DeepInfra API pricing

136 DeepInfra models, from price book 2026-10-22.

Billing rules Veqen applies

  • Token models: cached input at the cache-read rate, cache writes at the write rate; batch and service tiers at their own rates where published; long-context rates once the full prompt passes the threshold.

Also recognized as: deep_infra (framework, gateway and OpenTelemetry names).

Reconcile your bill

DeepInfra doesn't offer a cost API, so Veqen's ledger is your running record of spend. Enter each month's bill to reconcile it and book it in the close. How reconciliation works.

Prices come from DeepInfra's pricing page. Negotiated rates or committed-use discounts can be set as custom prices.

Text 136 models

ModelInputOutputCached inputBatch inputContextStatus
mistralai/Mistral-Nemo-Instruct-2407$0.019$0.03——131.1K
google/gemma-4-E4B-it$0.02$0.10——131.1K
meta-llama/Llama-3.2-3B-Instruct$0.02$0.02——131.1K
meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo$0.02$0.04——131.1K
meta-llama/Meta-Llama-3-8B-Instruct$0.03$0.06——8.2K
meta-llama/Meta-Llama-3.1-8B-Instruct$0.03$0.05——131.1K
openai/gpt-oss-20b$0.03$0.14——131.1K
openai/gpt-oss-120b$0.037$0.17——131.1K
Qwen/Qwen2.5-7B-Instruct$0.04$0.10——32.8K
Sao10K/L3-8B-Lunaris-v1-Turbo$0.04$0.05——8.2K
nvidia/NVIDIA-Nemotron-Nano-9B-v2$0.04$0.16——131.1K
meta-llama/Llama-3.2-11B-Vision-Instruct$0.049$0.049——131.1K
google/gemma-3-12b-it$0.05$0.15——131.1K
google/gemma-3-4b-it$0.05$0.10——131.1K
mistralai/Mistral-Small-24B-Instruct-2501$0.05$0.08——32.8K
nvidia/Nemotron-3-Nano-30B-A3B$0.05$0.20$0.025—262.1K
meta-llama/Llama-Guard-3-8B$0.055$0.055——131.1K
inclusionAI/Ling-3.0-flash$0.06$0.18$0.012—131.1K
zai-org/GLM-4.7-Flash$0.06$0.40$0.01—202.8K
google/gemma-4-26B-A4B-it$0.07$0.34——262.1K
microsoft/phi-4$0.07$0.14——16.4K
mistralai/Mistral-Small-3.2-24B-Instruct-2506$0.075$0.20——128K
Qwen/Qwen3-32B$0.08$0.28——41K
deepseek-ai/DeepSeek-V4-Flash-0731$0.08$0.18$0.016—1M
google/gemma-3-27b-it$0.08$0.16——131.1K
nvidia/NVIDIA-Nemotron-3.5-Lightning$0.08$0.20$0.04—262.1K
nvidia/NVIDIA-Nemotron-3-Super-120B-A12B$0.085$0.40——262.1K
Qwen/Qwen3-235B-A22B-Instruct-2507$0.09$0.55——262.1K
Qwen/Qwen3-Next-80B-A3B-Instruct$0.09$1.10——262.1K
deepseek-ai/DeepSeek-V4-Flash$0.09$0.18$0.018—1M
google/gemma-4-31B-it-turbo$0.09$0.34$0.05—262.1K
ByteDance/Seed-2.0-mini$0.10$0.40$0.02—256K
Qwen/Qwen3.5-9B$0.10$0.15——262.1K
Qwen/Qwen3.6-35B-A3B$0.10$0.95——262.1K
meta-llama/Llama-3.3-70B-Instruct-Turbo$0.10$0.32——131.1K
meta-llama/Llama-4-Scout-17B-16E-Instruct$0.10$0.30——327.7K
nvidia/Llama-3.3-Nemotron-Super-49B-v1.5$0.10$0.40——131.1K
Qwen/Qwen3-14B$0.12$0.24——41K
Qwen/Qwen3-30B-A3B$0.12$0.50——41K
google/gemma-4-31B-it$0.13$0.38——262.1K
Qwen/Qwen3-Next-80B-A3B-Thinking$0.14$1.40——262.1K
Qwen/Qwen3.5-35B-A3B$0.14$1.00$0.05—262.1K
deepseek-ai/DeepSeek-V4.1-Flash$0.14$0.42$0.0042—1M
deepseek-ai/DeepSeek-V4.1-Flash-1017$0.14$0.42$0.0042—1M
tencent/Hy3$0.14$0.58$0.035—262.1K
Qwen/QwQ-32B$0.15$0.40——131.1K
Qwen/Qwen3-VL-30B-A3B-Instruct$0.15$0.60——262.1K
openai/gpt-oss-120b-Turbo$0.15$0.60——131.1K
Qwen/Qwen3-235B-A22B$0.18$0.54——41K
meta-llama/Llama-Guard-4-12B$0.18$0.18——163.8K
Qwen/Qwen2.5-VL-32B-Instruct$0.20$0.60——128K
Qwen/Qwen3-VL-235B-A22B-Instruct$0.20$0.88$0.11—262.1K
deepseek-ai/DeepSeek-R1-Distill-Llama-70B$0.20$0.60——131.1K
meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8$0.20$0.80——1M
nvidia/Nemotron-Content-Safety-3.5$0.20$0.20——131.1K
openai/gpt-oss-120b-Ultra$0.20$0.95——131.1K
stepfun-ai/Step-3.7-Flash$0.20$1.15$0.04—262.1K
meta-llama/Llama-3.3-70B-Instruct$0.23$0.40——131.1K
deepseek-ai/DeepSeek-V3-0324$0.24$0.90$0.135—163.8K
ByteDance/Seed-1.8$0.25$2.00$0.05—256K
MiniMaxAI/MiniMax-M2.7$0.25$1.00$0.05—196.6K
deepseek-ai/DeepSeek-V3.1$0.25$0.95$0.216—163.8K
google/gemini-3.1-flash-lite$0.25$1.50——1M
Qwen/Qwen3.5-27B$0.26$2.60——262.1K
deepseek-ai/DeepSeek-V3.2$0.26$0.38$0.13—163.8K
allenai/olmOCR-7B-0725-FP8$0.27$1.50——16.4K
deepseek-ai/DeepSeek-R1-Distill-Qwen-32B$0.27$0.27——131.1K
deepseek-ai/DeepSeek-V3.1-Terminus$0.27$1.00$0.216—163.8K
google/gemma-4-31B-it-Ultra$0.27$0.76——131.1K
MiniMaxAI/MiniMax-M3$0.28$1.10$0.056—524.3K
Qwen/Qwen3.5-122B-A10B$0.29$2.40——262.1K
Qwen/Qwen3-235B-A22B-Thinking-2507$0.30$2.90——262.1K
Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo$0.30$1.00$0.10—262.1K
google/gemini-2.5-flash$0.30$2.50——1M
meta-models/Muse-Glimmer-30B$0.30$1.20$0.04—131.1K
Qwen/Qwen3.6-27B$0.32$3.20——262.1K
deepseek-ai/DeepSeek-V3$0.32$0.89——163.8K
Qwen/Qwen2.5-72B-Instruct$0.36$0.40——32.8K
MiniMaxAI/MiniMax-M2.7-Turbo$0.38$1.70$0.07—196.6K
Gryphe/MythoMax-L2-13b$0.40$0.40——4.1K
Qwen/Qwen3-Coder-480B-A35B-Instruct$0.40$1.60——262.1K
Qwen/Qwen3.8-27B$0.40$3.00$0.04—262.1K
XiaomiMiMo/MiMo-V2.5$0.40$2.00$0.08—262.1K
meta-llama/Meta-Llama-3.1-70B-Instruct$0.40$0.40——131.1K
meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo$0.40$0.40——131.1K
mistralai/Mixtral-8x7B-Instruct-v0.1$0.40$0.40——32.8K
zai-org/GLM-4.5$0.40$1.60——131.1K
zai-org/GLM-4.7$0.40$1.75$0.08—202.8K
Qwen/Qwen3.5-397B-A17B$0.45$3.00$0.22—262.1K
moonshotai/Kimi-K2.5$0.45$2.25$0.07—262.1K
thinkingmachines/Inkling-Small$0.45$1.20$0.10—524.3K
microsoft/WizardLM-2-8x22B$0.48$0.48——65.5K
ByteDance/Seed-2.0-code$0.50$3.00$0.10—256K
ByteDance/Seed-2.0-pro$0.50$3.00$0.10—256K
deepseek-ai/DeepSeek-R1-0528$0.50$2.15$0.40—163.8K
moonshotai/Kimi-K2-Instruct$0.50$2.00——131.1K
moonshotai/Kimi-K2-Instruct-0905$0.50$2.00$0.40—262.1K
nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B$0.50$2.20$0.10—262.1K
zai-org/GLM-4.6$0.50$2.00$0.10—202.8K
nvidia/Llama-3.1-Nemotron-70B-Instruct$0.60$0.60——131.1K
zai-org/GLM-5$0.60$2.08$0.12—202.8K
Sao10K/L3.3-70B-Euryale-v2.3$0.65$0.75——131.1K
moonshotai/Kimi-K2.7-Code$0.68$3.40$0.136—262.1K
NousResearch/Hermes-3-Llama-3.1-70B$0.70$0.70——131.1K
deepseek-ai/DeepSeek-R1$0.70$2.40——163.8K
google/gemini-3.7-flash$0.75$3.75——1M
moonshotai/Kimi-K2.6$0.75$3.50$0.15—262.1K
zai-org/GLM-5.2$0.75$2.40$0.14—1M
Sao10K/L3.1-70B-Euryale-v2.2$0.85$0.85——131.1K
thinkingmachines/Inkling$0.95$4.05$0.16—524.3K
NousResearch/Hermes-3-Llama-3.1-405B$1.00$1.00——131.1K
XiaomiMiMo/MiMo-V2.5-Pro$1.00$3.00$0.20—1M
anthropic/claude-haiku-4-5$1.00$5.00——200K
deepseek-ai/DeepSeek-R1-0528-Turbo$1.00$3.00——32.8K
deepseek-ai/DeepSeek-R1-Turbo$1.00$3.00——41K
zai-org/GLM-5.1$1.05$3.50$0.205—202.8K
Qwen/Qwen3-Max$1.20$6.00$0.24—256K
Qwen/Qwen3-Max-Thinking$1.20$6.00$0.24—256K
google/gemini-2.5-pro$1.25$10.00——1M
deepseek-ai/DeepSeek-V4-Pro$1.30$2.60$0.10—1M
deepseek-ai/DeepSeek-V4-Pro-0813$1.30$2.60$0.10—1M
google/gemini-3.5-flash$1.50$9.00——1M
Qwen/Qwen3.8-Max$1.65$4.951$0.206—256K
Qwen/Qwen3.8-2.4T-A95B$2.00$6.00$0.20—262.1K
anthropic/claude-sonnet-5$2.00$10.00——1M
google/gemini-3.1-pro$2.00$12.00——1M
Qwen/Qwen3.7-Max$2.50$7.50$0.50—256K
moonshotai/Kimi-K3$2.85$14.25$0.285—1M
anthropic/claude-sonnet-4-6$3.00$15.00——1M
anthropic/claude-3-7-sonnet-latest$3.30$16.50$0.33—200K
anthropic/claude-4-sonnet$3.30$16.50——200K
anthropic/claude-opus-4-7$5.00$25.00——1M
anthropic/claude-opus-4-8$5.00$25.00——1M
anthropic/claude-opus-5$5.00$25.00——1M
anthropic/claude-fable-5$10.00$50.00——1M
anthropic/claude-4-opus$16.50$82.50——200K