↑↓ move↵ openesc close

Overage / LLM APIs

DeepInfra pricing and rate limits

LLM APIsdeepinfra.comReport a correctionChange history (0)

Verified 2026-10-24 (1 day ago)Source: deepinfra.com/pricing

Models and cost at your volume

deepseek-ai/DeepSeek-V4-Flash-Vision-Exp: $0.34496 / mo base $0 + Input tokens overage $0.2156 + Output tokens overage $0.12936

Uses the shared Overage cost function. Example volumes you can edit, not vendor data. Cached, batch and cache-write prices are listed below but not added to this total.

DeepInfra models, USD per 1M tokens, sortable
deepseek-ai/DeepSeek-V4-Flash-Vision-Expunlisted$0.2156$0.2156 source$0.6468$0.6468 source$0.0069$0.0069 sourceunlistedunlistedunlisted$0.34496
DeepSeek-V4-Flash-07311.024M$0.06DeepSeek-V4-Flash-0731 | 1024k | $0.06 / $0.015 cached | $0.18 source$0.18DeepSeek-V4-Flash-0731 | 1024k | $0.06 / $0.015 cached | $0.18 source$0.015DeepSeek-V4-Flash-0731 | 1024k | $0.06 / $0.015 cached | $0.18 sourceunlistedunlistedunlisted$0.096
DeepSeek-V4-Pro1.024M$1.30DeepSeek-V4-Pro | 1024k | $1.30 / $0.10 cached | $2.60 source$2.60DeepSeek-V4-Pro | 1024k | $1.30 / $0.10 cached | $2.60 source$0.10DeepSeek-V4-Pro | 1024k | $1.30 / $0.10 cached | $2.60 sourceunlistedunlistedunlisted$1.82
DeepSeek-V4-Flash1.024M$0.09DeepSeek-V4-Flash | 1024k | $0.09 / $0.018 cached | $0.18 source$0.18DeepSeek-V4-Flash | 1024k | $0.09 / $0.018 cached | $0.18 source$0.018DeepSeek-V4-Flash | 1024k | $0.09 / $0.018 cached | $0.18 sourceunlistedunlistedunlisted$0.126
DeepSeek-V3.2unlisted$0.26DeepSeek-V3.2 | - | $0.26 / $0.13 cached | $0.38 source$0.38DeepSeek-V3.2 | - | $0.26 / $0.13 cached | $0.38 source$0.13DeepSeek-V3.2 | - | $0.26 / $0.13 cached | $0.38 sourceunlistedunlistedunlisted$0.336
DeepSeek-V3.1160K$0.25DeepSeek-V3.1 | 160k | $0.25 / $0.13 cached | $0.95 source$0.95DeepSeek-V3.1 | 160k | $0.25 / $0.13 cached | $0.95 source$0.13DeepSeek-V3.1 | 160k | $0.25 / $0.13 cached | $0.95 sourceunlistedunlistedunlisted$0.44
DeepSeek-V3160K$0.32DeepSeek-V3 | 160k | $0.32 | $0.89 source$0.89DeepSeek-V3 | 160k | $0.32 | $0.89 sourceunlistedunlistedunlistedunlisted$0.498
DeepSeek-R1-0528160K$0.50DeepSeek-R1-0528 | 160k | $0.50 / $0.35 cached | $2.15 source$2.15DeepSeek-R1-0528 | 160k | $0.50 / $0.35 cached | $2.15 source$0.35DeepSeek-R1-0528 | 160k | $0.50 / $0.35 cached | $2.15 sourceunlistedunlistedunlisted$0.93
Kimi-K31.024M$2.85Kimi-K3 | 1024k | $2.85 / $0.285 cached | $14.25 source$14.25Kimi-K3 | 1024k | $2.85 / $0.285 cached | $14.25 source$0.285Kimi-K3 | 1024k | $2.85 / $0.285 cached | $14.25 sourceunlistedunlistedunlisted$5.70
Kimi-K2.6256K$0.75Kimi-K2.6 | 256k | $0.75 / $0.15 cached | $3.50 source$3.50Kimi-K2.6 | 256k | $0.75 / $0.15 cached | $3.50 source$0.15Kimi-K2.6 | 256k | $0.75 / $0.15 cached | $3.50 sourceunlistedunlistedunlisted$1.45
Qwen3.6-27B256K$0.32Qwen3.6-27B | 256k | $0.32 | $3.20 source$3.20Qwen3.6-27B | 256k | $0.32 | $3.20 sourceunlistedunlistedunlistedunlisted$0.96
Qwen3.6-35B-A3B256K$0.10Qwen3.6-35B-A3B | 256k | $0.10 / $0.10 cached | $0.95 source$0.95Qwen3.6-35B-A3B | 256k | $0.10 / $0.10 cached | $0.95 source$0.10Qwen3.6-35B-A3B | 256k | $0.10 / $0.10 cached | $0.95 sourceunlistedunlistedunlisted$0.29
Qwen3.5-397B-A17B256K$0.45Qwen3.5-397B-A17B | 256k | $0.45 / $0.22 cached | $3.00 source$3Qwen3.5-397B-A17B | 256k | $0.45 / $0.22 cached | $3.00 source$0.22Qwen3.5-397B-A17B | 256k | $0.45 / $0.22 cached | $3.00 sourceunlistedunlistedunlisted$1.05
Qwen3.5-35B-A3B256K$0.14Qwen3.5-35B-A3B | 256k | $0.14 / $0.05 cached | $1.00 source$1Qwen3.5-35B-A3B | 256k | $0.14 / $0.05 cached | $1.00 source$0.05Qwen3.5-35B-A3B | 256k | $0.14 / $0.05 cached | $1.00 sourceunlistedunlistedunlisted$0.34
Qwen3.5-27B256K$0.26Qwen3.5-27B | 256k | $0.26 | $2.60 source$2.60Qwen3.5-27B | 256k | $0.26 | $2.60 sourceunlistedunlistedunlistedunlisted$0.78
Qwen3.5-9B256K$0.10Qwen3.5-9B | 256k | $0.10 | $0.15 source$0.15Qwen3.5-9B | 256k | $0.10 | $0.15 sourceunlistedunlistedunlistedunlisted$0.13
Qwen3.8-Max250K$1.65Qwen3.8-Max | 250k | $1.65 / $0.206 cached | $4.951 source$4.951Qwen3.8-Max | 250k | $1.65 / $0.206 cached | $4.951 source$0.206Qwen3.8-Max | 250k | $1.65 / $0.206 cached | $4.951 sourceunlistedunlistedunlisted$2.6402
Qwen3.7-Max250K$2.50Qwen3.7-Max | 250k | $2.50 / $0.50 cached | $7.50 source$7.50Qwen3.7-Max | 250k | $2.50 / $0.50 cached | $7.50 source$0.50Qwen3.7-Max | 250k | $2.50 / $0.50 cached | $7.50 sourceunlistedunlistedunlisted$4
Qwen3-VL-30B-A3B-Instruct256K$0.15Qwen3-VL-30B-A3B-Instruct | 256k | $0.15 | $0.60 source$0.60Qwen3-VL-30B-A3B-Instruct | 256k | $0.15 | $0.60 sourceunlistedunlistedunlistedunlisted$0.27
Qwen3-VL-235B-A22B-Instruct256K$0.20Qwen3-VL-235B-A22B-Instruct | 256k | $0.20 / $0.11 cached | $0.88 source$0.88Qwen3-VL-235B-A22B-Instruct | 256k | $0.20 / $0.11 cached | $0.88 source$0.11Qwen3-VL-235B-A22B-Instruct | 256k | $0.20 / $0.11 cached | $0.88 sourceunlistedunlistedunlisted$0.376
Qwen3-Next-80B-A3B-Instruct256K$0.09Qwen3-Next-80B-A3B-Instruct | 256k | $0.09 | $1.10 source$1.10Qwen3-Next-80B-A3B-Instruct | 256k | $0.09 | $1.10 sourceunlistedunlistedunlistedunlisted$0.31
Qwen3-Coder-480B-A35B-Instruct-Turbo256K$0.30Qwen3-Coder-480B-A35B-Instruct-Turbo | 256k | $0.30 / $0.10 cached | $1.00 source$1Qwen3-Coder-480B-A35B-Instruct-Turbo | 256k | $0.30 / $0.10 cached | $1.00 source$0.10Qwen3-Coder-480B-A35B-Instruct-Turbo | 256k | $0.30 / $0.10 cached | $1.00 sourceunlistedunlistedunlisted$0.50
Qwen3-235B-A22B-Instruct-2507256K$0.09Qwen3-235B-A22B-Instruct-2507 | 256k | $0.09 | $0.55 source$0.55Qwen3-235B-A22B-Instruct-2507 | 256k | $0.09 | $0.55 sourceunlistedunlistedunlistedunlisted$0.20
Qwen3-32B40K$0.08Qwen3-32B | 40k | $0.08 | $0.28 source$0.28Qwen3-32B | 40k | $0.08 | $0.28 sourceunlistedunlistedunlistedunlisted$0.136
Qwen3-30B-A3B40K$0.12Qwen3-30B-A3B | 40k | $0.12 | $0.50 source$0.50Qwen3-30B-A3B | 40k | $0.12 | $0.50 sourceunlistedunlistedunlistedunlisted$0.22
Qwen3-14B40K$0.12Qwen3-14B | 40k | $0.12 | $0.24 source$0.24Qwen3-14B | 40k | $0.12 | $0.24 sourceunlistedunlistedunlistedunlisted$0.168
Qwen2.5-72B-Instruct32K$0.36Qwen2.5-72B-Instruct | 32k | $0.36 | $0.40 source$0.40Qwen2.5-72B-Instruct | 32k | $0.36 | $0.40 sourceunlistedunlistedunlistedunlisted$0.44
Llama-4-Scout-17B-16E320K$0.10Llama-4-Scout-17B-16E | 320k | $0.10 | $0.30 source$0.30Llama-4-Scout-17B-16E | 320k | $0.10 | $0.30 sourceunlistedunlistedunlistedunlisted$0.16
Llama-Guard-4-12B160K$0.18Llama-Guard-4-12B | 160k | $0.18 | $0.18 source$0.18Llama-Guard-4-12B | 160k | $0.18 | $0.18 sourceunlistedunlistedunlistedunlisted$0.216
Llama-3.3-70B-Instruct-Turbo128K$0.10Llama-3.3-70B-Instruct-Turbo | 128k | $0.10 | $0.32 source$0.32Llama-3.3-70B-Instruct-Turbo | 128k | $0.10 | $0.32 sourceunlistedunlistedunlistedunlisted$0.164
Meta-Llama-3.1-70B-Instruct-Turbo128K$0.40Meta-Llama-3.1-70B-Instruct-Turbo | 128k | $0.40 | $0.40 source$0.40Meta-Llama-3.1-70B-Instruct-Turbo | 128k | $0.40 | $0.40 sourceunlistedunlistedunlistedunlisted$0.48
Meta-Llama-3.1-8B-Instruct-Turbo128K$0.02Meta-Llama-3.1-8B-Instruct-Turbo | 128k | $0.02 | $0.04 source$0.04Meta-Llama-3.1-8B-Instruct-Turbo | 128k | $0.02 | $0.04 sourceunlistedunlistedunlistedunlisted$0.028
gemini-3.5-flash976K$1.50gemini-3.5-flash | 976k | $1.50 | $9.00 source$9gemini-3.5-flash | 976k | $1.50 | $9.00 sourceunlistedunlistedunlistedunlisted$3.30
gemini-3.1-flash-lite976K$0.25gemini-3.1-flash-lite | 976k | $0.25 | $1.50 source$1.50gemini-3.1-flash-lite | 976k | $0.25 | $1.50 sourceunlistedunlistedunlistedunlisted$0.55
gemini-3.1-pro976K$2gemini-3.1-pro | 976k | $2.00 | $12.00 source$12gemini-3.1-pro | 976k | $2.00 | $12.00 sourceunlistedunlistedunlistedunlisted$4.40
gemini-2.5-pro976K$1.25gemini-2.5-pro | 976k | $1.25 | $10.00 source$10gemini-2.5-pro | 976k | $1.25 | $10.00 sourceunlistedunlistedunlistedunlisted$3.25
gemini-2.5-flash976K$0.30gemini-2.5-flash | 976k | $0.30 | $2.50 source$2.50gemini-2.5-flash | 976k | $0.30 | $2.50 sourceunlistedunlistedunlistedunlisted$0.80
gemma-4-31B-it-Ultra128K$0.27gemma-4-31B-it-Ultra | 128k | $0.27 | $0.76 source$0.76gemma-4-31B-it-Ultra | 128k | $0.27 | $0.76 sourceunlistedunlistedunlistedunlisted$0.422
gemma-4-31B-it-turbo256K$0.09gemma-4-31B-it-turbo | 256k | $0.09 / $0.05 cached | $0.34 source$0.34gemma-4-31B-it-turbo | 256k | $0.09 / $0.05 cached | $0.34 source$0.05gemma-4-31B-it-turbo | 256k | $0.09 / $0.05 cached | $0.34 sourceunlistedunlistedunlisted$0.158
gemma-4-31B-it256K$0.20gemma-4-31B-it | 256k | $0.20 | $0.40 source$0.40gemma-4-31B-it | 256k | $0.20 | $0.40 sourceunlistedunlistedunlistedunlisted$0.28
gemma-4-26B-A4B-it256K$0.07gemma-4-26B-A4B-it | 256k | $0.07 | $0.34 source$0.34gemma-4-26B-A4B-it | 256k | $0.07 | $0.34 sourceunlistedunlistedunlistedunlisted$0.138
gemma-3-27b-it128K$0.08gemma-3-27b-it | 128k | $0.08 | $0.16 source$0.16gemma-3-27b-it | 128k | $0.08 | $0.16 sourceunlistedunlistedunlistedunlisted$0.112
gemma-3-12b-it128K$0.05gemma-3-12b-it | 128k | $0.05 | $0.15 source$0.15gemma-3-12b-it | 128k | $0.05 | $0.15 sourceunlistedunlistedunlistedunlisted$0.08
gemma-3-4b-it128K$0.05gemma-3-4b-it | 128k | $0.05 | $0.10 source$0.10gemma-3-4b-it | 128k | $0.05 | $0.10 sourceunlistedunlistedunlistedunlisted$0.07
NVIDIA-Nemotron-3.5-Lightning256K$0.06NVIDIA-Nemotron-3.5-Lightning | 256k | $0.06 / $0.03 cached | $0.16 source$0.16NVIDIA-Nemotron-3.5-Lightning | 256k | $0.06 / $0.03 cached | $0.16 source$0.03NVIDIA-Nemotron-3.5-Lightning | 256k | $0.06 / $0.03 cached | $0.16 sourceunlistedunlistedunlisted$0.092
NVIDIA-Nemotron-3.5-Super-VL256K$0.15NVIDIA-Nemotron-3.5-Super-VL | 256k | $0.15 / $0.02 cached | $0.50 source$0.50NVIDIA-Nemotron-3.5-Super-VL | 256k | $0.15 / $0.02 cached | $0.50 source$0.02NVIDIA-Nemotron-3.5-Super-VL | 256k | $0.15 / $0.02 cached | $0.50 sourceunlistedunlistedunlisted$0.25
Nemotron-Content-Safety-3.5128K$0.20Nemotron-Content-Safety-3.5 | 128k | $0.20 | $0.20 source$0.20Nemotron-Content-Safety-3.5 | 128k | $0.20 | $0.20 sourceunlistedunlistedunlistedunlisted$0.24
NVIDIA-Nemotron-3-Ultra-550B-A55B256K$0.50NVIDIA-Nemotron-3-Ultra-550B-A55B | 256k | $0.50 / $0.10 cached | $2.20 source$2.20NVIDIA-Nemotron-3-Ultra-550B-A55B | 256k | $0.50 / $0.10 cached | $2.20 source$0.10NVIDIA-Nemotron-3-Ultra-550B-A55B | 256k | $0.50 / $0.10 cached | $2.20 sourceunlistedunlistedunlisted$0.94
NVIDIA-Nemotron-3-Super-120B-A12B256K$0.085NVIDIA-Nemotron-3-Super-120B-A12B | 256k | $0.085 | $0.40 source$0.40NVIDIA-Nemotron-3-Super-120B-A12B | 256k | $0.085 | $0.40 sourceunlistedunlistedunlistedunlisted$0.165
claude-opus-5976K$5claude-opus-5 | 976k | $5.00 | $25.00 source$25claude-opus-5 | 976k | $5.00 | $25.00 sourceunlistedunlistedunlistedunlisted$10
claude-fable-5976K$10claude-fable-5 | 976k | $10.00 | $50.00 source$50claude-fable-5 | 976k | $10.00 | $50.00 sourceunlistedunlistedunlistedunlisted$20
claude-sonnet-5976K$3claude-sonnet-5 | 976k | $3.00 | $15.00 source$15claude-sonnet-5 | 976k | $3.00 | $15.00 sourceunlistedunlistedunlistedunlisted$6
claude-haiku-4-5195K$1claude-haiku-4-5 | 195k | $1.00 | $5.00 source$5claude-haiku-4-5 | 195k | $1.00 | $5.00 sourceunlistedunlistedunlistedunlisted$2
claude-sonnet-4-6976K$3claude-sonnet-4-6 | 976k | $3.00 | $15.00 source$15claude-sonnet-4-6 | 976k | $3.00 | $15.00 sourceunlistedunlistedunlistedunlisted$6
claude-opus-4-7976K$5claude-opus-4-7 | 976k | $5.00 | $25.00 source$25claude-opus-4-7 | 976k | $5.00 | $25.00 sourceunlistedunlistedunlistedunlisted$10
claude-opus-4-8976K$5claude-opus-4-8 | 976k | $5.00 | $25.00 source$25claude-opus-4-8 | 976k | $5.00 | $25.00 sourceunlistedunlistedunlistedunlisted$10
phi-416K$0.07phi-4 | 16k | $0.07 | $0.14 source$0.14phi-4 | 16k | $0.07 | $0.14 sourceunlistedunlistedunlistedunlisted$0.098
Mistral-Small-3.2-24B-Instruct-2506125K$0.075Mistral-Small-3.2-24B-Instruct-2506 | 125k | $0.075 | $0.20 source$0.20Mistral-Small-3.2-24B-Instruct-2506 | 125k | $0.075 | $0.20 sourceunlistedunlistedunlistedunlisted$0.115
Mistral-Small-24B-Instruct-250132K$0.05Mistral-Small-24B-Instruct-2501 | 32k | $0.05 | $0.08 source$0.08Mistral-Small-24B-Instruct-2501 | 32k | $0.05 | $0.08 sourceunlistedunlistedunlistedunlisted$0.066
Mistral-Nemo-Instruct-2407128K$0.029Mistral-Nemo-Instruct-2407 | 128k | $0.029 | $0.03 source$0.03Mistral-Nemo-Instruct-2407 | 128k | $0.029 | $0.03 sourceunlistedunlistedunlistedunlisted$0.035

USD per 1M tokens. "+" marks a model whose price changes with volume; the standard band is shown. Context in tokens (60 models).

Prices in USD, per the vendor's billing period. Hover or focus a number for the line it came from, with a link to the stored snapshot. "unlisted" means the vendor does not publish it; we never fill the gap.

Rate limits

No rate limits recorded for this service: unlisted.

Change timeline

No changes recorded.

Tracking began 2026-10-24; no change has been detected since.

Sources

Captured source pages and their last snapshot
URLKindLast capturedSnapshot
deepinfra.com/pricingpricing2026-10-24snap_deepinfra-pricing-0_20261024T024537Z

Report a correction

Spotted a wrong or missing number on DeepInfra? Send the field, the value you see and a source link. Reports with a source are reviewed first.