Provider Pricing Index

AI model & agent cost comparison

Every priced model across 137 providers, normalized to USD per 1M tokens, with quality scored by Artificial Analysis. Start from your workload, explore the full catalog on a price map, and pin models side by side — token costs kept separate from subscriptions and agent software.

Prices: models.dev Benchmarks: Artificial Analysis

Providers

137

Models priced

4,743

Cheapest lab (blended)

$0.040

Ministral 3B (latest)

Official sources

137/137

Updated

Jun 1, 2026, 10:56 AM

Step 1 · Start from your workload

What are you building?

Quality from Artificial Analysis Coding Index

Monthly volume8K calls

256M input + 48M output tokens / month
32,000 in / 6,000 out per call

Best value for coding agent

Step 3.5 Flashbest value

StepFun (China) · ctx 256K

31.6

Coding

$38.40

/ month

MiMo-V2-Flash

Xiaomi · ctx 262K

33.5

Coding

$40.00

/ month

DeepSeek V4 Flash

DeepSeek · ctx 1M

39.8

Coding

$49.28

/ month

DeepSeek V3.2 Exp

Alibaba (China) · ctx 131K

36.7

Coding

$94.16

/ month

Mercury 2

Inception · ctx 128K

30.6

Coding

/ month

GPT-5.4 nano

OpenAI · ctx 400K

43.9

Coding

/ month

Coding Index from Artificial Analysis. Cost is API tokens only — excludes subscriptions, caching, and agent software.

Step 2 · Explore the full catalog

Price explorer

max blended $200

.40

1.00

80.00Input $/1M tokens (log)Output $/1M (log)

lab reseller pinnedbubble = context window

394 models match@workload column = monthly API cost for Coding agent

						Capabilities
DeepSeek R1 Distill Llama 8BAA 12 deepseek-r1-distill-llama-8b	Alibaba (China)	$0	$0	33K	$0.000	ReasoningTools
DeepSeek R1 Distill Qwen 1.5BAA 9 deepseek-r1-distill-qwen-1-5b	Alibaba (China)	$0	$0	33K	$0.000	ReasoningTools
Cerebras-Llama-4-Maverick-17B-128E-Instruct cerebras-llama-4-maverick-17b-128e-instruct	Llama	$0	$0	128K	$0.000	ToolsOpen
Cerebras-Llama-4-Scout-17B-16E-Instruct cerebras-llama-4-scout-17b-16e-instruct	Llama	$0	$0	128K	$0.000	ToolsOpen
Groq-Llama-4-Maverick-17B-128E-Instruct groq-llama-4-maverick-17b-128e-instruct	Llama	$0	$0	128K	$0.000	ToolsOpen
Llama-3.3-70B-InstructAA 15 llama-3.3-70b-instruct	Llama	$0	$0	128K	$0.000	ToolsOpen
Llama-3.3-8B-Instruct llama-3.3-8b-instruct	Llama	$0	$0	128K	$0.000	ToolsOpen
Llama-4-Maverick-17B-128E-Instruct-FP8 llama-4-maverick-17b-128e-instruct-fp8	Llama	$0	$0	128K	$0.000	ToolsVisionOpen
Llama-4-Scout-17B-16E-Instruct-FP8 llama-4-scout-17b-16e-instruct-fp8	Llama	$0	$0	128K	$0.000	ToolsVisionOpen
Devstral Small 2AA 20 labs-devstral-small-2512	Mistral	$0	$0	256K	$0.000	ToolsVisionOpen
Hy3 previewAA 42 hy3-preview	Tencent TokenHub	$0	$0	256K	$0.000	ReasoningToolsOpen
GLM-4.5-Flash glm-4.5-flash	Z.AI	$0	$0	131K	$0.000	ReasoningToolsOpen
GLM-4.7-FlashAA 30 glm-4.7-flash	Z.AI	$0	$0	200K	$0.000	ReasoningToolsOpen
GLM-4.5-Flash glm-4.5-flash	Zhipu AI	$0	$0	131K	$0.000	ReasoningToolsOpen
GLM-4.7-FlashAA 30 glm-4.7-flash	Zhipu AI	$0	$0	200K	$0.000	ReasoningToolsOpen
text-embedding-3-small text-embedding-3-small	OpenAI	$0.020	$0	8K	$5.12	—
Qwen3-ASR Flash qwen3-asr-flash	Alibaba (China)	$0.032	$0.032	53K	$9.73	—
Qwen3-ASR Flash qwen3-asr-flash	Alibaba	$0.035	$0.035	53K	0.64	—
Ministral 3B (latest) ministral-3b-latest	Mistral	$0.040	$0.040	128K	2.16	ToolsOpen
Qwen Turbo qwen-turbo	Alibaba (China)	$0.044	$0.087	1M	5.44	ReasoningTools
Mistral Embed mistral-embed	Mistral	$0.100	$0	8K	5.60	—
text-embedding-ada-002 text-embedding-ada-002	OpenAI	$0.100	$0	8K	5.60	—
Command R7B command-r7b-12-2024	Cohere	$0.037	$0.150	128K	6.80	ToolsOpen
Command R7B Arabic command-r7b-arabic-02-2025	Cohere	$0.037	$0.150	128K	6.80	ToolsOpen
Qwen Flash qwen-flash	Alibaba (China)	$0.022	$0.216	1M	6.00	ReasoningTools
Tongyi Intent Detect V3 tongyi-intent-detect-v3	Alibaba (China)	$0.058	$0.144	8K	1.76	—
text-embedding-3-large text-embedding-3-large	OpenAI	$0.130	$0	8K	$33.28	—
DeepSeek R1 Distill Qwen 7B deepseek-r1-distill-qwen-7b	Alibaba (China)	$0.072	$0.144	33K	5.34	ReasoningTools
Qwen2.5 7B Instruct qwen2-5-7b-instruct	Alibaba (China)	$0.072	$0.144	131K	5.34	ToolsOpen
Qwen Turbo qwen-turbo	Alibaba	$0.050	$0.200	1M	2.40	ReasoningTools
Ministral 8B (latest) ministral-8b-latest	Mistral	$0.100	$0.100	128K	$30.40	ToolsOpen
Qwen Doc Turbo qwen-doc-turbo	Alibaba (China)	$0.087	$0.144	131K	9.18	Tools
Gemini Embedding 001 gemini-embedding-001	Google	$0.150	$0	2K	$38.40	—
Gemini Embedding 001 gemini-embedding-001	Vertex	$0.150	$0	2K	$38.40	—
Qwen-Omni Turbo qwen-omni-turbo	Alibaba (China)	$0.058	$0.230	33K	5.89	ToolsVision
Qwen3-Omni Flash qwen3-omni-flash	Alibaba (China)	$0.058	$0.230	66K	5.89	ReasoningToolsVision
GPT OSS 20BAA 25 openai/gpt-oss-20b-maas	Vertex	$0.070	$0.250	131K	9.92	ReasoningToolsOpen
Qwen-Omni Turbo qwen-omni-turbo	Alibaba	$0.070	$0.270	33K	$30.88	ToolsVision
Qwen Long qwen-long	Alibaba (China)	$0.072	$0.287	10M	$32.21	Tools
Qwen3 8BAA 13 qwen3-8b	Alibaba (China)	$0.072	$0.287	131K	$32.21	ReasoningToolsOpen
Gemini 2.0 Flash-LiteAA 15 gemini-2.0-flash-lite	Google	$0.075	$0.300	1M	$33.60	ToolsVision
Gemini 2.0 Flash-LiteAA 15 gemini-2.0-flash-lite	Vertex	$0.075	$0.300	1M	$33.60	ToolsVision
Mistral Nemo mistral-nemo	Mistral	$0.150	$0.150	128K	$45.60	ToolsOpen
Pixtral 12B pixtral-12b	Mistral	$0.150	$0.150	128K	$45.60	ToolsVisionOpen
solar-miniAA 12 solar-mini	Upstage	$0.150	$0.150	33K	$45.60	Tools
Step 3.5 FlashAA 38 step-3.5-flash	StepFun (China)	$0.096	$0.288	256K	$38.40	ReasoningToolsOpen
Step 3.5 FlashAA 38 step-3.5-flash	StepFun	$0.096	$0.288	256K	$38.40	ReasoningToolsOpen
Qwen-MT Turbo qwen-mt-turbo	Alibaba (China)	$0.101	$0.280	16K	$39.30	—
Qwen Flash qwen-flash	Alibaba	$0.050	$0.400	1M	$32.00	ReasoningTools
GPT-5 NanoAA 27 gpt-5-nano	OpenAI	$0.050	$0.400	400K	$32.00	ReasoningToolsVision
Devstral Small 2505 devstral-small-2505	Mistral	$0.100	$0.300	128K	$40.00	ToolsOpen
Devstral SmallAA 18 devstral-small-2507	Mistral	$0.100	$0.300	128K	$40.00	ToolsOpen
Mistral Small 3.2AA 15 mistral-small-2506	Mistral	$0.100	$0.300	128K	$40.00	ToolsVisionOpen
Step 3.5 Flash 2603AA 39 step-3.5-flash-2603	StepFun (China)	$0.100	$0.300	256K	$40.00	ReasoningToolsOpen
Step 3.5 Flash 2603AA 39 step-3.5-flash-2603	StepFun	$0.100	$0.300	256K	$40.00	ReasoningToolsOpen
MiMo-V2-FlashAA 42 mimo-v2-flash	Xiaomi	$0.100	$0.300	262K	$40.00	ReasoningToolsOpen
Qwen2.5-Omni 7B qwen2-5-omni-7b	Alibaba (China)	$0.087	$0.345	33K	$38.83	ToolsVisionOpen
Qwen Plus qwen-plus	Alibaba (China)	$0.115	$0.287	1M	$43.22	ReasoningTools
Qwen Plus Character qwen-plus-character	Alibaba (China)	$0.115	$0.287	33K	$43.22	Tools
Qwen-VL Plus qwen-vl-plus	Alibaba (China)	$0.115	$0.287	131K	$43.22	ToolsVision

Sources & full catalog

the underlying evidence, kept separate from the live tools above

Official-page prices — graded & tracked

Token prices read from providers' own pages, each carrying a confidence grade, hidden-cost flags, and a change history. 285 of 296 rows are grade A/A+ (official sources).

296 priced rows

Provider	Model	Confidence	Input	Cached	Output	Context	Source
Fireworks (Firepass)	Kimi K2.6 Turbofree Free tier	A	$0	$0	$0	256K	source
OpenCode Zen	MiniMax M3 Freefree Free tier	A	$0	$0	$0	200K	source
routing.run	route/deepseek-v3.2free Free tier	D	$0	$0	$0	163K	source
SiliconFlow (China)	PaddlePaddle/PaddleOCR-VL-1.5free No cache priceFree tier	A+	$0	—	$0	—	source
Z.AI	GLM-4.7-Flashfree Free tier	A	$0	$0	$0	—	source
Z.AI	GLM-4.5-Flashfree Free tier	A	$0	$0	$0	—	source
Z.AI	GLM-4.6V-Flashfree Free tier	A	$0	$0	$0	—	source
DeepSeek	deepseek-v4-flash	A+	$0.0028	$0.0028	$0.280	1M	source
DeepSeek	deepseek-v4-pro	A+	$0.0036	$0.015	$0.870	1M	source
Together AI	Juggernaut Pro Flux No cache price	A+	$0.0049	—	—	—	source
Fireworks AI	Base Embeddings	A+	$0.0080	$0.0040	—	150M	source
Vultr	nvidia/Llama-3.1-Nemotron-Safety-Guard-8B-v3 No cache price	A+	$0.010	—	$0.010	—	source
xAI	Voice API - TTS No cache price	A+	$0.015	—	—	—	source
Fireworks AI	Base Embeddings	A+	$0.016	$0.0080	—	150M	source
Together AI	Gemma 4 31B No cache price	A+	$0.018	—	—	—	source
NovitaAI	Llama 3.1 8B Instruct No cache price	A+	$0.020	—	$0.050	16K	source
Together AI	Multilingual e5 large instruct No cache price	A+	$0.020	—	—	—	source
xAI	Imagine API - Image No cache price	A+	$0.020	—	—	—	source
Cloudflare Workers AI	@cf/meta/llama-3.2-1b-instruct No cache price	A+	$0.027	—	$0.201	—	source
Inference	Schematron V2 Turbo No cache price	C	$0.030	—	$0.150	125K	source
NovitaAI	DeepSeek-OCR 2 No cache price	A+	$0.030	—	$0.030	8K	source
Z.AI	GLM-OCR No cache price	A	$0.030	—	$0.030	—	source
Amazon Bedrock	gpt-oss-20b (OpenAI)	A+	$0.036	$0.036	$0.154	—	source
NovitaAI	OpenAI GPT OSS 20B No cache price	A+	$0.040	—	$0.150	131K	source
Z.AI	GLM-4.6V-FlashX	A	$0.040	$0.0040	$0.400	—	source
Cloudflare Workers AI	@cf/meta/llama-3.1-8b-instruct-fp8-fast No cache price	A+	$0.045	—	$0.384	—	source
Cloudflare Workers AI	@cf/meta/llama-3.2-11b-vision-instruct No cache price	A+	$0.049	—	$0.676	—	source
Groq	Llama 3.1 8B Instant 128k No cache price	A+	$0.050	—	$0.080	128K	source
Inference	Schematron V2 Small No cache price	C	$0.050	—	$0.250	125K	source
NovitaAI	Sao10k L3 8B Lunaris No cache price	A+	$0.050	—	$0.050	8K	source
NovitaAI	L3 8B Stheno V3.2 No cache price	A+	$0.050	—	$0.050	8K	source
NovitaAI	OpenAI GPT OSS 120B No cache price	A+	$0.050	—	$0.250	131K	source
Cloudflare Workers AI	@cf/meta/llama-3.2-3b-instruct No cache price	A+	$0.051	—	$0.335	—	source
SiliconFlow	Qwen/Qwen3.6-35B-A3B (0-128k tokens) No cache price	A+	$0.060	—	$0.480	—	source
SiliconFlow (China)	Qwen/Qwen3.6-35B-A3B (0-128k tokens) No cache price	A+	$0.060	—	$0.480	—	source
Z.AI	GLM-4.7-FlashX	A	$0.070	$0.010	$0.400	—	source
Zhipu AI	GLM-4.7-FlashX	A	$0.070	$0.010	$0.400	—	source
Alibaba (China)	qwen3-8b No cache price	A	$0.072	—	$0.287	129K	source
Groq	GPT OSS 20B 128k	A+	$0.075	$0.037	$0.300	128K	source
Groq	GPT OSS Safeguard 20B	A+	$0.075	$0.037	$0.300	128K	source
Groq	openai/gpt-oss-20b	A+	$0.075	$0.037	$0.300	—	source
Amazon Bedrock	gpt-oss-120b (OpenAI)	A+	$0.077	$0.077	$0.309	—	source
Amazon Bedrock	GPT OSS Safeguard 20B (Europe – Ireland/Milan)	A+	$0.080	$0.080	$0.240	—	source
Alibaba (China)	qwen-mt-lite (Global) No cache price	A	$0.086	—	$0.229	16K	source
Amazon Bedrock	gpt-oss-20b (OpenAI) – Training hour price	A+	$0.090	$0.090	$0.390	—	source
Deep Infra	Qwen3-Next-80B-A3B-Instruct	A+	$0.090	$0.090	.10	256	source
Alibaba	Qwen3.5-Flash No cache price	A	$0.100	—	$0.210	1M	source
Baseten	GPT OSS 120B No cache price	A+	$0.100	—	$0.500	—	source
Deep Infra	DeepSeek-V4-Flash	A+	$0.100	$0.100	$0.200	1K	source
Fireworks AI	Qwen3 8B	A+	$0.100	$0.050	—	—	source
Friendli	Llama-3.1-8B-Instruct No cache price	A+	$0.100	—	—	—	source
Together AI	Llama 3 8B Instruct Lite No cache price	A+	$0.100	—	$0.100	—	source
Together AI	Qwen3.5 9B No cache price	A+	$0.100	—	$0.150	—	source
Z.AI	GLM-4-32B-0414-128K No cache price	A	$0.100	—	$0.100	—	source
Zhipu AI	GLM-4-32B-0414-128K No cache price	A	$0.100	—	$0.100	—	source
Alibaba (China)	qwen-mt-flash (Global) No cache price	A	$0.101	—	$0.280	16K	source
Alibaba (China)	qwen3-30b-a3b-thinking-2507 No cache price	A	$0.108	—	.08	127K	source
Amazon Bedrock	GPT OSS Safeguard 20B (Europe – London)	A+	$0.110	$0.110	$0.310	—	source
Cloudflare Workers AI	@cf/mistral/mistral-7b-instruct-v0.1 No cache price	A+	$0.110	—	$0.190	—	source
Groq	Llama 4 Scout (17Bx16E) 128k No cache price	A+	$0.110	—	$0.340	128K	source
SiliconFlow	stepfun-ai/Step-3.5-Flash No cache price	A+	$0.110	—	$0.330	—	source
NovitaAI	Gemma 3 27B No cache price	A+	$0.119	—	$0.200	98K	source
Alibaba	qwen-mt-lite No cache price	A	$0.120	—	$0.360	—	source
Alibaba (China)	qwen-mt-lite No cache price	A	$0.120	—	$0.360	—	source
Vertex	Gemini 3.1 Flash-Lite	A+	$0.125	$0.013	—	—	source
NovitaAI	zai-org/glm-4.5-air	A+	$0.130	$0.025	$0.850	131K	source
Vultr	nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16 No cache price	A+	$0.130	—	$0.380	—	source
Friendli	gemma-4-31B-it No cache price	A+	$0.140	—	$0.400	—	source
NovitaAI	Deepseek V4 Flash	A+	$0.140	$0.028	$0.280	1M	source
NovitaAI	Kimi K2.6 No cache price	A+	$0.140	—	$0.400	262K	source
SiliconFlow	deepseek-ai/DeepSeek-V4-Flash	A+	$0.140	$0.0030	$0.290	—	source
SiliconFlow	zai-org/GLM-4.5V No cache price	A+	$0.140	—	$0.860	—	source
SiliconFlow	tencent/Hunyuan-A13B-Instruct No cache price	A+	$0.140	—	$0.570	—	source
Alibaba (China)	qwen3-next-80b-a3b-thinking No cache price	A	$0.144	—	.43	131K	source
Alibaba (China)	qwen3-14b No cache price	A	$0.144	—	$0.574	129K	source
Deep Infra	Qwen3-VL-30B-A3B-Instruct	A+	$0.150	$0.150	$0.600	256	source
Groq	GPT OSS 120B 128k	A+	$0.150	$0.075	$0.600	128K	source
Groq	openai/gpt-oss-120b	A+	$0.150	$0.075	$0.600	—	source
Vivgrid	deepseek-v4-flash	A	$0.150	$0.030	$0.280	1M	source
Vultr	nvidia/Nemotron-Cascade-2-30B-A3B No cache price	A+	$0.150	—	$0.600	—	source
Vultr	moonshotai/Kimi-K2.6 No cache price	A+	$0.150	—	$0.600	—	source
Amazon Bedrock	Qwen3 Coder 30B A3B (Asia Pacific – Sydney)	A+	$0.154	$0.154	$0.618	—	source
Amazon Bedrock	Qwen3 32B (Asia Pacific – Sydney)	A+	$0.154	$0.154	$0.618	—	source
Alibaba	qwen-mt-flash No cache price	A	$0.160	—	$0.490	—	source
Alibaba (China)	qwen-mt-flash No cache price	A	$0.160	—	$0.490	—	source
Alibaba (China)	qwen-mt-turbo No cache price	A	$0.160	—	$0.490	—	source
Alibaba (China)	qwen3-32b No cache price	A	$0.160	—	$0.640	129K	source
Amazon Bedrock	GPT OSS Safeguard 120B (Europe – Ireland/Milan)	A+	$0.180	$0.180	$0.710	—	source
Amazon Bedrock	Qwen3 Next 80B A3B (South America – Sao Paulo / Asia Pacific – Tokyo)	A+	$0.180	$0.180	.45	—	source
Deep Infra	DeepSeek-V3-0324	A+	$0.200	$0.200	$0.770	160	source
Deep Infra	Qwen3-VL-235B-A22B-Instruct	A+	$0.200	$0.200	$0.880	256	source
Friendli	Qwen3-235B-A22B-Instruct-2507 No cache price	A+	$0.200	—	$0.800	—	source
Friendli	K-EXAONE-236B-A23B	A+	$0.200	$0.100	$0.800	—	source
OpenAI	gpt-5.4-nano	A+	$0.200	$0.020	.25	—	source
Together AI	Qwen3 235B A22B Instruct 2507 FP8 Throughput No cache price	A+	$0.200	—	$0.600	—	source
Together AI	Llama Guard 4 12B No cache price	A+	$0.200	—	—	—	source
Vivgrid	gpt-5.4-nano	A	$0.200	$0.020	.25	400K	source
Z.AI	GLM-4.5-Air	A	$0.200	$0.030	.10	—	source
Zhipu AI	GLM-4.5-Air	A	$0.200	$0.030	.10	—	source
Deep Infra	DeepSeek-V3.1	A+	$0.210	$0.210	$0.790	160	source
Amazon Bedrock	Qwen3 235B A22B 2507 (Asia Pacific – Sydney)	A+	$0.227	$0.227	$0.906	—	source
Alibaba (China)	qwen3-235b-a22b-thinking-2507 No cache price	A	$0.230	—	.30	127K	source
Amazon Bedrock	GPT OSS Safeguard 120B (Europe – London)	A+	$0.230	$0.230	$0.930	—	source
SiliconFlow	Qwen/Qwen3.6-35B-A3B (128k-256k tokens) No cache price	A+	$0.240	—	.92	—	source
SiliconFlow (China)	Qwen/Qwen3.6-35B-A3B (128k-256k tokens) No cache price	A+	$0.240	—	.92	—	source
Deep Infra	gemini-3.1-flash-lite	A+	$0.250	$0.250	.50	976	source
Vertex	Gemini 3 Flash Preview No cache price	A+	$0.250	—	.50	—	source
Perplexity Agent	perplexity/sonar	A	$0.250	$0.063	.50	—	source
Vivgrid	gemini-3.1-flash-lite-preview No cache price	A	$0.250	—	.50	1M	source
Vivgrid	gpt-5-mini	A	$0.250	$0.030	.00	272K	source
Alibaba	qwen-mt-plus No cache price	A	$0.259	—	$0.775	16K	source
Alibaba (China)	qwen-mt-plus (Global) No cache price	A	$0.259	—	$0.775	16K	source
Deep Infra	DeepSeek-V3.2	A+	$0.260	$0.260	$0.380	160	source
NovitaAI	Deepseek V3.2	A+	$0.269	$0.135	$0.400	164K	source
Deep Infra	DeepSeek-V3.1-Terminus	A+	$0.270	$0.270	$0.950	160	source
Alibaba (China)	qwen3-235b-a22b No cache price	A	$0.287	—	.15	129K	source
Groq	Qwen3 32B 131k No cache price	A+	$0.290	—	$0.590	131K	source
SiliconFlow	deepseek-ai/DeepSeek-V3.2	A+	$0.290	$0.029	$0.430	—	source
Cloudflare Workers AI	@cf/meta/llama-3.1-70b-instruct-fp8-fast No cache price	A+	$0.293	—	.25	—	source
Cloudflare Workers AI	@cf/meta/llama-3.3-70b-instruct-fp8-fast No cache price	A+	$0.293	—	.25	—	source
Baseten	NVIDIA Nemotron 3 Super	A+	$0.300	$0.060	$0.750	—	source
Baseten	MiniMax M2.5	A+	$0.300	$0.060	.20	—	source
Cohere	Command-light No cache price	A+	$0.300	—	$0.600	—	source
Deep Infra	Qwen3-Coder-480B-A35B-Instruct-Turbo	A+	$0.300	$0.300	.00	256	source
Deep Infra	gemini-2.5-flash	A+	$0.300	$0.300	.50	976	source
Friendli	MiniMax-M2.5	A+	$0.300	$0.060	.20	—	source
Inference	ClipTagger 12B No cache price	C	$0.300	—	$0.500	8K	source
MiniMax (minimax.io)	MiniMax-M3	A+	$0.300	$0.060	.20	1M	source
MiniMax (minimaxi.com)	MiniMax-M3	A+	$0.300	$0.060	.20	1M	source
NovitaAI	MiniMax M2.7	A+	$0.300	$0.060	.20	205K	source
NovitaAI	MiniMax M2.5	A+	$0.300	$0.030	.20	205K	source
NovitaAI	Minimax M2.1	A+	$0.300	$0.030	.20	205K	source
NovitaAI	MiniMax-M2	A+	$0.300	$0.030	.20	205K	source
NovitaAI	Kat Coder Pro	A+	$0.300	$0.060	.20	256K	source
OpenRouter	MiniMax: MiniMax M3	A+	$0.300	$0.060	.20	1M	source
SiliconFlow	MiniMaxAI/MiniMax-M2.5	A+	$0.300	$0.030	.20	—	source
SiliconFlow (China)	MiniMaxAI/MiniMax-M2.5	A+	$0.300	$0.030	.20	—	source
Together AI	MiniMax M2.7	A+	$0.300	$0.060	.20	—	source
Vercel AI Gateway	MiniMax M3	A+	$0.300	$0.060	.20	1M	source
Vivgrid	minimax-m2.7	A	$0.300	$0.060	.20	205K	source
Vultr	Qwen/Qwen3.5-397B-A17B-FP8 No cache price	A+	$0.300	—	.20	—	source
Vultr	MiniMaxAI/MiniMax-M2.7 No cache price	A+	$0.300	—	.20	—	source
Z.AI	GLM-4.6V	A	$0.300	$0.050	$0.900	—	source
Amazon Bedrock	Minimax M2 (Asia Pacific – Sydney)	A+	$0.309	$0.309	.24	—	source
Amazon Bedrock	Minimax M2.1 (Asia Pacific – Sydney)	A+	$0.309	$0.309	.24	—	source
Amazon Bedrock	Minimax M2.5 (Asia Pacific – Sydney)	A+	$0.310	$0.310	.24	—	source
Deep Infra	DeepSeek-V3	A+	$0.320	$0.320	$0.890	160	source
Cloudflare Workers AI	@cf/mistralai/mistral-small-3.1-24b-instruct No cache price	A+	$0.351	—	$0.555	—	source
Amazon Bedrock	Minimax M2	A+	$0.360	$0.360	.45	—	source
Amazon Bedrock	Minimax M2.1	A+	$0.360	$0.360	.44	—	source
Amazon Bedrock	Minimax M2.5	A+	$0.360	$0.360	.44	—	source
Alibaba	Qwen3.5-Plus No cache price	A	$0.400	—	$0.630	1M	source
SiliconFlow	deepseek-ai/DeepSeek-V4-Pro	A+	$0.430	$0.0043	$0.860	—	source
SiliconFlow (China)	deepseek-ai/DeepSeek-V4-Pro	A+	$0.430	$0.0043	$0.860	—	source
MiniMax (minimax.io)	MiniMax-M3 (Priority) Enterprise-only	A+	$0.450	$0.090	.80	1M	source
MiniMax (minimaxi.com)	MiniMax-M3 (Priority) Enterprise-only	A+	$0.450	$0.090	.80	1M	source
Amazon Bedrock	Minimax M2 (Europe – London)	A+	$0.470	$0.470	.86	—	source
Amazon Bedrock	Minimax M2.1 (Europe – London)	A+	$0.470	$0.470	.86	—	source
Amazon Bedrock	Minimax M2.5 (Europe – London)	A+	$0.470	$0.470	.86	—	source
Cloudflare Workers AI	@cf/deepseek-ai/deepseek-r1-distill-qwen-32b No cache price	A+	$0.497	—	$4.88	—	source
Baseten	DeepSeek V3.1	A+	$0.500	$0.250	.50	—	source
Cohere	Command R 03-2024 No cache price	A+	$0.500	—	.50	—	source
Cohere	Aya Expanse (8B and 32B) No cache price	A+	$0.500	—	.50	—	source
Deep Infra	DeepSeek-R1-0528	A+	$0.500	$0.500	.15	160	source
Friendli	DeepSeek-V3.2	A+	$0.500	$0.250	.50	—	source
Vertex	Gemini 3.1 Flash No cache price	A+	$0.500	—	$3.00	—	source
Together AI	Qwen3.6-Plus No cache price	A+	$0.500	—	$3.00	—	source
Vivgrid	gemini-3-flash-preview	A	$0.500	$0.0050	$3.00	1M	source
NovitaAI	MiniMax M1 No cache price	A+	$0.550	—	.20	1M	source
Vultr	nvidia/DeepSeek-V3.2-NVFP4 No cache price	A+	$0.550	—	.65	—	source
Vultr	deepseek-ai/DeepSeek-V4-Pro No cache price	A+	$0.550	—	.65	—	source
Groq	Llama 3.3 70B Versatile 128k No cache price	A+	$0.590	—	$0.790	128K	source
Amazon Bedrock	Qwen3 Coder Next (South America – Sao Paulo / Asia Pacific – Tokyo)	A+	$0.600	$0.600	.44	—	source
Baseten	Kimi K2.5	A+	$0.600	$0.120	$3.00	—	source
Baseten	GLM 4.7	A+	$0.600	$0.120	.20	—	source
Friendli	Llama-3.3-70B-Instruct No cache price	A+	$0.600	—	—	—	source
Friendli	Kimi-K2.5 No cache price	A+	$0.600	—	$3.00	—	source
NovitaAI	MiniMax M2.5-highspeed	A+	$0.600	$0.030	.40	205K	source
OpenCode Go	MiniMax M3	A	$0.600	$0.120	.40	512K	source
Z.AI	GLM-4.7	A	$0.600	$0.110	.20	—	source
Z.AI	GLM-4.6	A	$0.600	$0.110	.20	—	source
Z.AI	GLM-4.5	A	$0.600	$0.110	.20	—	source
Z.AI	GLM-4.5V	A	$0.600	$0.110	.80	—	source
Zhipu AI	GLM-4.7	A	$0.600	$0.110	.20	—	source
Zhipu AI	GLM-4.6	A	$0.600	$0.110	.20	—	source
Zhipu AI	GLM-4.5	A	$0.600	$0.110	.20	—	source
Amazon Bedrock	Qwen3 VL 235B A22B (South America – Sao Paulo / Asia Pacific – Tokyo)	A+	$0.640	$0.640	$3.22	—	source
Vertex	Gemini 3.5 Flash Flex/Batch	A+	$0.750	$0.075	$4.50	—	source
OpenAI	gpt-5.4-mini	A+	$0.750	$0.075	$4.50	—	source
Vivgrid	gpt-5.4-mini	A	$0.750	$0.080	$4.50	400K	source
Vultr	zai-org/GLM-5.1-FP8 No cache price	A+	$0.850	—	$3.10	—	source
SiliconFlow	Pro/zai-org/GLM-5.1 (0-32k tokens)	A+	$0.860	$0.190	$3.43	—	source
SiliconFlow (China)	Pro/zai-org/GLM-5.1 (0-32k tokens)	A+	$0.860	$0.190	$3.44	—	source
SiliconFlow	Pro/moonshotai/Kimi-K2.6	A+	$0.930	$0.160	$3.86	—	source
SiliconFlow (China)	Pro/moonshotai/Kimi-K2.6	A+	$0.930	$0.160	$3.86	—	source
Baseten	Kimi K2.6	A+	$0.950	$0.160	$4.00	—	source
Baseten	GLM 5	A+	$0.950	$0.200	$3.15	—	source
Anthropic	Claude Haiku 4.5 No cache price	A+	.00	—	$5.00	—	source
Cohere	Command No cache priceMay be deprecated	A+	.00	—	.00	—	source
Friendli	GLM-5	A+	.00	$0.500	$3.20	—	source
Vertex	Gemini 3.1 Pro Preview Flex/Batch No cache price	A+	.00	—	$6.00	—	source
Vertex	Gemini 2.0 Flash Lite	A+	.00	$0.019	—	—	source
Groq	moonshotai/kimi-k2-instruct-0905	A+	.00	$0.500	$3.00	—	source
Perplexity	Sonar No cache price	A+	.00	—	.00	—	source
v0	v0 Mini	A+	.00	$0.100	$5.00	—	source
Vivgrid	kimi-k2.6	A	.00	$0.200	$4.00	256K	source
Vivgrid	claude-haiku-4.5	A	.00	$0.100	$5.00	200K	source
xAI	Grok Build 0.1 No cache price	A+	.00	—	.00	256K	source
Z.AI	GLM-5	A	.00	$0.200	$3.20	—	source
Zhipu AI	GLM-5	A	.00	$0.200	$3.20	—	source
Z.AI	GLM-4.5-AirX	A	.10	$0.220	$4.50	—	source
Zhipu AI	GLM-4.5-AirX	A	.10	$0.220	$4.50	—	source
SiliconFlow	Pro/zai-org/GLM-5.1 (32k+ tokens)	A+	.14	$0.290	$4.00	—	source
SiliconFlow (China)	Pro/zai-org/GLM-5.1 (32k+ tokens)	A+	.15	$0.290	$4.03	—	source
Alibaba	Qwen3-Max No cache price	A	.20	—	$0.270	262K	source
Deep Infra	Qwen3-Max-Thinking	A+	.20	.20	$6.00	250	source
Deep Infra	Qwen3-Max	A+	.20	.20	$6.00	250	source
MiniMax (minimax.io)	MiniMax-M3 (>512k input)	A+	.20	$0.240	$4.80	1M	source
MiniMax (minimaxi.com)	MiniMax-M3 (>512k input)	A+	.20	$0.240	$4.80	1M	source
Together AI	Kimi K2.6	A+	.20	$0.200	$4.50	—	source
Z.AI	GLM-5-Turbo	A	.20	$0.240	$4.00	—	source
Z.AI	GLM-5V-Turbo	A	.20	$0.240	$4.00	—	source
Zhipu AI	GLM-5-Turbo	A	.20	$0.240	$4.00	—	source
Deep Infra	gemini-2.5-pro	A+	.25	.25	0.00	976	source
Vivgrid	gpt-5.1-codex-max	A	.25	$0.125	0.00	400K	source
Vivgrid	gpt-5.1-codex	A	.25	$0.125	0.00	400K	source
Vivgrid	gpt-5.1	A	.25	$0.125	0.00	400K	source
Vivgrid	gpt-5	A	.25	$0.125	0.00	400K	source
xAI	Grok 4.3 No cache price	A+	.25	—	.50	1M	source
Baseten	GLM 5.1	A+	.30	$0.260	$4.30	—	source
Deep Infra	DeepSeek-V4-Pro	A+	.30	.30	.60	1K	source
Friendli	GLM-5.1 Enterprise-only	A+	.40	$0.260	$4.40	—	source
Together AI	GLM-5.1 No cache price	A+	.40	—	$4.40	—	source
Vivgrid	glm-5.1	A	.40	$0.300	$4.40	200K	source
Z.AI	GLM-5.1	A	.40	$0.260	$4.40	—	source
Zhipu AI	GLM-5.1	A	.40	$0.260	$4.40	—	source
NovitaAI	L31 70B Euryale V2.2 No cache price	A+	.48	—	.48	8K	source
Deep Infra	gemini-3.5-flash	A+	.50	.50	$9.00	976	source
NovitaAI	Deepseek V4 Pro	A+	.60	$0.135	$3.20	1M	source
Baseten	DeepSeek V4	A+	.74	$0.145	$3.48	—	source
Vivgrid	deepseek-v4-pro	A	.74	$0.140	$3.48	1M	source
OpenAI	gpt-5.3-codex	A+	.75	$0.175	4.00	—	source
Vivgrid	gpt-5.3-codex	A	.75	$0.175	4.00	400K	source
Vivgrid	gpt-5.2-codex	A	.75	$0.175	4.00	400K	source
Vivgrid	gpt-5.2	A	.75	$0.175	4.00	400K	source
MiniMax (minimax.io)	MiniMax-M3 (Priority, >512k input) Enterprise-only	A+	.80	$0.360	$7.20	1M	source
MiniMax (minimaxi.com)	MiniMax-M3 (Priority, >512k input) Enterprise-only	A+	.80	$0.360	$7.20	1M	source
Deep Infra	gemini-3.1-pro	A+	.00	.00	2.00	976	source
Vertex	Gemini 3 Pro No cache price	A+	.00	—	2.00	—	source
LucidQuery AI	lucidnova-rf1-100b No cache price	A	.00	—	$5.00	120K	source
LucidQuery AI	lucidquery-nexus-coder No cache price	A	.00	—	$5.00	60K	source
Perplexity	Sonar Reasoning Pro No cache price	A+	.00	—	$8.00	—	source
Perplexity	Sonar Deep Research	A+	.00	.00	$8.00	—	source
Vivgrid	gemini-3-pro-preview	A	.00	$0.400	2.00	1M	source
Z.AI	GLM-4.5-X	A	.20	$0.450	$8.90	—	source
Zhipu AI	GLM-4.5-X	A	.20	$0.450	$8.90	—	source
Alibaba	qwen3-vl-plus No cache price	A	.46	—	$7.37	262K	source
Alibaba (China)	qwen3-vl-plus No cache price	A	.46	—	$7.37	262K	source
Cohere	Command R+ 08-2024 No cache price	A+	.50	—	0.00	—	source
Deep Infra	Qwen3.7-Max	A+	.50	.50	$7.50	250	source
Inference	Nemotron 3 Super No cache price	C	.50	—	$5.00	1M	source
OpenAI	gpt-5.4	A+	.50	$0.250	5.00	—	source
OpenAI	gpt-4o-transcribe No cache price	A+	.50	—	0.00	—	source
Vivgrid	gpt-5.4	A	.50	$0.250	5.00	1.1M	source
Vertex	Gemini 3.5 Flash Priority	A+	.70	$0.270	—	—	source
Anthropic	Claude Sonnet 4.6 No cache price	A+	$3.00	—	5.00	—	source
Anthropic	Claude Sonnet 4.5 No cache price	A+	$3.00	—	5.00	—	source
Cohere	Command R+ 04-2024 No cache price	A+	$3.00	—	5.00	—	source
Perplexity	Sonar Pro No cache price	A+	$3.00	—	5.00	—	source
v0	v0 Pro	A+	$3.00	$0.300	5.00	—	source
Vivgrid	gemini-3.1-pro-preview	A	$3.00	$0.300	2.00	1M	source
Vertex (Anthropic)	Claude Sonnet 4.6 No cache price	C	$3.30	—	6.50	—	source
Vertex (Anthropic)	Claude Sonnet 4.5 No cache price	C	$3.30	—	6.50	—	source
Vertex	Gemini 3.1 Pro Preview Priority	A+	$3.60	$0.360	1.60	—	source
Vivgrid	claude-sonnet-4.6	A	$4.00	.00	5.00	200K	source
Anthropic	Claude Opus 4.8 No cache price	A+	$5.00	—	5.00	1M	source
Anthropic	Claude Opus 4.7 No cache price	A+	$5.00	—	5.00	—	source
Anthropic	Claude Opus 4.6 No cache price	A+	$5.00	—	5.00	—	source
Anthropic	Claude Opus 4.5 No cache price	A+	$5.00	—	5.00	—	source
Vertex (Anthropic)	Claude Opus 4.8 No cache price	C	$5.00	—	5.00	—	source
Vertex (Anthropic)	Claude Opus 4.7 No cache price	C	$5.00	—	5.00	—	source
OpenAI	gpt-5.5	A+	$5.00	$0.500	$30.00	—	source
OpenAI	chat-latest	A+	$5.00	$0.500	$30.00	—	source
v0	v0 Max	A+	$5.00	$0.500	5.00	—	source
Vivgrid	gpt-5.5	A	$5.00	$0.500	$30.00	1.1M	source
Vivgrid	cluade-opus-4.6	A	$5.00	.00	5.00	200K	source
Vertex (Anthropic)	Claude Opus 4.6 No cache price	C	$5.50	—	7.50	—	source
Vertex (Anthropic)	Claude Opus 4.5 No cache price	C	$5.50	—	7.50	—	source
Anthropic	Claude Opus 4.1 No cache price	A+	5.00	—	$75.00	—	source
OpenAI	gpt-5.5-pro No cache price	A+	$30.00	—	80.00	—	source
v0	v0 Max Fast	A+	$30.00	$3.00	50.00	—	source
OpenAI	gpt-realtime-2	A+	$32.00	$0.400	$64.00	—	source
Lilac	Gemma 4 No cache price	A	10.00	—	$3500.00	262K	source
Lilac	MiniMax M2.7	A	$300.00	$55.00	200.00	205K	source
Lilac	Kimi K2.6	A	$700.00	00.00	$3500.00	262K	source
Lilac	GLM 5.1	A	$900.00	70.00	$3000.00	203K	source

Subscriptions, seats & agent plans

44 products · 125 flat-rate / seat plans · 2 agent frameworks — now on a dedicated page.

Open

Generative media pricing (image, video, audio & 3D)

1,252 fal.ai-hosted models from 215 creators, priced per image / megapixel / video-second — billed per output, not per token, so kept separate from the index above.

Open

Provider directory

Every provider in the index with model counts, cheapest entries, and official source coverage.

137 providers

Provider	Models	Priced	Cheapest input	Cheapest output	Official source
NanoGPT nano-gpt	525	521	Auto model ($0)	Auto model ($0)	official
OpenRouter openrouter	357	354	Uncensored (free) ($0)	Uncensored (free) ($0)	official
Kilo Gateway kilo	345	345	Baidu: CoBuddy (free) ($0)	Baidu: CoBuddy (free) ($0)	official
Vercel AI Gateway vercel	246	224	Llama-3.3-70B-Instruct ($0)	Qwen3 Embedding 0.6B ($0)	official
LLM Gateway llmgateway	189	189	Auto Route ($0)	Auto Route ($0)	official
NovitaAI novita-ai	104	104	Ling-2.6-1T ($0)	Ling-2.6-1T ($0)	official
Azure azure	103	103	text-embedding-3-small ($0.020)	Embed v4 ($0)	official
302.AI 302ai	97	97	Qwen-Flash ($0.022)	Qwen-Flash ($0.220)	official
Azure Cognitive Services azure-cognitive-services	96	96	text-embedding-3-small ($0.020)	Embed v4 ($0)	official
ZenMux zenmux	96	96	Step 3.5 Flash (Free) ($0)	Step 3.5 Flash (Free) ($0)	official
Nvidia nvidia	93	93	dracarys-llama-3.1-70b-instruct ($0)	dracarys-llama-3.1-70b-instruct ($0)	official
Poe poe	137	93	Kimi-K2.5-FW ($0)	Kimi-K2.5-FW ($0)	official
Amazon Bedrock amazon-bedrock	91	91	Nova Micro ($0.035)	Voxtral Mini 3B 2507 ($0.040)	official
Helicone helicone	90	90	Google Gemma 2 ($0.010)	Meta Llama Prompt Guard 2 22M ($0.010)	official
Alibaba (China)lab alibaba-cn	82	82	DeepSeek R1 Distill Llama 8B ($0)	DeepSeek R1 Distill Llama 8B ($0)	official
SiliconFlow (China) siliconflow-cn	82	82	deepseek-ai/DeepSeek-OCR ($0)	deepseek-ai/DeepSeek-OCR ($0)	official
Merge Gateway merge-gateway	83	81	Command R7B ($0.037)	Command R7B ($0.150)	official
OrcaRouter orcarouter	81	81	OrcaRouter Auto ($0)	OrcaRouter Auto ($0)	official
Cloudflare AI Gateway cloudflare-ai-gateway	76	76	Deepgram Aura 2 (EN) ($0)	BGE Base EN v1.5 ($0)	official
SiliconFlow siliconflow	76	76	tencent/Hunyuan-MT-7B ($0)	tencent/Hunyuan-MT-7B ($0)	official
Venice AI venice	69	69	OpenAI GPT OSS 120B ($0.070)	Qwen 3.5 9B ($0.150)	official
DigitalOcean digitalocean	78	66	All-MiniLM-L6-v2 ($0.0090)	All-MiniLM-L6-v2 ($0)	official
Abacus abacus	65	65	Llama 3.1 8B Instruct ($0.020)	Llama 3.1 8B Instruct ($0.050)	official
OpenCode Zen opencode	65	65	Big Pickle ($0)	Big Pickle ($0)	official
Jiekou.AI jiekou	61	61	XiaomiMiMo/MiMo-V2-Flash ($0)	XiaomiMiMo/MiMo-V2-Flash ($0)	official
GitHub Models github-models	55	55	AI21 Jamba 1.5 Large ($0)	AI21 Jamba 1.5 Large ($0)	official
AIHubMix aihubmix	50	50	Coding GLM 5.1 (free) ($0)	Coding GLM 5.1 (free) ($0)	official
Alibabalab alibaba	50	50	Qwen3-ASR Flash ($0.035)	Qwen3-ASR Flash ($0.035)	official
Cortecs cortecs	49	49	Devstral 2 2512 ($0)	Devstral 2 2512 ($0)	official
OpenAIlab openai	52	48	text-embedding-3-small ($0.020)	text-embedding-3-large ($0)	official
Vertexlab google-vertex	40	40	GPT OSS 20B ($0.070)	Gemini Embedding 001 ($0)	official
Chutes chutes	39	39	Qwen3Guard Gen 0.6B ($0.010)	Qwen3Guard Gen 0.6B ($0.011)	official
Deep Infra deepinfra	39	39	Llama 3.1 8B ($0.020)	Llama 3.1 8B Turbo ($0.030)	official
Requesty requesty	38	38	GPT-5 Nano ($0.050)	GPT-5 Nano ($0.400)	official
NEAR AI Cloud nearai	37	37	Whisper Large v3 ($0.010)	Whisper Large v3 ($0)	official
Synthetic synthetic	33	33	GLM-4.7-Flash ($0.060)	GPT OSS 120B ($0.100)	official
Nebius Token Factory nebius	31	31	Qwen3-Embedding-8B ($0.010)	Qwen3-Embedding-8B ($0)	official
GitHub Copilot github-copilot	29	29	Claude Haiku 4.5 ($0)	Claude Haiku 4.5 ($0)	official
Mistrallab mistral	28	28	Devstral Small 2 ($0)	Devstral Small 2 ($0)	official
Cloudflare Workers AI cloudflare-workers-ai	27	27	Granite 4.0 H Micro ($0.017)	Llama Guard 3 8B ($0.030)	official
Groq groq	27	27	ALLaM-2-7b ($0)	ALLaM-2-7b ($0)	official
FrogBot frogbot	26	26	GPT OSS 20B ($0.070)	GPT OSS 20B ($0.200)	official
routing.run routing-run	26	26	Step 3.5 Flash ($0.096)	Step 3.5 Flash ($0.288)	official
Databricks databricks	25	25	GPT-5 Nano ($0.050)	GPT OSS 20B ($0.200)	official
SAP AI Core sap-ai-core	25	25	gpt-5-nano ($0.050)	gemini-2.5-flash-lite ($0.400)	official
Anthropiclab anthropic	24	24	Claude Haiku 3 ($0.250)	Claude Haiku 3 ( .25)	official
Hugging Face huggingface	24	24	GLM-4.7-Flash ($0)	Qwen 3 Embedding 4B ($0)	official
CrofAI crof	21	21	GLM-4.7-Flash ($0.040)	Qwen3.5 9B ($0.150)	official
Googlelab google	21	19	Gemini 2.0 Flash-Lite ($0.075)	Gemini Embedding 001 ($0)	official
Meganova meganova	19	19	Mistral Small 3.2 24B Instruct ($0)	Mistral Small 3.2 24B Instruct ($0)	official
Together AI togetherai	19	19	Rnj-1 Instruct ($0.150)	Rnj-1 Instruct ($0.150)	official
Perplexity Agent perplexity-agent	18	18	Grok 4.1 Fast (Non-Reasoning) ($0.200)	Grok 4.1 Fast (Non-Reasoning) ($0.500)	official
Weights & Biases wandb	18	18	gpt-oss-20b ($0.050)	Qwen3 235B A22B Instruct 2507 ($0.100)	official
GitLab Duo gitlab	17	17	Agentic Chat (GPT-5.1) ($0)	Agentic Chat (GPT-5.1) ($0)	official
IO.NET io-net	17	17	Mistral Nemo Instruct 2407 ($0.020)	Mistral Nemo Instruct 2407 ($0.040)	official
OpenCode Go opencode-go	16	16	DeepSeek V4 Flash ($0.140)	DeepSeek V4 Flash ($0.280)	official
Scaleway scaleway	16	16	Whisper Large v3 ($0.0030)	BGE Multilingual Gemma2 ($0)	official
Auriko auriko	15	15	DeepSeek V4 Flash ($0.140)	DeepSeek V4 Flash ($0.280)	official
FastRouter fastrouter	15	15	DeepSeek R1 Distill Llama 70B ($0.030)	DeepSeek R1 Distill Llama 70B ($0.140)	official
Baseten baseten	14	14	GPT OSS 120B ($0.100)	DeepSeek V3.2 ($0.450)	official
iFlow iflowcn	14	14	DeepSeek-R1 ($0)	DeepSeek-R1 ($0)	official
Neuralwatt neuralwatt	14	14	GPT OSS 20B ($0.030)	GPT OSS 20B ($0.160)	official
evroc evroc	13	13	KB Whisper ($0.0024)	KB Whisper ($0.0024)	official
Regolo AI regolo-ai	13	13	Llama 3.1 8B Instruct ($0.050)	Qwen3-Embedding-8B ($0.100)	official
Vertex (Anthropic) google-vertex-anthropic	13	13	Claude Haiku 3.5 ($0.800)	Claude Haiku 3.5 ($4.00)	official
Vivgrid vivgrid	13	13	GPT-5.4 Nano ($0.200)	DeepSeek-V3.2 ($0.420)	official
Z.AIlab zai	13	13	GLM-4.5-Flash ($0)	GLM-4.5-Flash ($0)	official
Clarifai clarifai	12	12	Trinity Mini ($0.045)	Trinity Mini ($0.150)	official
Fireworks AI fireworks-ai	12	12	GPT OSS 20B ($0.070)	DeepSeek V4 Flash ($0.280)	official
Zhipu AIlab zhipuai	12	12	GLM-4.5-Flash ($0)	GLM-4.5-Flash ($0)	official
Alibaba Coding Plan alibaba-coding-plan	11	11	GLM-4.7 ($0)	GLM-4.7 ($0)	official
Alibaba Coding Plan (China) alibaba-coding-plan-cn	11	11	GLM-4.7 ($0)	GLM-4.7 ($0)	official
OVHcloud AI Endpoints ovhcloud	11	11	gpt-oss-20b ($0.050)	Llama-3.1-8B-Instruct ($0.110)	official
MiniMax (minimax.io)lab minimax	10	10	MiniMax-M2 ($0.300)	MiniMax-M2 ( .20)	official
MiniMax (minimaxi.com)lab minimax-cn	10	10	MiniMax-M2 ($0.300)	MiniMax-M2 ( .20)	official
Inference inference	9	9	Llama 3.2 1B Instruct ($0.010)	Qwen 3 Embedding 4B ($0)	official
QiHang qihang-ai	9	9	GPT-5-Mini ($0.040)	GPT-5-Mini ($0.290)	official
submodel submodel	9	9	GPT OSS 120B ($0.100)	Qwen3 235B A22B Instruct 2507 ($0.300)	official
Coherelab cohere	12	8	Command R7B ($0.037)	Command R7B ($0.150)	official
GMI Cloud gmicloud	8	8	DeepSeek V4 Flash ($0.112)	DeepSeek V4 Flash ($0.224)	official
STACKIT stackit	8	8	E5 Mistral 7B ($0.020)	E5 Mistral 7B ($0.020)	official
Tencent Coding Plan (China) tencent-coding-plan	8	8	GLM-5 ($0)	GLM-5 ($0)	official
Xiaomi Token Plan (China) xiaomi-token-plan-cn	8	8	MiMo-V2-Omni ($0)	MiMo-V2-Omni ($0)	official
Xiaomi Token Plan (Europe) xiaomi-token-plan-ams	8	8	MiMo-V2-Omni ($0)	MiMo-V2-Omni ($0)	official
Xiaomi Token Plan (Singapore) xiaomi-token-plan-sgp	8	8	MiMo-V2-Omni ($0)	MiMo-V2-Omni ($0)	official
Berget.AI berget	7	7	Gemma 4 31B Instruct ($0.275)	Mistral Small 3.2 24B Instruct 2506 ($0.330)	official
Llamalab llama	7	7	Cerebras-Llama-4-Maverick-17B-128E-Instruct ($0)	Cerebras-Llama-4-Maverick-17B-128E-Instruct ($0)	official
MiniMax Token Plan (minimax.io) minimax-coding-plan	7	7	MiniMax-M2 ($0)	MiniMax-M2 ($0)	official
MiniMax Token Plan (minimaxi.com) minimax-cn-coding-plan	7	7	MiniMax-M2 ($0)	MiniMax-M2 ($0)	official
ModelScope modelscope	7	7	Qwen3 235B A22B Instruct 2507 ($0)	Qwen3 235B A22B Instruct 2507 ($0)	official
Moonshot AIlab moonshotai	7	7	Kimi K2 0711 ($0.600)	Kimi K2 0711 ( .50)	official
Moonshot AI (China)lab moonshotai-cn	7	7	Kimi K2 0711 ($0.600)	Kimi K2 0711 ( .50)	official
Vultr vultr	7	7	Llama 3.1 Nemotron Safety Guard ($0.010)	Llama 3.1 Nemotron Safety Guard ($0.010)	official
Friendli friendli	6	6	Llama 3.1 8B Instruct ($0.100)	Llama 3.1 8B Instruct ($0.100)	official
Atomic Chat atomic-chat	5	5	Gemma 4 E4B Instruct (IQ4_XS) ($0)	Gemma 4 E4B Instruct (IQ4_XS) ($0)	official
CloudFerro Sherlock cloudferro-sherlock	5	5	MiniMax-M2.5 ($0.300)	Bielik 11B v2.6 Instruct ($0.670)	official
DInference dinference	5	5	GPT OSS 120B ($0.068)	GPT OSS 120B ($0.270)	official
Mixlayer mixlayer	5	5	Qwen3.5 9B ($0.100)	Qwen3.5 9B ($0.400)	official
Privatemode AI privatemode-ai	5	5	Gemma 3 27B ($0)	Gemma 3 27B ($0)	official
Umans AI Coding Plan umans-ai-coding-plan	5	5	Umans Coder ($0)	Umans Coder ($0)	official
xAIlab xai	8	5	Grok Build 0.1 ( .00)	Grok Build 0.1 ( .00)	official
Xiaomilab xiaomi	5	5	MiMo-V2-Flash ($0.100)	MiMo-V2-Flash ($0.300)	official
Z.AI Coding Plan zai-coding-plan	5	5	GLM-4.5-Air ($0)	GLM-4.5-Air ($0)	official
Zhipu AI Coding Plan zhipuai-coding-plan	5	5	GLM-4.5-Air ($0)	GLM-4.5-Air ($0)	official
DeepSeeklab deepseek	4	4	DeepSeek Chat ($0.140)	DeepSeek Chat ($0.280)	official
Inceptron inceptron	4	4	Llama 3.3 70B Instruct ($0.120)	Llama 3.3 70B Instruct ($0.380)	official
Lilac lilac	4	4	Gemma 4 31B IT ($0.110)	Gemma 4 31B IT ($0.350)	official
Perplexitylab perplexity	4	4	Sonar ( .00)	Sonar ( .00)	official
StepFun (China)lab stepfun	4	4	Step 3.5 Flash ($0.096)	Step 3.5 Flash ($0.288)	official
Wafer wafer.ai	4	4	GLM-5.1 ($0)	GLM-5.1 ($0)	official
Cerebras cerebras	3	3	Llama 3.1 8B ($0.100)	Llama 3.1 8B ($0.100)	official
D.Run (China) drun	3	3	DeepSeek V3 ($0.280)	DeepSeek V3 ( .10)	official
HPC-AI hpc-ai	3	3	MiniMax M2.5 ($0.140)	MiniMax M2.5 ($0.560)	official
Kimi For Coding kimi-for-coding	3	3	Kimi K2.5 ($0)	Kimi K2.5 ($0)	official
LMStudio lmstudio	3	3	GPT OSS 20B ($0)	GPT OSS 20B ($0)	official
Morph morph	3	3	Morph v3 Fast ($0.800)	Morph v3 Fast ( .20)	official
Upstagelab upstage	3	3	solar-mini ($0.150)	solar-mini ($0.150)	official
v0 v0	3	3	v0-1.0-md ($3.00)	v0-1.0-md ( 5.00)	official
Ambient ambient	2	2	Kimi K2.6 ($0.950)	Kimi K2.6 ($4.00)	official
Bailing bailing	2	2	Ling-1T ($0.570)	Ling-1T ( .29)	official
Inceptionlab inception	2	2	Mercury 2 ($0.250)	Mercury 2 ($0.750)	official
LucidQuery AI lucidquery	2	2	LucidNova RF1 100B ( .00)	LucidNova RF1 100B ($5.00)	official
Moark moark	2	2	MiniMax-M2.1 ( .10)	MiniMax-M2.1 ($8.40)	official
Nova nova	2	2	Nova 2 Lite ($0)	Nova 2 Lite ($0)	official
Poolside poolside	2	2	Laguna M.1 ($0)	Laguna M.1 ($0)	official
Qiniu qiniu-ai	91	2	Mimo-V2-Flash ($0.100)	Mimo-V2-Flash ($0.300)	official
StepFunlab stepfun-ai	2	2	Step 3.5 Flash ($0.096)	Step 3.5 Flash ($0.288)	official
abliteration.ai abliteration-ai	1	1	Abliterated Model ($3.00)	Abliterated Model ($3.00)	official
Claudinio claudinio	1	1	Claudinio ($0.500)	Claudinio ( .00)	official
Fireworks (Firepass) firepass	1	1	Kimi K2.6 Turbo ($0)	Kimi K2.6 Turbo ($0)	official
KUAE Cloud Coding Plan kuae-cloud-coding-plan	1	1	GLM-4.7 ($0)	GLM-4.7 ($0)	official
Tencent TokenHublab tencent-tokenhub	1	1	Hy3 preview ($0)	Hy3 preview ($0)	official
Xpersona xpersona	1	1	Xpersona Frieren Coder ( .50)	Xpersona Frieren Coder ($6.00)	official
Ollama Cloud ollama-cloud	39	0	—	—	official
Sarvam AIlab sarvam	2	0	—	—	official
Snowflake Cortex snowflake-cortex	11	0	—	—	official
The Grid AI the-grid-ai	9	0	—	—	official

Token prices are normalized to USD per 1M tokens where a provider publishes token-based pricing. Model quality (Intelligence & Coding indices) is sourced from Artificial Analysis and joined by model name; 2,224 models carry a benchmark. “Labs” are first-party model creators; gateways and cloud resellers are flagged so you can strip duplicate listings. Monthly costs are token-only estimates and exclude caching discounts, batch tiers, and committed-use pricing. Prices: models.dev plus official provider pages.