Pricing built for growth

Production inference that won't break
your product or your bank.

Pay as you go

Serverless endpoints

Per-token access to 2M+ open models. Call an endpoint and go — zero setup.

2M+ open models
No minimums
Community support

Get Started

Early access

Per million tokens

Elastic Endpoints

Private, optimized endpoints priced per million tokens.

Private optimized endpoints
Per-workload tuning
Dedicated support

Talk to sales

Reserved capacity

Dedicated deployments

Reserved GPUs sized to your roadmap, with negotiated SLAs.

Reserved GPUs, sized to you
Negotiated latency SLA
Dedicated support

Talk to sales

Lowest rate

Batch

High-throughput offline jobs at the lowest per-token rate, on spare fleet capacity.

Lowest per-token rate
Millions of requests per job
Great for evals & embeddings

Get Started

Elastic Endpoints

Per-token model pricing

Pay only for what you use. No minimums, no rate limits.

Price per 1M tokens

Model	Input	Output	Cache read
Kimi K3	$3.00	$15.00	$0.30
Kimi K2.7 Code	$0.75	$3.50	$0.16
Kimi K2.6	$0.75	$3.50	$0.16
GLM-5.3 Flash	$0.15	$0.50	$0.03
GLM-5.3	$1.40	$4.40	$0.26
GLM-5.2	$1.40	$4.40	$0.26
GLM-5.1	$1.40	$4.40	$0.26
GLM-5	$1.00	$3.20	$0.20
MiniMax M3	$0.30	$1.20	$0.06
MiniMax M2.5	$0.30	$1.20	$0.03
DeepSeek V4 Pro	$1.74	$3.48	$0.10
DeepSeek V4 Flash	$0.14	$0.28	$0.07
Qwen3.6 35B-A3B	$0.15	$1.00	$0.05
Qwen3.5 397B-A17B	$0.50	$3.60	$0.30
Qwen3.5 35B-A3B	$0.15	$1.00	$0.05
Qwen3-Coder-Next	$0.12	$0.80	$0.07
Qwen3-VL 235B-A22B	$0.21	$1.90	$0.10
Qwen3-VL 8B	$0.25	$0.75	$0.12
Qwen3-Next 80B	$0.10	$1.10	$0.07
Qwen3 235B-A22B (2507)	$0.14	$0.80	$0.05
Qwen2.5-VL 72B	$0.80	$1.00	$0.40
Mistral Small 3.2 24B	$0.09	$0.30	$0.05
Llama 4 Maverick (FP8)	$0.35	$1.00	$0.17
Llama 3.3 70B (FP8)	$0.22	$0.50	$0.11
Nemotron 3 Ultra 550B (NVFP4)	$0.50	$2.50	$0.10
MiMo v2.5	$0.14	$0.28	$0.05
Resemble TTS (English)	$18.50	—	—
Trinity Large (Thinking)	$0.22	$0.85	$0.06
Gemma 4 26B-A4B	$0.13	$0.40	$0.05
Gemma 4 31B	$0.15	$0.40	$0.06
Skyfall 31B v4.2	$0.55	$0.80	$0.25
Cydonia 24B v4.1	$0.30	$0.50	$0.15
gpt-oss-120b	$0.10	$0.75	$0.055
gpt-oss-120b (Fast)	$0.15	$0.60	—
gpt-oss-20b	$0.04	$0.20	$0.02
UI-TARS 1.5 7B	$0.10	$0.20	$0.10
Gemma 3 27B	$0.08	$0.45	$0.04
Skyfall 36B v2 (FP8)	$0.55	$0.80	$0.25
BGE-M3	$0.01	—	—

Dedicated deployments

Reserved GPU pricing

Hourly price per GPU, billed by the minute. Volume discounts available.

Talk to sales

Hardware	Memory	Enquire
NVIDIA B300	288 GiB	Get a quote
NVIDIA B200	192 GiB	Get a quote
NVIDIA H200	141 GiB	Get a quote
NVIDIA H100 SXM	80 GiB	Get a quote
NVIDIA RTX PRO 6000	96 GiB	Get a quote
NVIDIA RTX 5090	32 GiB	Get a quote

Hourly rates available on request · volume discounts available

Batch

Self-service batch pricing

Best pricing and speed for your largest jobs. We find a unique fleet configuration, including spot instances, for the best value — a discount on serverless rates, plus an additional discount for cached tokens.

Precision

Batch pricing at FP4 precision, per 1M tokens
Model size	Input	Output	Cache read
0 – 4.1B params	$0.02	$0.04	$0.01
4.1B – 8.1B params	$0.03	$0.06	$0.01
8.1B – 16.1B params	$0.04	$0.10	$0.02
16.1B – 21.1B params	$0.05	$0.15	$0.02
21.1B – 41.1B params	$0.07	$0.22	$0.03
41.1B – 80.1B params	$0.13	$0.35	$0.06
80.1B – 150.1B params	$0.17	$0.47	$0.09
150.1B – 250.1B params	$0.22	$0.60	$0.11
250.1B – 500B params	$0.05	$0.25	$0.20
500B+ params	$0.52	$1.35	$0.26

Batch pricing at FP8 precision, per 1M tokens
Model size	Input	Output	Cache read
0 – 4.1B params	$0.03	$0.05	$0.01
4.1B – 8.1B params	$0.04	$0.09	$0.02
8.1B – 16.1B params	$0.05	$0.14	$0.03
16.1B – 21.1B params	$0.07	$0.22	$0.03
21.1B – 41.1B params	$0.10	$0.32	$0.05
41.1B – 80.1B params	$0.18	$0.50	$0.09
80.1B – 150.1B params	$0.25	$0.68	$0.12
150.1B – 250.1B params	$0.32	$0.86	$0.20
250.1B – 500B params	$0.57	$1.55	$0.29
500B+ params	$0.74	$1.93	$0.37

Batch pricing at FP16 precision, per 1M tokens
Model size	Input	Output	Cache read
0 – 4.1B params	$0.04	$0.07	$0.02
4.1B – 8.1B params	$0.05	$0.12	$0.02
8.1B – 16.1B params	$0.07	$0.19	$0.04
16.1B – 21.1B params	$0.09	$0.28	$0.04
21.1B – 41.1B params	$0.13	$0.41	$0.06
41.1B – 80.1B params	$0.23	$0.64	$0.12
80.1B – 150.1B params	$0.32	$0.88	$0.16
150.1B – 250.1B params	$0.41	$1.11	$0.20
250.1B – 500B params	$0.75	$2.02	$0.37
500B+ params	$0.97	$2.51	$0.48

Models with special batch pricing

Model	Input	Output	Cache read
Qwen/Qwen3-235B-A22B-Instruct-2507-FP8	$0.40	$0.40	—
Qwen/Qwen3.5-397B-A17B-FP8	$0.25	$1.80	—
deepseek-ai/DeepSeek-R1-0528	$2.00	$2.00	—
google/gemma-4-31B-it	$0.07	$0.20	—

Priced per 1M tokens · discounted from serverless rates

Start building today

Instantly run any open model — popular or specialized.