, bf16)Newjuspay/xor-26b-a4b— ctx— in · — out— ctx · —/— per M
- Z.ai: GLM 4.5z-ai/glm-4.5131K ctx$0.60 in · $2.20 outtoolsrsnopen-weight131K ctx · $0.60/$2.20 per M · tools
- Z.ai: GLM 4.5 Airz-ai/glm-4.5-air131K ctx$0.13 in · $0.85 outtoolsrsn131K ctx · $0.13/$0.85 per M · tools
- Z.ai: GLM 4.5Vz-ai/glm-4.5v66K ctx$0.60 in · $1.80 outtoolsvisrsnopen-weight66K ctx · $0.60/$1.80 per M · tools · vis
- Z.ai: GLM 4.6z-ai/glm-4.6205K ctx$0.55 in · $2.20 outtoolsrsnopen-weight205K ctx · $0.55/$2.20 per M · tools
- Z.ai: GLM 4.6Vz-ai/glm-4.6-20251208131K ctx$0.30 in · $0.90 outtoolsvisrsnopen-weight131K ctx · $0.30/$0.90 per M · tools · vis
- Z.ai: GLM 4.7z-ai/glm-4.7-20251222205K ctx$0.54 in · $1.98 outtoolsrsn205K ctx · $0.54/$1.98 per M · tools
- Z.ai: GLM 4.7 Flashz-ai/glm-4.7-flash-20260119200K ctx$0.061 in · $0.40 outtoolsrsnopen-weight200K ctx · $0.061/$0.40 per M · tools
- Z.ai: GLM 5z-ai/glm-5-20260211205K ctx$0.60 in · $1.92 outtoolsrsn205K ctx · $0.60/$1.92 per M · tools
- Z.ai: GLM 5 Turboz-ai/glm-5-turbo-20260315203K ctx$1.20 in · $4 outtoolsrsnopen-weight203K ctx · $1.20/$4 per M · tools
- Z.ai: GLM 5.1z-ai/glm-5.1-20260406205K ctx$0.97 in · $3.04 outtoolsrsnopen-weight205K ctx · $0.97/$3.04 per M · tools
- Z.ai: GLM 5.2z-ai/glm-5.2-202606161.0M ctx$0.62 in · $2.42 outtoolsrsnopen-weight1.0M ctx · $0.62/$2.42 per M · tools
- Z.ai: GLM 5.3z-ai/glm-5.3-202608161.0M ctx$0.079 in · $1.40 outtoolsrsnopen-weight1.0M ctx · $0.079/$1.40 per M · tools
- Z.ai: GLM 5.3 Flashz-ai/glm-5.3-flash-202608261.0M ctx$0.047 in · $0.16 outtoolsvisrsnopen-weight1.0M ctx · $0.047/$0.16 per M · tools · vis
- Z.ai: GLM 5.3 FlashXz-ai/glm-5.3-flashx-202609181.0M ctx$0.37 in · $1.25 outtoolsvisrsnopen-weight1.0M ctx · $0.37/$1.25 per M · tools · vis
- Z.ai: GLM 5.3 Primez-ai/glm-5.3-prime-202609211M ctx$2.80 in · $8.80 outtoolsrsn1M ctx · $2.80/$8.80 per M · tools
- Z.ai: GLM 5V Turboz-ai/glm-5v-turbo-20260401203K ctx$1.20 in · $4 outtoolsvisrsn203K ctx · $1.20/$4 per M · tools · vis