GPU compute markets

Inference pricing

What LLM inference costs in US dollars per million tokens, as listed on OpenRouter.

Loading…

Providers for one model

What each host charges right now, cheapest output first.

Model

Loading…

Recent price changes

Each time a model's headline price on OpenRouter has moved, newest first.

Loading…

All models

OpenRouter's headline price for every model it lists, newest first.

Loading…

Provider	Quantization	Input per million	Output per million
DeepInfra	fp8	$0.10	$0.32
Parasail	fp8	$0.22	$0.50
AkashML	fp8	$0.20	$0.52
CoreWeave	fp16	$0.71	$0.71
Google	Not stated	$0.72	$0.72
Featherless	Not stated	$0.65	$0.75
Groq	Not stated	$0.59	$0.79
SambaNova	Not stated	$0.45	$0.90
Cloudflare	fp8	$0.29	$2.25

Model	Input per million	Output per million	Output change	When
OpenAI: gpt-oss-120bopenai/gpt-oss-120b	$0.15 to $0.029	$0.60 to $0.11	▼ -82.0%	1 min ago
Google: Gemma 4 26B A4B google/gemma-4-26b-a4b-it	$0.066 to $0.079	$0.20 to $0.24	▲ +19.2%	1 min ago
MoonshotAI: Kimi Latest~moonshotai/kimi-latest	$0.18 to $0.16	$10.56 to $9.34	▼ -11.5%	1 min ago
MiniMax: MiniMax M3.1 Flashminimax/minimax-m3.1-flash	$0.15 to $0.075	$0.60 to $0.30	▼ -50.0%	1 min ago
Meta: Llama 3.1 70B Instructmeta-llama/llama-3.1-70b-instruct	$0.40 to $0.72	$0.40 to $0.72	▲ +80.0%	3 h ago
Meta: Llama 3.3 70B Instructmeta-llama/llama-3.3-70b-instruct	$0.100 to $0.20	$0.32 to $0.52	▲ +62.5%	3 h ago
Qwen: Qwen3 Coder 30B A3B Instructqwen/qwen3-coder-30b-a3b-instruct	$0.070 to $0.15	$0.28 to $0.60	▲ +114.3%	3 h ago
Qwen: Qwen3 Next 80B A3B Instructqwen/qwen3-next-80b-a3b-instruct	$0.090 to $0.100	$1.10		3 h ago
Google: Gemma 4 26B A4B google/gemma-4-26b-a4b-it	$0.085 to $0.066	$0.26 to $0.20	▼ -22.7%	3 h ago
MoonshotAI: Kimi Latest~moonshotai/kimi-latest	$0.15 to $0.18	$7.15 to $10.56	▲ +47.7%	3 h ago
DeepSeek: DeepSeek V4 Flash 0731deepseek/deepseek-v4-flash-0731	$0.12 to $0.059	$0.24 to $0.30	▲ +26.1%	3 h ago
Z.ai: GLM 5.3 Flashz-ai/glm-5.3-flash	$0.029 to $0.031	$0.092 to $0.085	▼ -8.3%	3 h ago
Z.ai: GLM Flash Latest~z-ai/glm-flash-latest	$0.029 to $0.031	$0.092 to $0.085	▼ -8.3%	3 h ago
DeepSeek: DeepSeek Flash Latest~deepseek/deepseek-flash-latest	$0.035	$0.50 to $0.32	▼ -37.0%	3 h ago
MiniMax: MiniMax M3.1 Flashminimax/minimax-m3.1-flash	$0.075 to $0.15	$0.30 to $0.60	▲ +100.0%	3 h ago
Meta: Llama 3.2 3B Instructmeta-llama/llama-3.2-3b-instruct	$0.050 to $0.051	$0.33 to $0.34	▲ +1.5%	1 d ago
OpenAI: gpt-oss-20bopenai/gpt-oss-20b	$0.018 to $0.030	$0.090 to $0.13	▲ +44.4%	1 d ago
Z.ai: GLM 4.7z-ai/glm-4.7	$0.54 to $0.60	$1.98 to $2.20	▲ +11.1%	1 d ago
Google: Gemma 4 26B A4B google/gemma-4-26b-a4b-it	$0.068 to $0.085	$0.22 to $0.26	▲ +13.8%	1 d ago
MoonshotAI: Kimi Latest~moonshotai/kimi-latest	$0.16 to $0.15	$10.55 to $7.15	▼ -32.3%	1 d ago
Z.ai: GLM 5.2z-ai/glm-5.2	$0.006	$7.00 to $6.80	▼ -2.9%	1 d ago
DeepSeek: DeepSeek V4 Flash Latest~deepseek/deepseek-v4-flash-latest	$0.034 to $0.059	$0.18 to $0.30	▲ +64.8%	1 d ago
DeepSeek: DeepSeek V4 Pro 0813deepseek/deepseek-v4-pro-0813	$0.66 to $0.11	$1.98 to $4.00	▲ +102.0%	1 d ago
Z.ai: GLM 5.3z-ai/glm-5.3	$0.070 to $0.080	$1.40 to $3.60	▲ +157.1%	1 d ago
Z.ai: GLM 5.3 Flashz-ai/glm-5.3-flash	$0.024 to $0.029	$0.11 to $0.092	▼ -19.2%	1 d ago

Model	Weights	Context	Input per million	Output per million
Z.ai: GLM 5.3 FlashX Legalz-ai/glm-5.3-flashx-legal	Closed	1M	$0.37	$1.25
Particle AI: Particle-1particle-ai/particle-1	Closed	1M	$0.050	$0.50
OpenAI: GPT-6.1 Terra Proopenai/gpt-6.1-terra-pro	Closed	1M	$1.00	$5.00
OpenAI: GPT-6.1 Terra Pro (batch)openai/gpt-6.1-terra-pro:batch	Closed	1M	$0.50	$2.50
OpenAI: GPT-6.1 Terraopenai/gpt-6.1-terra	Closed	1M	$1.00	$5.00
OpenAI: GPT-6.1 Terra (batch)openai/gpt-6.1-terra:batch	Closed	1M	$0.50	$2.50
MoonshotAI: Kimi K3.1 Promoonshotai/kimi-k3.1-pro	Closed	1M	$2.00	$10.00
Recursive: Flint (free)recursive/flint-v1.0:free	Open	262K	Free	Free
MiniMax: MiniMax M3.1 Flashminimax/minimax-m3.1-flash	Open	1M	$0.075	$0.30
DeepSeek: DeepSeek V4.1 Flash 1017deepseek/deepseek-v4.1-flash-1017	Open	1M	$0.15	$0.60
Elorian: Glimpseelorian/glimpse	Closed	262K	$0.60	$3.00
XingChen: Xing4.0 29B A4B (free)xingchen-agi/xing4.0-29b-a4b:free	Open	262K	Free	Free
Reflection: Beam 1.0 501B A23Breflection/beam-1.0-501b-a23b	Open	1M	$0.25	$1.00
Inception: Mercury 3inception/mercury-3	Closed	1M	$0.100	$0.35
PrismML: Ternary Bonsai 2 9Bprism-ml/ternary-bonsai-2-9b	Open	262K	$0.080	$0.13
Moondream: Moondream 3 Previewmoondream/moondream3-preview	Open	32K	$0.30	$2.50
Moondream: Moondream 3.1moondream/moondream3.1-9b-a2b	Open	32K	$0.30	$2.50
Meta: Muse Spark Openmeta/muse-spark-open	Open	1M	$1.25	$4.25
NVIDIA: Nemotron 3.5 Super VLnvidia/nemotron-3.5-super-vl	Open	1M	$0.15	$0.50
NVIDIA: Nemotron 3.5 Super VL (free)nvidia/nemotron-3.5-super-vl:free	Open	1M	Free	Free
Pareto 26.10unbiased/pareto-26.10	Closed	1M	$0.80	$3.20
Pareto Latest~unbiased/pareto-latest	Closed	1M	$0.80	$3.20
Pareto 26.9unbiased/pareto-26.9	Closed	262K	$2.50	$7.50
LiquidAI: LFM2.5-24B-A2Bliquid/lfm-2.5-24b-a2b	Open	128K	$0.050	$0.70
Google: Gemini 4 Argongoogle/gemini-4-argon	Closed	1M	$2.00	$10.00
Google: Gemini 4 Argon (batch)google/gemini-4-argon:batch	Closed	1M	$1.00	$5.00
ScaleDown: Summarizescaledown/summarize	Closed	1M	$0.040	Free
ScaleDown: Extractscaledown/extract	Closed	1M	$0.040	Free
Meta: Muse Wondermeta/muse-wonder	Closed	1M	$4.00	$20.00
StepFun: Step 5 Previewstepfun/step-5-preview	Open	1M	$1.00	$2.70
Anthropic: Claude Haiku 5.5anthropic/claude-haiku-5.5	Closed	1M	$0.100	$0.50
Anthropic: Claude Haiku 5.5 (batch)anthropic/claude-haiku-5.5:batch	Closed	1M	$0.050	$0.25
Google: Nano Banana 2.1google/gemini-nano-banana-2.1	Closed	66K	$1.50	$7.50
Mistral: Mistral Large 4mistralai/mistral-large-4-0	Open	1M	$0.70	$2.10
inclusionAI: Ling 3.1 Flashinclusionai/ling-3.1-flash	Closed	1M	$0.075	$0.22
OpenAI: GPT-6.1 Sol Proopenai/gpt-6.1-sol-pro	Closed	1M	$2.00	$10.00
OpenAI: GPT-6.1 Sol Pro (batch)openai/gpt-6.1-sol-pro:batch	Closed	1M	$1.00	$5.00
OpenAI: GPT-6.1 Solopenai/gpt-6.1-sol	Closed	1M	$2.00	$10.00
OpenAI: GPT-6.1 Sol (batch)openai/gpt-6.1-sol:batch	Closed	1M	$1.00	$5.00
Anthropic: Claude Sonnet 5.5anthropic/claude-sonnet-5.5	Closed	1M	$2.00	$10.00

Model	Providers	Cheapest provider	Its input price	Its output price	Median output	Highest output
Llama 3.3 70B	9	DeepInfra	$0.10	$0.32	$0.72	$2.25
gpt-oss-120b	24	PrimeIntellect	$0.03	$0.12	$0.46	$0.95
DeepSeek V4 Pro	15	Relace	$0.90	$1.50	$2.83	$3.83
DeepSeek V4 Flash	18	StreamLake	$0.08	$0.17	$0.28	$1.32
Qwen3.6 35B	12	PrimeIntellect	$0.01	$0.11	$0.97	$1.80
Gemma 4 31B	16	DeepInfra	$0.16	$0.32	$0.40	$1.15
Kimi K2.6	18	Baidu	$0.39	$1.64	$3.50	$4.60
GLM 5.1	14	Baidu	$0.90	$2.82	$4.25	$4.40

Inference pricing

Providers for one model

Recent price changes

All models

444

170

8

Open models, cheapest output price