Models · Conifer

Fig. 01·the frontier

Price against quality221 models

Blended price per million tokens against measured score. Higher and further left is better.

Intelligence and blended price for 221 models
Model	Lab	Intelligence	Price per million tokens	Price frontier	On Conifer	Runs locally
Claude Fable 5	Anthropic	62.1	$20	no	yes	no
Claude Fable 5.1 (max)	Anthropic	65.7	$20	yes	yes	no
Claude 4.5 Haiku (Non-reasoning)	Anthropic	24.1	$2	no	yes	no
Claude Opus 4.8 (max)	Anthropic	57.3	$10	no	yes	no
Claude Opus 4.6 (Non-reasoning, high)	Anthropic	38.8	$10	no	yes	no
Claude Opus 4.7 (max)	Anthropic	55	$10	no	yes	no
Claude Opus 5 (max)	Anthropic	63.1	$10	yes	yes	no
Claude Sonnet 4.6 (Non-reasoning, high)	Anthropic	36.8	$6	no	yes	no
Claude Sonnet 5 (max)	Anthropic	55.3	$4	no	yes	no
Command A	Cohere	7.5	$4.4	no	yes	no
DeepSeek R1 0528	DeepSeek	20.4	$1.8	no	yes	no
DeepSeek V3.1	DeepSeek	21	$0.86	no	yes	no
DeepSeek V3.1 Terminus	DeepSeek	31.4	$1.9	no	yes	no
DeepSeek V3.2	DeepSeek	32.8	$0.32	no	yes	no
DeepSeek V4 Flash 0731 (max)	DeepSeek	51.8	$0.66	no	yes	no
DeepSeek V4 Flash Vision (max)	DeepSeek	51.5	$0.66	no	yes	no
DeepSeek V4 Pro 0813 (max)	DeepSeek	53.2	$2.0	no	yes	no
Gemini 2.5 Flash	Google	20.3	$0.85	no	yes	no
Gemini 2.5 Pro	Google	25.9	$3.4	no	yes	no
Gemini 3 Flash (Non-reasoning)	Google	27.9	$1.1	no	yes	no
Gemini 3.1 Flash-Lite	Google	25.6	$0.56	no	yes	no
Gemini 3.1 Pro Preview	Google	47.7	$4.5	no	yes	no
Gemini 3.5 Flash	Google	52	$3.4	no	yes	no
Gemini 3.5 Flash-Lite	Google	37.4	$0.85	no	yes	no
Gemini 3.6 Flash	Google	51.6	$1.5	no	yes	no
Gemini 3.7 Flash (high)	Google	56	$1.5	no	yes	no
Gemma 4 26B A4B	Google	26.1	$0.18	no	yes	no
GLM-4.5-Air	Z AI	16.7	$0.37	no	yes	no
GLM-4.5V	Z AI	9	$0.90	no	yes	no
GLM-4.6	Z AI	29.3	$0.96	no	yes	no
GLM-4.6V	Z AI	16.9	$0.45	no	yes	no
GLM-4.7	Z AI	34.5	$1	no	yes	no
GLM-4.7-Flash	Z AI	23.3	$0.15	no	yes	no
GLM-5	Z AI	40.6	$1.6	no	yes	no
GLM-5.1	Z AI	41	$2.0	no	yes	no
GLM-5.2 (max)	Z AI	52.6	$2.1	no	yes	no
GLM-5.3 (max)	Z AI	59.5	$2.1	yes	yes	no
GLM-5.3-Flash	Z AI	57.5	$0.24	yes	yes	no
GPT-4.1	OpenAI	19.6	$3.5	no	yes	no
GPT-4.1 mini	OpenAI	14.8	$0.70	no	yes	no
GPT-4.1 nano	OpenAI	9.6	$0.17	no	yes	no
GPT-4o (May)	OpenAI	8.4	$7.5	no	yes	no
GPT-4o (Aug)	OpenAI	9.4	$4.4	no	yes	no
GPT-4o (Nov)	OpenAI	11.1	$4.4	no	yes	no
GPT-4o mini	OpenAI	6.7	$0.26	no	yes	no
GPT-5 (high)	OpenAI	35.3	$3.4	no	yes	no
GPT-5 mini (high)	OpenAI	25.8	$0.69	no	yes	no
GPT-5 nano (high)	OpenAI	20.1	$0.14	no	yes	no
GPT-5.1 (high)	OpenAI	37.5	$3.4	no	yes	no
GPT-5.2 (xhigh)	OpenAI	43.3	$4.8	no	yes	no
GPT-5.4 (xhigh)	OpenAI	53.1	$5.6	no	yes	no
GPT-5.4 mini (xhigh)	OpenAI	40.9	$1.7	no	yes	no
GPT-5.4 nano (xhigh)	OpenAI	39.7	$0.46	no	yes	no
GPT-5.5 (xhigh)	OpenAI	56.3	$11	no	yes	no
GPT-5.6 Luna (max)	OpenAI	52.3	$0.45	no	yes	no
GPT-5.6 Sol (max)	OpenAI	60.9	$8	no	yes	no
GPT-5.6 Terra (max)	OpenAI	56.6	$4.5	no	yes	no
gpt-oss-120b (high)	OpenAI	24.1	$0.26	no	yes	no
gpt-oss-20b (high)	OpenAI	15.2	$0.09	no	yes	no
Granite 4.2 8B	IBM	19.6	$0.11	no	yes	no
Grok 4.3 (high)	SpaceXAI	37.9	$1.6	no	yes	no
Grok 4.5 (high)	SpaceXAI	55.8	$3	no	yes	no
Grok 4.6 (high)	SpaceXAI	60.9	$3	yes	yes	no
Hermes 3 - Llama-3.1 70B	Nous Research	4.8	$0.70	no	yes	no
Hermes 4 405B	Nous Research	8.8	$1.5	no	yes	no
Hermes 4 70B	Nous Research	9.9	$0.20	no	yes	no
Hy3	Tencent	42.2	$0.24	no	yes	no
Inkling	Thinking Machines	42.3	$1.8	no	yes	no
Inkling Small	Thinking Machines	41.2	$0.53	no	yes	no
Kimi K2 0905	Kimi	24	$1.1	no	yes	no
Kimi K2.5	Kimi	36	$1.2	no	yes	no
Kimi K2.6	Kimi	45.1	$1.7	no	yes	no
Kimi K2.7 Code	Kimi	43	$1.7	no	yes	no
Kimi K3 (max)	Kimi	59.7	$6	no	yes	no
Ling 3.0 Flash	InclusionAI	37.8	$0.11	yes	yes	no
Llama 3.1 8B	Meta	7.4	$0.03	yes	yes	no
Llama 3.3 70B	Meta	9.3	$0.67	no	yes	no
Llama 4 Maverick	Meta	14.5	$0.42	no	yes	no
Llama 4 Scout	Meta	10.3	$0.30	no	yes	no
MiMo-V2.5	Xiaomi	38	$0.17	no	yes	no
MiMo-V2.5-Pro	Xiaomi	42.9	$0.54	no	yes	no
MiniMax-M2	MiniMax	28.9	$0.53	no	yes	no
MiniMax-M2.1	MiniMax	32.1	$0.53	no	yes	no
MiniMax-M2.5	MiniMax	34.5	$0.53	no	yes	no
MiniMax-M2.7	MiniMax	38.9	$0.53	no	yes	no
MiniMax-M3	MiniMax	45.4	$0.53	no	yes	no
Ministral 3 14B	Mistral	11.2	$0.20	no	yes	no
Ministral 3 3B	Mistral	7.1	$0.10	no	yes	yes
Ministral 3 8B	Mistral	9	$0.15	no	yes	no
Mistral Large 3	Mistral	15.9	$0.75	no	yes	no
Mistral Medium 3	Mistral	12.5	$0.80	no	yes	no
Mistral Medium 3.5	Mistral	30.4	$3	no	yes	no
Mistral Small 3	Mistral	6.7	$0.15	no	yes	no
Mistral Small 4	Mistral	19.7	$0.26	no	yes	no
Muse Glimmer (high)	Meta	35.1	$0.64	no	yes	no
Nemotron 3 Nano	NVIDIA	14.5	$0.09	no	yes	no
Nemotron 3 Super	NVIDIA	25.7	$0.35	no	yes	no
Nemotron 3 Ultra	NVIDIA	38.3	$1.1	no	yes	no
Nemotron 3.5 Lightning	NVIDIA	23.6	$0.11	yes	yes	no
o1	OpenAI	23.9	$26	no	yes	no
o3	OpenAI	31.1	$3.5	no	yes	no
o3-mini	OpenAI	19.2	$1.9	no	yes	no
o4-mini (high)	OpenAI	26.1	$1.9	no	yes	no
Phi-4	Microsoft	4.6	$0.22	no	yes	no
Qwen2.5 72B	Alibaba	9.4	$0.48	no	yes	no
Qwen3 14B	Alibaba	10.4	$1.3	no	yes	no
Qwen3 235B A22B 2507	Alibaba	19.9	$0.75	no	yes	no
Qwen3 30B A3B 2507	Alibaba	14.6	$0.75	no	yes	no
Qwen3 30B A3B 2507 (Non-reasoning)	Alibaba	8.9	$0.35	no	yes	no
Qwen3 32B	Alibaba	11.4	$0.28	no	yes	no
Qwen3 Coder 30B A3B	Alibaba	13.6	$0.90	no	yes	no
Qwen3 Coder 480B	Alibaba	18.2	$3	no	yes	no
Qwen3 Coder Next	Alibaba	21.3	$0.56	no	yes	no
Qwen3 Max	Alibaba	24.5	$2.4	no	yes	no
Qwen3 Next 80B A3B (Reasoning)	Alibaba	16.9	$0.41	no	yes	no
Qwen3 VL 235B A22B	Alibaba	14.4	$0.70	no	yes	no
Qwen3 VL 235B A22B (Reasoning)	Alibaba	20.9	$1.3	no	yes	no
Qwen3 VL 30B A3B	Alibaba	9.9	$0.35	no	yes	no
Qwen3.5 122B A10B	Alibaba	32.8	$1.1	no	yes	no
Qwen3.5 27B	Alibaba	34.6	$0.82	no	yes	yes
Qwen3.5 35B A3B	Alibaba	29.9	$0.69	no	yes	no
Qwen3.5 397B A17B	Alibaba	34.3	$1.4	no	yes	no
Qwen3.5 9B	Alibaba	21.8	$0.15	no	yes	yes
Qwen3.6 27B	Alibaba	37.7	$1.4	no	yes	yes
Qwen3.6 35B A3B	Alibaba	32.1	$0.84	no	yes	no
Qwen3.7 Max	Alibaba	46.7	$3.8	no	yes	no
Qwen3.8 2.4T A95B	Alibaba	57.7	$3	no	yes	no
Qwen3.8 27B (xhigh)	Alibaba	52	$1.1	no	yes	yes
Qwen3.8-Flash-Next	Alibaba	55.8	$0.23	yes	yes	no
Qwen3.8 Max	Alibaba	58.1	$3	no	yes	no
Step 3.7 Flash	StepFun	30.9	$0.44	no	yes	no
Mercury 2	Inception	21.9	$0.38	no	no	no
Qwen3.5 Omni Plus	Alibaba	31.3	$1.5	no	no	no
Nova 2.0 Omni (medium)	Amazon	21.3	$0.85	no	no	no
Qwen3.5 122B A10B (Non-reasoning)	Alibaba	28.2	$1.1	no	no	no
Gemma 4 12B (Non-reasoning)	Google	13.2	$0.15	no	no	no
Muse Spark 1.2 (xhigh)	Meta	56.8	$2	no	no	no
Apodex 1.1	Apodex	44	$0.97	no	no	no
Qwen3 Omni 30B A3B	Alibaba	4.8	$0.43	no	no	no
Granite 4.2 3B	IBM	14.3	$0.05	yes	no	no
Nova 2.0 Pro Preview (medium)	Amazon	22.1	$3.4	no	no	no
Granite 4.2 30B	IBM	23.7	$0.28	no	no	no
Mistral Small 4 (Non-reasoning)	Mistral	12.3	$0.26	no	no	no
Solar Pro 4	Upstage	41.6	$0.53	no	no	no
Nova 2.0 Omni (Non-reasoning)	Amazon	10.4	$0.85	no	no	no
Qwen3.5 9B (Non-reasoning)	Alibaba	20.6	$0.19	no	no	no
GPT-6 Astra (Non-reasoning)	OpenAI	55.3	$20	no	no	no
Hermes 4 70B (Non-reasoning)	Nous Research	6.7	$0.20	no	no	no
Nemotron 3 Nano (Non-reasoning)	NVIDIA	7.2	$0.09	no	no	no
Qwen3 Next 80B A3B	Alibaba	13.8	$0.41	no	no	no
Llama Nemotron Super 49B v1.5 (Non-reasoning)	NVIDIA	8.5	$0.40	no	no	no
NVIDIA Nemotron Nano 9B V2 (Non-reasoning)	NVIDIA	7.2	$0.09	no	no	no
GPT-6 Astra (max)	OpenAI	61.2	$20	no	no	no
Qwen3.5 4B (Non-reasoning)	Alibaba	16.1	$0.06	no	no	no
Qwen3.5 397B A17B (Non-reasoning)	Alibaba	32.7	$1.4	no	no	no
HyperNova 60B 2605 (high)	Multiverse Computing	18.3	$0.07	no	no	no
Nova Micro	Amazon	4.4	$0.06	no	no	no
Qwen3.8 27B	Alibaba	34.7	$1.1	no	no	yes
Qwen3.6 27B (Non-reasoning)	Alibaba	31.3	$1.4	no	no	no
Nex-N2-Pro	Nex AGI	41.7	$1	no	no	no
Sarvam 105B (high)	Sarvam	11.9	$0.07	no	no	no
MiMo-V2.5-Pro (Non-reasoning)	Xiaomi	28.4	$0.54	no	no	no
Ring-flash-2.0	InclusionAI	8	$0.25	no	no	no
Apertus 70B Instruct	Swiss AI Initiative	2	$1.3	no	no	no
Gemma 4 E4B (Non-reasoning)	Google	8.7	$0.04	no	no	no
GPT-5.3 Codex (xhigh)	OpenAI	45.5	$4.8	no	no	no
LongCat 2.0	LongCat	34	$1.3	no	no	no
Granite 4.0 H Small	IBM	4.9	$0.11	no	no	no
Llama 3.2 11B (Vision)	Meta	3	$0.34	no	no	no
Nova 2.0 Lite (high)	Amazon	20.8	$0.85	no	no	no
Qwen3.5 4B	Alibaba	20.4	$0.06	yes	no	yes
Qwen3.6 35B A3B (Non-reasoning)	Alibaba	24.6	$0.84	no	no	no
DeepSeek V4 Pro (Non-reasoning)	DeepSeek	31.9	$0.54	no	no	no
NVIDIA Nemotron Nano 12B v2 VL	NVIDIA	8.8	$0.30	no	no	no
Qwen3.5 Omni Flash	Alibaba	19.2	$0.28	no	no	no
Magistral Small 1.2	Mistral	11.5	$0.75	no	no	no
Gemma 4 26B A4B (Non-reasoning)	Google	20.4	$0.20	no	no	no
Llama 3.1 Nemotron 70B	NVIDIA	7.4	$1.2	no	no	no
Sarvam 30B (high)	Sarvam	6.4	$0.05	no	no	no
Nova 2.0 Lite (Non-reasoning)	Amazon	11.8	$0.85	no	no	no
GPT-5.6 Sol (Non-reasoning)	OpenAI	41.9	$8	no	no	no
Celeris-1	Celeris	12.4	$0.33	no	no	no
Granite 4.1 8B	IBM	6.4	$0.06	no	no	no
Apertus 8B Instruct	Swiss AI Initiative	1	$0.13	no	no	no
Gemini 3.8 Flash (high)	Google	58.7	$1.5	yes	no	no
Nemotron 3 Nano Omni 30B A3B	NVIDIA	15	$0.13	no	no	no
Agnes 2.5 Pro Alpha	Sapiens AI	39.7	$0.56	no	no	no
Olmo 3 7B	Allen Institute for AI	2.4	$0.13	no	no	no
Grok 4.3 (Non-reasoning)	SpaceXAI	25	$1.6	no	no	no
GPT-5.6 Terra (Non-reasoning)	OpenAI	34.6	$4.5	no	no	no
Nova 2.0 Pro Preview (Non-reasoning)	Amazon	14.4	$3.4	no	no	no
Claude 4.5 Haiku	Anthropic	29.9	$2	no	no	no
Qwen3.7 Plus	Alibaba	39.4	$0.70	no	no	no
NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning)	NVIDIA	4.2	$0.30	no	no	no
DeepSeek V4 Flash (Non-reasoning)	DeepSeek	29.3	$0.12	no	no	no
ERNIE 4.5 300B A47B	Baidu	8.9	$0.48	no	no	no
Nova 2.0 Omni (low)	Amazon	16.7	$0.85	no	no	no
Trinity Large Thinking	Arcee AI	18.7	$0.41	no	no	no
Solar Pro 3	Upstage	14.5	$0.26	no	no	no
Qwen3 Omni 30B A3B (Reasoning)	Alibaba	9.5	$0.43	no	no	no
DeepSeek V4 Pro (max)	DeepSeek	45.3	$0.54	no	no	no
GPT-5.5 Instant (June 2026)	OpenAI	29.2	$11	no	no	no
Llama Nemotron Ultra	NVIDIA	8.9	$0.90	no	no	no
Gemma 4 31B (Non-reasoning)	Google	22.3	$0.21	no	no	no
Hermes 4 405B (Non-reasoning)	Nous Research	8.6	$1.5	no	no	no
Claude Sonnet 5 (Non-reasoning)	Anthropic	42.6	$4	no	no	no
Gemma 4 E4B	Google	12.2	$0.04	yes	no	yes
Reka Flash 3	Reka AI	3.7	$0.35	no	no	no
GPT-5.6 Luna (Non-reasoning)	OpenAI	26.8	$0.45	no	no	no
Llama Nemotron Super 49B v1.5	NVIDIA	12.4	$0.40	no	no	no
Nova Premier	Amazon	12.7	$5	no	no	no
GLM-5.2 (Non-reasoning)	Z AI	34.8	$2.1	no	no	no
Ring-2.6-1T	InclusionAI	31.7	$0.85	no	no	no
Qwen3.5 35B A3B (Non-reasoning)	Alibaba	24.3	$0.69	no	no	no
NVIDIA Nemotron Nano 9B V2	NVIDIA	8.7	$0.07	no	no	no
Claude Sonnet 4.6 (Non-reasoning, low)	Anthropic	35.1	$6	no	no	no
Agnes 2.5 Pro Beta	Sapiens AI	49.1	$0.15	yes	no	no
Nova 2.0 Pro Preview (low)	Amazon	19.8	$3.4	no	no	no
Quasar 438B (max)	Multiverse Computing	43	$0.90	no	no	no
KAT-Coder-Pro V2	KwaiKAT	33.7	$0.53	no	no	no
Gemma 4 12B	Google	22.2	$0.15	no	no	yes

02·release dates

83 records · 139 served models

Intelligence by release date

Claude Fable 5.1maxAnthropicreleased 2026-09-01intelligence 65.7on Conifer $9 in · $45 outhighest served score when released

highest served score to date one lab's best score, in release order

03·running cost

8 models · 60k in + 4k out per minute

Cost per hour of a steady coding workload

the meters start when this panel is on screen

Gemini 3.7 Flash (high)Google$3.6/hour$3.6/hour · $0.75 in / $3.8 out per Mtok
DeepSeek V4 Pro 0813 (max)DeepSeek$5.3/hour$5.3/hour · $1.3 in / $2.6 out per Mtok
GLM-5.3 (max)Z AI$6.1/hour$6.1/hour · $1.4 in / $4.4 out per Mtok
Qwen3.8 MaxAlibaba$8.6/hour$8.6/hour · $2 in / $6 out per Mtok
Kimi K3 (max)Kimi$14/hour$14/hour · $3 in / $15 out per Mtok
Grok 4.6 (high)SpaceXAI$17/hour$17/hour · $4 in / $12 out per Mtok
GPT-5.6 Sol (max)OpenAI$19/hour$19/hour · $4 in / $20 out per Mtok
Claude Fable 5.1 (max)Anthropic$43/hour$43/hour · $9 in / $45 out per Mtok

04·time to first token

Time to first token, best model per lab

Median time to first token; the reply then streams at each model's output speed.

11.49s

In one sentence, what is a Pareto frontier?

DeepSeek V4 Pro 0813 (max)
A Pareto frontier is the set of choices where nothing can be improved without making something else worse.
first token at 1.9s
GLM-5.3 (max)
A Pareto frontier is the set of choices where nothing can be improved without making something else worse.
first token at 2.0s
Claude Opus 4.6 (Non-reasoning, high)
A Pareto frontier is the set of choices where nothing can be improved without making something else worse.
first token at 2.1s
Qwen3.8 Max
A Pareto frontier is the set of choices where nothing can be improved without making something else worse.
first token at 2.5s
Kimi K3 (max)
A Pareto frontier is the set of choices where nothing can be improved without making something else worse.
first token at 5.3s
GPT-5.4 mini (xhigh)
A Pareto frontier is the set of choices where nothing can be improved without making something else worse.
first token at 7.6s
Grok 4.5 (high)
A Pareto frontier is the set of choices where nothing can be improved without making something else worse.
first token at 10s
Gemini 3.7 Flash (high)
A Pareto frontier is the set of choices where nothing can be improved without making something else worse.
first token at 11s

Claude Fable 5.1 (max), the slowest served model at 273s to first token, is left out. The fastest, Ministral 3 3B, takes 0.60s.

05·hallucination rate

Wrong answers instead of declining

Of 100 questions a model could not answer correctly, how many it answered anyway instead of declining.

30 of 100GLM-5.3 (max)guessed · 70 declined
34 of 100Grok 4.6 (high)guessed · 66 declined
42 of 100Qwen3.8 Maxguessed · 58 declined
53 of 100Kimi K3 (max)guessed · 47 declined
65 of 100Gemini 3.7 Flash (high)guessed · 35 declined
73 of 100Claude Fable 5.1 (max)guessed · 27 declined
92 of 100GPT-5.6 Sol (max)guessed · 8 declined
95 of 100DeepSeek V4 Pro 0813 (max)guessed · 5 declined

GLM-5.3maxZ AIintelligence 59.5hallucinated 29.6%on Conifer $1.4 in · $4.4 out

06·labs

12 labs · 221 models

Price against intelligence, by lab

Intelligence Index against blended list price per million tokens, log scale, the same axes in every panel.

Claude Fable 5.1maxAnthropicintelligence 65.7blended $20/Mtokon Conifer $9 in · $45 outserved by Conifer

07·output speed

The same paragraph at six output speeds

Each model types at its median measured output speed.

Gemini 3.5 Flash-Lite382 tok/s

Conifer routes each request to a model that fits it. A small local model takes a quick question and a larger hosted model takes a hard one, and nothing leaves the machine unless the route says it should. The runtime installs with one command, the router reads the request before it picks a model, and every answer carries a receipt that says what it cost. Your own hardware and your own keys cost nothing extra, and cloud tokens are billed at the provider's own rate. One key and one endpoint reach every model, and the response looks the same whether it came from the laptop or from a hosted model.

0.4s

Gemini 3.7 Flash293 tok/s

Conifer routes each request to a model that fits it. A small local model takes a quick question and a larger hosted model takes a hard one, and nothing leaves the machine unless the route says it should. The runtime installs with one command, the router reads the request before it picks a model, and every answer carries a receipt that says what it cost. Your own hardware and your own keys cost nothing extra, and cloud tokens are billed at the provider's own rate. One key and one endpoint reach every model, and the response looks the same whether it came from the laptop or from a hosted model.

0.5s

GPT-5.4134 tok/s

Conifer routes each request to a model that fits it. A small local model takes a quick question and a larger hosted model takes a hard one, and nothing leaves the machine unless the route says it should. The runtime installs with one command, the router reads the request before it picks a model, and every answer carries a receipt that says what it cost. Your own hardware and your own keys cost nothing extra, and cloud tokens are billed at the provider's own rate. One key and one endpoint reach every model, and the response looks the same whether it came from the laptop or from a hosted model.

1.1s

Claude Fable 5.167 tok/s

Conifer routes each request to a model that fits it. A small local model takes a quick question and a larger hosted model takes a hard one, and nothing leaves the machine unless the route says it should. The runtime installs with one command, the router reads the request before it picks a model, and every answer carries a receipt that says what it cost. Your own hardware and your own keys cost nothing extra, and cloud tokens are billed at the provider's own rate. One key and one endpoint reach every model, and the response looks the same whether it came from the laptop or from a hosted model.

2.2s

Claude Opus 557 tok/s

Conifer routes each request to a model that fits it. A small local model takes a quick question and a larger hosted model takes a hard one, and nothing leaves the machine unless the route says it should. The runtime installs with one command, the router reads the request before it picks a model, and every answer carries a receipt that says what it cost. Your own hardware and your own keys cost nothing extra, and cloud tokens are billed at the provider's own rate. One key and one endpoint reach every model, and the response looks the same whether it came from the laptop or from a hosted model.

2.6s

Gemma 4 31B35 tok/s

Conifer routes each request to a model that fits it. A small local model takes a quick question and a larger hosted model takes a hard one, and nothing leaves the machine unless the route says it should. The runtime installs with one command, the router reads the request before it picks a model, and every answer carries a receipt that says what it cost. Your own hardware and your own keys cost nothing extra, and cloud tokens are billed at the provider's own rate. One key and one endpoint reach every model, and the response looks the same whether it came from the laptop or from a hosted model.

4.3s

08·memory footprint

What fits on your machine

Pick a memory size and a model; the model needs its Q4_K_M file plus 0.6 GB for the runtime.

The next size up, Mistral Small 3.2 24B Instruct 2506, needs about 15 GB.

09·served models

153 served models

Every served model


Claude Fable 5.1max	Anthropic	closed	65.7	81.6	67	273s	1M	$9	$45	2026-09-01
Claude Opus 5max	Anthropic	closed	63.1	78	57	77s	1M	$5	$25	2026-07-24
Claude Fable 5	Anthropic	closed	62.1	76.5	70	105s	1M	$10	$50	2026-06-09
GPT-5.6 Solmax	OpenAI	closed	60.9	77.4	77	99s	1.1M	$4	$20	2026-07-09
Grok 4.6high	SpaceXAI	closed	60.9	76.8	60	50s	500k	$4	$12	2026-08-12
Kimi K3max	Kimi	open	59.7	76.2	38	5.3s	1M	$3	$15	2026-07-16
GLM-5.3max	Z AI	open	59.5	74.8	75	2.0s	1M	$1.4	$4.4	2026-08-18
Qwen3.8 Max	Alibaba	closed	58.1	71.8	39	2.5s	256k	$2	$6	2026-08-03
Qwen3.8 2.4T A95B	Alibaba	open	57.7	71.9	40	2.6s	262k	$2	$6	2026-08-12
GLM-5.3-Flash	Z AI	open	57.5	71.5	47	1.7s	1M	$0.15	$0.50	2026-08-26
Claude Opus 4.8max	Anthropic	closed	57.3	74.3	62	44s	1M	$5	$25	2026-05-28
GPT-5.6 Terramax	OpenAI	closed	56.6	76.7	103	231s	1.1M	$2	$12	2026-07-09
GPT-5.5xhigh	OpenAI	closed	56.3	74.9	84	52s	1.1M	$5	$30	2026-04-23
Gemini 3.7 Flashhigh	Google	closed	56	76.1	293	11s	1M	$0.75	$3.8	2026-08-13
Grok 4.5high	SpaceXAI	closed	55.8	72.4	54	10s	500k	$4	$12	2026-07-08
Qwen3.8-Flash-Next	Alibaba	open	55.8	73.1	82	2.8s	1M	$0.15	$0.47	2026-08-26
Claude Sonnet 5max	Anthropic	closed	55.3	71.5	78	178s	1M	$2	$10	2026-06-30
Claude Opus 4.7max	Anthropic	closed	55	73.6	52	18s	1M	$5	$25	2026-04-16
DeepSeek V4 Pro 0813max	DeepSeek	open	53.2	68.8	60	1.9s	1M	$1.3	$2.6	2026-08-13
GPT-5.4xhigh	OpenAI	closed	53.1	71.1	134	115s	1.1M	$2.5	$15	2026-03-05
GLM-5.2max	Z AI	open	52.6	68.8	69	1.6s	1M	$1.4	$4.4	2026-06-16
GPT-5.6 Lunamax	OpenAI	closed	52.3	71.4	120	162s	1.1M	$0.20	$1.2	2026-07-09
Gemini 3.5 Flash	Google	closed	52	70.1	196	15s	1M	$1.5	$9	2026-05-19
Qwen3.8 27Bxhigh	Alibaba	open	52	68.1	40	4.2s	262k	$0.50	$3	2026-08-14
DeepSeek V4 Flash 0731max	DeepSeek	open	51.8	69.1	140	1.2s	1M	$0.44	$1.3	2026-07-31
Gemini 3.6 Flash	Google	closed	51.6	69.2	182	16s	1M	$0.75	$3.8	2026-07-21
DeepSeek V4 Flash Visionmax	DeepSeek	closed	51.5	65	120	1.1s	1M	$0.44	$1.3	2026-08-21
Gemini 3.1 Pro Preview	Google	closed	47.7	68.8	111	27s	1M	$2	$12	2026-02-19
Qwen3.7 Max	Alibaba	closed	46.7	66	204	2.3s	1M	$2.5	$7.5	2026-05-19
MiniMax-M3	MiniMax	open	45.4	58.6	89	1.4s	1M	$0.30	$1.2	2026-06-01
Kimi K2.6	Kimi	open	45.1	61.8	41	2.5s	262k	$0.95	$4	2026-04-20
GPT-5.2xhigh	OpenAI	closed	43.3	·	72	109s	400k	$3.5	$28	2025-12-11
Kimi K2.7 Code	Kimi	open	43	60.8	39	3.0s	262k	$0.95	$4	2026-06-12
MiMo-V2.5-Pro	Xiaomi	open	42.9	60.2	35	4.1s	1M	$1	$3	2026-04-22
Inkling	Thinking Machines	open	42.3	52.1	74	2.9s	524k	$1	$4.0	2026-07-15
Hy3	Tencent	open	42.2	58.8	94	2.8s	262k	$0.14	$0.58	2026-07-06
Inkling Small	Thinking Machines	open	41.2	52.9	111	2.7s	524k	$0.50	$1.2	2026-07-30
GLM-5.1	Z AI	open	41	55.8	50	1.8s	203k	$1.1	$3.5	2026-04-07
GPT-5.4 minixhigh	OpenAI	closed	40.9	56.1	191	7.6s	400k	$0.75	$4.5	2026-03-17
GLM-5	Z AI	open	40.6	·	66	1.4s	203k	$0.60	$2.1	2026-02-11
GPT-5.4 nanoxhigh	OpenAI	closed	39.7	56.1	169	5.5s	400k	$0.20	$1.3	2026-03-17
GLM-5-Turbo	Z AI	closed	39.1	·	·	·	203k	$1.2	$4	2026-03-15
MiniMax-M2.7	MiniMax	open	38.9	52.6	74	1.5s	197k	$0.25	$1	2026-03-18
Claude Opus 4.6 (Non-reasoning, high)	Anthropic	closed	38.8	·	36	2.1s	1M	$5	$25	2026-02-05
Nemotron 3 Ultra	NVIDIA	open	38.3	49.3	164	2.7s	262k	$0.50	$2.2	2026-06-04
MiMo-V2.5	Xiaomi	open	38	56.8	58	3.8s	262k	$0.40	$2	2026-04-22
Grok 4.3high	SpaceXAI	closed	37.9	42.2	135	19s	1M	$2.5	$5	2026-04-30
Ling 3.0 Flash	InclusionAI	open	37.8	50.6	330	2.6s	131k	$0.06	$0.18	2026-08-04
Qwen3.6 27B	Alibaba	open	37.7	53.7	53	3.6s	262k	$0.32	$3.2	2026-04-22
GPT-5.1high	OpenAI	closed	37.5	49.4	87	43s	400k	$2.5	$20	2025-11-13
Gemini 3.5 Flash-Lite	Google	closed	37.4	49.3	382	7.0s	1M	$0.30	$2.5	2026-07-21
Claude Sonnet 4.6 (Non-reasoning, high)	Anthropic	closed	36.8	·	44	1.7s	1M	$3	$15	2026-02-17
Kimi K2.5	Kimi	open	36	46.8	·	·	262k	$0.60	$3	2026-01-27
GLM 5V Turbo	Z AI	closed	35.3	·	·	·	205k	$1.2	$4	2026-04-01
GPT-5high	OpenAI	closed	35.3	37.8	86	63s	400k	$2.5	$20	2025-08-07
Muse Glimmerhigh	Meta	open	35.1	49	109	0.80s	131k	$0.30	$1.2	2026-08-10
Qwen3.5 27B	Alibaba	open	34.6	·	77	5.6s	262k	$0.26	$2.6	2026-02-24
GLM-4.7	Z AI	open	34.5	45.3	94	1.3s	200k	$0.60	$2.2	2025-12-22
MiniMax-M2.5	MiniMax	open	34.5	·	97	1.6s	205k	$0.30	$1.2	2026-02-12
Qwen3.5 397B A17B	Alibaba	open	34.3	48.2	89	2.2s	262k	$0.45	$3	2026-02-16
DeepSeek V3.2	DeepSeek	open	32.8	44.2	·	·	164k	$0.26	$0.38	2025-12-01
Qwen3.5 122B A10B	Alibaba	open	32.8	45.7	132	2.3s	262k	$0.29	$2.4	2026-02-24
Qwen3 Max Thinking	Alibaba	closed	32.5	·	·	·	256k	$1.2	$6	2026-01-26
MiniMax-M2.1	MiniMax	open	32.1	·	94	1.8s	205k	$0.30	$1.2	2025-12-23
Qwen3.6 35B A3B	Alibaba	open	32.1	41.9	125	2.0s	262k	$0.10	$0.95	2026-04-16
DeepSeek V3.1 Terminus	DeepSeek	open	31.4	43.5	·	·	131k	$0.27	$1	2025-09-22
o3	OpenAI	closed	31.1	·	109	6.2s	200k	$3.5	$14	2025-04-16
Step 3.7 Flash	StepFun	open	30.9	39.6	103	2.7s	262k	$0.20	$1.1	2026-05-29
Mistral Medium 3.5	Mistral	open	30.4	46.9	132	2.4s	262k	$1.5	$7.5	2026-04-29
Qwen3.5 35B A3B	Alibaba	open	29.9	·	152	2.0s	262k	$0.14	$1	2026-02-24
Gemma 4 31B	Google	open	29.7	43.4	35	1.1s	128k	$0.40	$0.60	2026-04-02
GLM-4.6	Z AI	open	29.3	45.8	50	2.5s	203k	$0.50	$2	2025-09-30
MiniMax-M2	MiniMax	open	28.9	·	97	1.6s	205k	$0.30	$1.2	2025-10-26
Gemini 3 Flash (Non-reasoning)	Google	closed	27.9	·	187	0.92s	1M	$0.50	$3	2025-12-17
Gemma 4 26B A4B	Google	open	26.1	39.3	·	·	262k	$0.07	$0.34	2026-04-02
o4-minihigh	OpenAI	closed	26.1	·	145	23s	200k	$2	$8	2025-04-16
Gemini 2.5 Pro	Google	closed	25.9	33.3	119	22s	1M	$1.3	$10	2025-06-05
GPT-5 minihigh	OpenAI	closed	25.8	15.6	108	73s	400k	$0.45	$3.6	2025-08-07
Nemotron 3 Super	NVIDIA	open	25.7	37.7	142	2.0s	262k	$0.09	$0.40	2026-03-11
Gemini 3.1 Flash-Lite	Google	closed	25.6	34.7	279	5.2s	1M	$0.25	$1.5	2026-03-03
Qwen3 Max	Alibaba	closed	24.5	·	43	2.4s	256k	$1.2	$6	2025-09-23
Claude 4.5 Haiku (Non-reasoning)	Anthropic	closed	24.1	·	83	0.73s	200k	$1	$5	2025-10-15
gpt-oss-120bhigh	OpenAI	open	24.1	30.4	150	0.85s	131k	$0.06	$0.40	2025-08-05
Kimi K2 0905	Kimi	open	24	·	40	1.2s	262k	$0.60	$2.5	2025-09-05
o1	OpenAI	closed	23.9	39.7	·	·	200k	$7.5	$30	2024-12-05
Nemotron 3.5 Lightning	NVIDIA	open	23.6	26.8	285	1.0s	262k	$0.08	$0.20	2026-08-11
GLM-4.7-Flash	Z AI	open	23.3	·	83	1.1s	203k	$0.06	$0.40	2026-01-19
Qwen3.5 9B	Alibaba	open	21.8	28.7	81	2.0s	262k	$0.10	$0.15	2026-03-02
Qwen3 Coder Next	Alibaba	open	21.3	36.2	129	1.1s	262k	$0.20	$1.5	2026-02-03
DeepSeek V3.1	DeepSeek	open	21	·	·	·	131k	$3	$4.5	2025-08-21
Qwen3 VL 235B A22B (Reasoning)	Alibaba	open	20.9	·	54	3.2s	131k	$0.98	$4.0	2025-09-23
DeepSeek R1 0528	DeepSeek	open	20.4	·	·	·	164k	$0.50	$2.1	2025-05-28
Gemini 2.5 Flash	Google	closed	20.3	·	221	19s	1M	$0.30	$2.5	2025-05-20
GPT-5 nanohigh	OpenAI	closed	20.1	·	146	95s	400k	$0.03	$0.20	2025-08-07
Qwen3 235B A22B 2507	Alibaba	open	19.9	22.1	72	2.7s	131k	$0.30	$3	2025-07-25
Mistral Small 4	Mistral	open	19.7	26.6	165	0.82s	262k	$0.15	$0.60	2026-03-16
GPT-4.1	OpenAI	closed	19.6	·	162	0.91s	1M	$3.5	$14	2025-04-14
Granite 4.2 8B	IBM	open	19.6	22.4	144	0.62s	131k	$0.06	$0.25	2026-08-25
o3-mini	OpenAI	closed	19.2	·	204	5.4s	200k	$0.55	$2.2	2025-01-31
Qwen3 Coder 480B	Alibaba	open	18.2	·	65	3.0s	262k	$1.5	$7.5	2025-07-22
GLM-4.6V	Z AI	open	16.9	·	55	3.7s	131k	$0.30	$0.90	2025-12-08
Qwen3 Next 80B A3B (Reasoning)	Alibaba	open	16.9	17.4	187	2.3s	262k	$0.15	$1.2	2025-09-11
GLM-4.5-Air	Z AI	open	16.7	·	83	2.6s	131k	$0.13	$0.85	2025-07-28
Mistral Large 3	Mistral	open	15.9	20.1	78	1.4s	262k	$0.50	$1.5	2025-12-02
gpt-oss-20bhigh	OpenAI	open	15.2	20.7	134	0.89s	131k	$0.03	$0.14	2025-08-05
GPT-4.1 mini	OpenAI	closed	14.8	20.2	79	0.93s	1M	$0.70	$2.8	2025-04-14
Qwen3 30B A3B 2507	Alibaba	open	14.6	12.1	144	2.3s	41k	$0.12	$0.50	2025-07-30
Llama 4 Maverick	Meta	open	14.5	16.3	85	0.91s	1M	$0.20	$0.80	2025-04-05
Nemotron 3 Nano	NVIDIA	open	14.5	14.4	224	1.2s	262k	$0.05	$0.20	2025-12-15
Qwen3 VL 235B A22B	Alibaba	open	14.4	·	52	2.7s	262k	$0.40	$1.6	2025-09-23
Qwen3 Coder 30B A3B	Alibaba	open	13.6	·	88	2.6s	160k	$0.07	$0.27	2025-07-31
Mistral Medium 3	Mistral	closed	12.5	·	132	2.3s	131k	$0.40	$2	2025-05-07
Qwen3 32B	Alibaba	open	11.4	15.3	105	2.5s	41k	$0.08	$0.28	2025-04-28
Ministral 3 14B	Mistral	open	11.2	14.4	95	0.88s	262k	$0.20	$0.20	2025-12-02
GPT-4o (Nov)	OpenAI	closed	11.1	·	117	1.1s	128k	$2.5	$10	2024-11-20
Qwen3 14B	Alibaba	open	10.4	13.8	62	2.8s	41k	$0.12	$0.24	2025-04-28
Llama 4 Scout	Meta	open	10.3	8.2	90	0.82s	328k	$0.10	$0.30	2025-04-05
Hermes 4 70B	Nous Research	open	9.9	·	82	1.4s	131k	$0.13	$0.40	2025-08-27
Qwen3 VL 30B A3B	Alibaba	open	9.9	·	113	2.2s	262k	$0.15	$0.60	2025-10-03
GPT-4.1 nano	OpenAI	closed	9.6	11.1	126	0.73s	1M	$0.20	$0.80	2025-04-14
GPT-4o (Aug)	OpenAI	closed	9.4	·	85	1.2s	128k	$2.5	$10	2024-08-06
Qwen2.5 72B	Alibaba	open	9.4	·	·	·	33k	$0.36	$0.40	2024-09-19
Llama 3.3 70B	Meta	open	9.3	11.9	85	1.7s	131k	$0.10	$0.32	2024-12-06
GLM-4.5V	Z AI	open	9	·	68	2.4s	66k	$0.60	$1.8	2025-08-11
Ministral 3 8B	Mistral	open	9	9.7	106	0.76s	262k	$0.15	$0.15	2025-12-02
Qwen3 30B A3B 2507 (Non-reasoning)	Alibaba	open	8.9	·	135	2.0s	262k	$0.05	$0.19	2025-07-29
Hermes 4 405B	Nous Research	open	8.8	·	43	2.5s	131k	$1	$3	2025-08-27
GPT-4o (May)	OpenAI	closed	8.4	24.2	74	1.2s	128k	$8.8	$26	2024-05-13
GPT-4o (ChatGPT)	OpenAI	closed	8.1	·	·	·	128k	$4.3	$17	2025-02-15
Command A	Cohere	open	7.5	·	57	1.6s	256k	$2.5	$10	2025-03-13
Gemma 3 27B	Google	open	7.4	10.1	·	·	131k	$0.08	$0.16	2025-03-12
Llama 3.1 8B	Meta	open	7.4	5.4	142	0.82s	16k	$0.02	$0.05	2024-07-23
Ministral 3 3B	Mistral	open	7.1	4.8	217	0.60s	131k	$0.10	$0.10	2025-12-02
GPT-4o mini	OpenAI	closed	6.7	11.4	129	0.84s	128k	$0.15	$0.60	2024-07-18
Mistral Small 3	Mistral	open	6.7	·	143	0.79s	33k	$0.05	$0.08	2025-01-30
Gemma 3 12B	Google	open	5.5	5.8	·	·	131k	$0.05	$0.15	2025-03-12
Hermes 3 - Llama-3.1 70B	Nous Research	open	4.8	·	35	2.0s	131k	$0.70	$0.70	2024-08-15
Phi-4	Microsoft	open	4.6	·	37	2.8s	16k	$0.07	$0.14	2024-12-12
Gemma 3 4B	Google	open	1	2.7	·	·	131k	$0.05	$0.10	2025-03-12
codestral-2508	mistral	·	·	·	·	·	256k	$0.30	$0.90	·
command-r-08-2024	cohere	·	·	·	·	·	128k	$0.15	$0.60	·
command-r-plus-08-2024	cohere	·	·	·	·	·	128k	$2.5	$10	·
command-r7b-12-2024	cohere	·	·	·	·	·	128k	$0.04	$0.15	·
ernie-4.5-vl-424b-a47b	novita	·	·	·	·	·	123k	$0.42	$1.3	·
grok-build-0.1	xai	·	·	·	·	·	256k	$1	$2	·
hermes-3-llama-3.1-405b	deepinfra	·	·	·	·	·	131k	$1	$1	·
llama-guard-4-12b	deepinfra	·	·	·	·	·	164k	$0.18	$0.18	·
mistral-nemo	novita	·	·	·	·	·	60k	$0.04	$0.17	·
mythomax-l2-13b	deepinfra	·	·	·	·	·	4k	$0.40	$0.40	·
Seed 2.0 Code	deepinfra	·	·	·	·	·	256k	$0.50	$3	·
Seed 2.0 Mini	deepinfra	·	·	·	·	·	256k	$0.10	$0.40	·
Seed 2.0 Pro	deepinfra	·	·	·	·	·	256k	$0.50	$3	·
wizardlm-2-8x22b	novita	·	·	·	·	·	66k	$0.62	$0.62	·

10·local catalog

26 models

Local models

Every model conifer models pull can install; on disk is the size of the Q4_K_M file.


Gemma 4 E2B IT	Google	4.6B	3.1 GB	128k	2026-03-31	reasoning · tools
Gemma 4 E4B IT	Google	7.5B	5.0 GB	128k	2026-03-31	reasoning · tools
Gemma 4 12B IT	Google	12B	7.1 GB	256k	2026-06-03	reasoning · tools
Gemma 4 31B IT	Google	31B	18.3 GB	256k	2026-03-31	reasoning · tools
Granite-Docling 258M	IBM	0.16B	0.33 GB	8k	2025-09-17	vision
Granite 4.0 Micro 3B	IBM	3.4B	2.1 GB	128k	2025-10-02	coding · reasoning · tools
Granite 4.1 3B	IBM	3.4B	2.1 GB	128k	2026-04-16	coding · reasoning · tools
Granite 4.0 H Tiny 7B A1B	IBM	6.9B · 1B active	4.2 GB	1M	2025-10-02	coding · MoE · reasoning · tools
Granite 4.0 H Small 32B A9B	IBM	32B · 9B active	19.5 GB	1M	2025-10-02	coding · MoE · reasoning · tools
LFM2.5 230M	Liquid AI	0.23B	0.15 GB	125k	2026-06-25	tools
LFM2.5 350M	Liquid AI	0.35B	0.23 GB	125k	2026-03-25	tools
LFM2-VL 1.6B	Liquid AI	1.2B	0.70 GB	125k	2025-08-12	tools · vision
LFM2.5 1.2B Instruct	Liquid AI	1.2B	0.73 GB	125k	2026-01-05	tools
LFM2.5 1.2B Thinking	Liquid AI	1.2B	0.73 GB	125k	2026-01-20	reasoning · tools
LFM2.5-VL 1.6B	Liquid AI	1.2B	0.73 GB	125k	2026-01-05	tools · vision
LFM2.5 8B A1B	Liquid AI	8.5B · 1B active	5.2 GB	125k	2026-05-28	MoE · reasoning · tools
Ministral 3 3B Instruct 2512	Mistral AI	3.4B	2.1 GB	256k	2025-12-02	tools
Mistral Small 3.2 24B Instruct 2506	Mistral AI	24B	14.3 GB	128k	2025-06-20	tools · vision
Hermes 4 14B	Nous Research	15B	9.0 GB	40k	2025-09-03	coding · reasoning · tools
Qwen 3.5 0.8B	Alibaba	0.75B	0.53 GB	256k	2026-03-01	reasoning · tools
Qwen3-VL 4B Instruct	Alibaba	4B	2.5 GB	256k	2025-10-11	tools · vision
Qwen 3.5 4B	Alibaba	4.2B	2.7 GB	256k	2026-03-02	coding · reasoning · tools
Qwen 3.5 9B	Alibaba	9B	5.7 GB	256k	2026-02-28	coding · reasoning · tools
Qwen 3.5 27B	Alibaba	27B	16.7 GB	256k	2026-02-24	coding · reasoning · tools
Qwen 3.6 27B	Alibaba	27B	16.8 GB	256k	2026-04-22	coding · reasoning · tools
Qwen 3.8 27B	Alibaba	27B	17.1 GB	128k	2026-08-14	coding · reasoning · tools