Batch pricing — pay only for what you use

Available models

Convoy batches requests for delivery in 30 minutes to 24 hours, with estimated savings around 40% off realtime API rates depending on model demand and token mix.

Available Models

Per-million-token batch prices and savings vs the underlying realtime APIs.

Model	Maker	Batch In /1M	Batch Out /1M	Realtime In /1M	Realtime Out /1M	Savings
Amazon Nova 2 Lite amazon-nova-2-lite	Amazon	$0.1914	$1.5906	$0.33	$2.75	−42%
Amazon Nova 2 Omni (Preview) amazon-nova-2-omni-preview	Amazon	$0.24	$1.68	$0.40	$2.80	−40%
Amazon Nova 2 Pro (Preview) amazon-nova-2-pro-preview	Amazon	$0.825	$6.60	$1.375	$11.00	−40%
Amazon Nova Lite amazon-nova-lite	Amazon	$0.036	$0.144	$0.06	$0.24	−40%
Amazon Nova Micro amazon-nova-micro	Amazon	$0.021	$0.084	$0.035	$0.14	−40%
Amazon Nova Premier amazon-nova-premier	Amazon	$1.50	$7.50	$2.50	$12.50	−40%
Amazon Nova Pro amazon-nova-pro	Amazon	$0.48	$1.92	$0.80	$3.20	−40%
Amazon Titan Text Embeddings v2 amazon-titan-text-embeddings-v2	Amazon	$0.012	$0.00	$0.02	$0.00	−40%
Claude 3 Haiku claude-3-haiku	Anthropic	$0.15	$0.75	$0.25	$1.25	−40%
Claude 3 Opus claude-3-opus	Anthropic	$9.00	$45.00	$15.00	$75.00	−40%
Claude 3 Sonnet claude-3-sonnet	Anthropic	$1.80	$9.00	$3.00	$15.00	−40%
Claude 3.5 Haiku claude-3.5-haiku	Anthropic	$0.48	$2.40	$0.80	$4.00	−40%
Claude 3.5 Sonnet claude-3.5-sonnet	Anthropic	$1.80	$9.00	$3.00	$15.00	−40%
Claude 3.5 Sonnet v1 claude-3.5-sonnet-v1	Anthropic	$1.80	$9.00	$3.00	$15.00	−40%
Claude 3.7 Sonnet claude-3.7-sonnet	Anthropic	$1.80	$9.00	$3.00	$15.00	−40%
Claude Haiku 4.5 claude-haiku-4.5	Anthropic	$0.66	$3.30	$1.10	$5.50	−40%
Claude Opus 4.5 claude-opus-4.5	Anthropic	$3.30	$16.50	$5.50	$27.50	−40%
Claude Opus 4.6 claude-opus-4.6	Anthropic	$3.30	$16.50	$5.50	$27.50	−40%
Claude Opus 4.6 Long claude-opus-4.6-long	Anthropic	$3.30	$16.50	$5.50	$27.50	−40%
Claude Sonnet 4 claude-sonnet-4	Anthropic	$1.80	$9.00	$3.00	$15.00	−40%
Claude Sonnet 4 Long claude-sonnet-4-long	Anthropic	$1.80	$9.00	$3.00	$15.00	−40%
Claude Sonnet 4.5 claude-sonnet-4.5	Anthropic	$1.98	$9.90	$3.30	$16.50	−40%
Claude Sonnet 4.5 Long claude-sonnet-4.5-long	Anthropic	$1.98	$9.90	$3.30	$16.50	−40%
Claude Sonnet 4.6 claude-sonnet-4.6	Anthropic	$1.98	$9.90	$3.30	$16.50	−40%
Claude Sonnet 4.6 Long claude-sonnet-4.6-long	Anthropic	$1.98	$9.90	$3.30	$16.50	−40%
DeepSeek V3.1 deepseek-v3.1	DeepSeek	$0.3584	$1.0382	$0.5974	$1.7304	−40%
DeepSeek V3.2 deepseek-v3.2	DeepSeek	$0.3832	$1.1434	$0.6386	$1.9055	−40%
Gemma 3 12B IT gemma-3-12b-it	Google	$0.054	$0.174	$0.09	$0.29	−40%
Gemma 3 27B IT gemma-3-27b-it	Google	$0.138	$0.228	$0.23	$0.38	−40%
Gemma 3 4B IT gemma-3-4b-it	Google	$0.024	$0.048	$0.04	$0.08	−40%
Llama 3.1 405B Instruct llama-3.1-405b-instruct	Meta	$1.44	$1.44	$2.40	$2.40	−40%
Llama 3.1 70B Instruct llama-3.1-70b-instruct	Meta	$0.432	$0.432	$0.72	$0.72	−40%
Llama 3.1 8B Instruct llama-3.1-8b-instruct	Meta	$0.132	$0.132	$0.22	$0.22	−40%
Llama 3.2 11B Vision Instruct llama-3.2-11b-vision-instruct	Meta	$0.096	$0.096	$0.16	$0.16	−40%
Llama 3.2 1B Instruct llama-3.2-1b-instruct	Meta	$0.06	$0.06	$0.10	$0.10	−40%
Llama 3.2 3B Instruct llama-3.2-3b-instruct	Meta	$0.09	$0.09	$0.15	$0.15	−40%
Llama 3.2 90B Vision Instruct llama-3.2-90b-vision-instruct	Meta	$0.432	$0.432	$0.72	$0.72	−40%
Llama 3.3 70B Instruct llama-3.3-70b-instruct	Meta	$0.432	$0.432	$0.72	$0.72	−40%
Llama 4 Maverick 17B Instruct llama-4-maverick-17b-instruct	Meta	$0.144	$0.582	$0.24	$0.97	−40%
Llama 4 Scout 17B Instruct llama-4-scout-17b-instruct	Meta	$0.102	$0.396	$0.17	$0.66	−40%
Minimax M2 minimax-m2	MiniMax AI	$0.18	$0.72	$0.30	$1.20	−40%
Minimax M2.1 minimax-m2.1	MiniMax AI	$0.18	$0.72	$0.30	$1.20	−40%
Devstral 2 123B devstral-2-123b	Mistral AI	$0.24	$1.20	$0.40	$2.00	−40%
Magistral Small 2509 magistral-small-2509	Mistral AI	$0.30	$0.90	$0.50	$1.50	−40%
Ministral 3 14B Instruct ministral-3-14b-instruct	Mistral AI	$0.12	$0.12	$0.20	$0.20	−40%
Ministral 3 3B Instruct ministral-3-3b-instruct	Mistral AI	$0.06	$0.06	$0.10	$0.10	−40%
Ministral 3 8B Instruct ministral-3-8b-instruct	Mistral AI	$0.09	$0.09	$0.15	$0.15	−40%
Mistral Large 2407 mistral-large-2407	Mistral AI	$1.80	$5.40	$2.00	$6.00	−10%
Mistral Large 3 mistral-large-3	Mistral AI	$0.30	$0.90	$0.50	$1.50	−40%
Voxtral Mini 3B 2507 voxtral-mini-3b-2507	Mistral AI	$0.024	$0.024	$0.04	$0.04	−40%
Voxtral Small 24B 2507 voxtral-small-24b-2507	Mistral AI	$0.06	$0.18	$0.10	$0.30	−40%
Kimi K2 Thinking kimi-k2-thinking	Moonshot AI	$0.36	$1.50	$0.60	$2.50	−40%
Kimi K2.5 kimi-k2.5	Moonshot AI	$0.36	$1.80	$0.60	$3.00	−40%
Nemotron Nano 12B v2 nemotron-nano-12b-v2	NVIDIA	$0.12	$0.36	$0.20	$0.60	−40%
Nemotron Nano 3 30B nemotron-nano-3-30b	NVIDIA	$0.036	$0.144	$0.06	$0.24	−40%
Nemotron Nano 9B v2 nemotron-nano-9b-v2	NVIDIA	$0.036	$0.138	$0.06	$0.23	−40%
GPT OSS 120B gpt-oss-120b	OpenAI	$0.0928	$0.3708	$0.1545	$0.618	−40%
GPT OSS 20B gpt-oss-20b	OpenAI	$0.0433	$0.1854	$0.0721	$0.309	−40%
GPT OSS Safeguard 120B gpt-oss-safeguard-120b	OpenAI	$0.09	$0.36	$0.15	$0.60	−40%
GPT OSS Safeguard 20B gpt-oss-safeguard-20b	OpenAI	$0.042	$0.12	$0.07	$0.20	−40%
Qwen3 235B A22B 2507 qwen3-235b-a22b-2507	Qwen	$0.136	$0.5438	$0.2266	$0.9064	−40%
Qwen3 32B qwen3-32b	Qwen	$0.0928	$0.3708	$0.1545	$0.618	−40%
Qwen3 Coder 30B A3B qwen3-coder-30b-a3b	Qwen	$0.0928	$0.3708	$0.1545	$0.618	−40%
Qwen3 Coder Next qwen3-coder-next	Qwen	$0.30	$0.72	$0.50	$1.20	−40%
Qwen3 Next 80B A3B qwen3-next-80b-a3b	Qwen	$0.09	$0.72	$0.15	$1.20	−40%
Qwen3 VL 235B A22B qwen3-vl-235b-a22b	Qwen	$0.318	$1.596	$0.53	$2.66	−40%
GLM 4.7 glm-4.7	Z AI	$0.36	$1.32	$0.60	$2.20	−40%
GLM 4.7 Flash glm-4.7-flash	Z AI	$0.042	$0.24	$0.07	$0.40	−40%

Pricing & savings disclaimers

All prices, savings percentages, and delivery windows shown on this page are estimates provided for informational purposes only and do not constitute a binding quote, offer, or guarantee of any kind.
Realtime API price comparisons reference third-party list prices as published by the underlying model provider at the time of last update. Those rates are set by the provider, may change without notice, and are not controlled by Convoy.
Actual savings depend on the specific model, your input/output token mix, batch size, queue depth, and current market demand. Models that are used infrequently may carry a slightly higher effective cost than displayed due to reduced batching efficiency.
The “30 minutes to 24 hours” delivery range is a target window, not a service-level guarantee. Convoy may extend processing time during periods of high demand or upstream provider degradation.
Final billed amounts are determined by the prices in effect and the actual token usage at the time your request is processed and reconciled, and may differ from any estimate displayed here.
Convoy may add, remove, retire, or reprice models at any time at its sole discretion. See the Terms of Service for the full terms governing pricing and billing.