Overage / Compare / LLM APIs
Cerebras Inference vs DeepInfra pricing Monthly cost at three volumes Monthly cost of Cerebras Inference and DeepInfra at three volumes and at your own Volume Cerebras InferenceCheapest model GPT OSS 120B Qwen 3.8 27B DeepInfraCheapest model deepseek-ai/DeepSeek-V4-Flash-Vision-Exp DeepSeek-V4-Flash-0731 DeepSeek-V4-Pro DeepSeek-V4-Flash DeepSeek-V3.2 DeepSeek-V3.1 DeepSeek-V3 DeepSeek-R1-0528 Kimi-K3 Kimi-K2.6 Qwen3.6-27B Qwen3.6-35B-A3B Qwen3.5-397B-A17B Qwen3.5-35B-A3B Qwen3.5-27B Qwen3.5-9B Qwen3.8-Max Qwen3.7-Max Qwen3-VL-30B-A3B-Instruct Qwen3-VL-235B-A22B-Instruct Qwen3-Next-80B-A3B-Instruct Qwen3-Coder-480B-A35B-Instruct-Turbo Qwen3-235B-A22B-Instruct-2507 Qwen3-32B Qwen3-30B-A3B Qwen3-14B Qwen2.5-72B-Instruct Llama-4-Scout-17B-16E Llama-Guard-4-12B Llama-3.3-70B-Instruct-Turbo Meta-Llama-3.1-70B-Instruct-Turbo Meta-Llama-3.1-8B-Instruct-Turbo gemini-3.5-flash gemini-3.1-flash-lite gemini-3.1-pro gemini-2.5-pro gemini-2.5-flash gemma-4-31B-it-Ultra gemma-4-31B-it-turbo gemma-4-31B-it gemma-4-26B-A4B-it gemma-3-27b-it gemma-3-12b-it gemma-3-4b-it NVIDIA-Nemotron-3.5-Lightning NVIDIA-Nemotron-3.5-Super-VL Nemotron-Content-Safety-3.5 NVIDIA-Nemotron-3-Ultra-550B-A55B NVIDIA-Nemotron-3-Super-120B-A12B claude-opus-5 claude-fable-5 claude-sonnet-5 claude-haiku-4-5 claude-sonnet-4-6 claude-opus-4-7 claude-opus-4-8 phi-4 Mistral-Small-3.2-24B-Instruct-2506 Mistral-Small-24B-Instruct-2501 Mistral-Nemo-Instruct-2407 small1M input, 200K output $0.50 / moGPT OSS 120B $0.028 / moMeta-Llama-3.1-8B-Instruct-Turbo growing50M input, 10M output $25 / moGPT OSS 120B $1.40 / moMeta-Llama-3.1-8B-Instruct-Turbo scale1B input, 200M output $500 / moGPT OSS 120B $28 / moMeta-Llama-3.1-8B-Instruct-Turbo your volumeset above $25 / moGPT OSS 120B $1.40 / moMeta-Llama-3.1-8B-Instruct-Turbo
Each cell is the cheapest feasible plan, or the chosen model, at that volume, from the shared Overage cost function. "Cheapest model" only considers models with both an input and an output price listed. Volumes are example scenarios you can edit.
Cheapest model per service, USD per 1M tokens Cheapest priced model of each service Service Cheapest model Input Output Models listed Cerebras Inference GPT OSS 120B $0.35 $0.75 2 DeepInfra Meta-Llama-3.1-8B-Instruct-Turbo $0.02 $0.04 60
Every model Every model of both services, USD per 1M tokens Model Service Input Output GPT OSS 120B Cerebras Inference $0.35 $0.75 Qwen 3.8 27B Cerebras Inference $0.99 $1.49 Meta-Llama-3.1-8B-Instruct-Turbo DeepInfra $0.02 $0.04 Mistral-Nemo-Instruct-2407 DeepInfra $0.029 $0.03 gemma-3-12b-it DeepInfra $0.05 $0.15 gemma-3-4b-it DeepInfra $0.05 $0.10 Mistral-Small-24B-Instruct-2501 DeepInfra $0.05 $0.08 DeepSeek-V4-Flash-0731 DeepInfra $0.06 $0.18 NVIDIA-Nemotron-3.5-Lightning DeepInfra $0.06 $0.16 gemma-4-26B-A4B-it DeepInfra $0.07 $0.34 phi-4 DeepInfra $0.07 $0.14 Mistral-Small-3.2-24B-Instruct-2506 DeepInfra $0.075 $0.20 Qwen3-32B DeepInfra $0.08 $0.28 gemma-3-27b-it DeepInfra $0.08 $0.16 NVIDIA-Nemotron-3-Super-120B-A12B DeepInfra $0.085 $0.40 DeepSeek-V4-Flash DeepInfra $0.09 $0.18 Qwen3-Next-80B-A3B-Instruct DeepInfra $0.09 $1.10 Qwen3-235B-A22B-Instruct-2507 DeepInfra $0.09 $0.55 gemma-4-31B-it-turbo DeepInfra $0.09 $0.34 Qwen3.6-35B-A3B DeepInfra $0.10 $0.95 Qwen3.5-9B DeepInfra $0.10 $0.15 Llama-4-Scout-17B-16E DeepInfra $0.10 $0.30 Llama-3.3-70B-Instruct-Turbo DeepInfra $0.10 $0.32 Qwen3-30B-A3B DeepInfra $0.12 $0.50 Qwen3-14B DeepInfra $0.12 $0.24 Qwen3.5-35B-A3B DeepInfra $0.14 $1 Qwen3-VL-30B-A3B-Instruct DeepInfra $0.15 $0.60 NVIDIA-Nemotron-3.5-Super-VL DeepInfra $0.15 $0.50 Llama-Guard-4-12B DeepInfra $0.18 $0.18 Qwen3-VL-235B-A22B-Instruct DeepInfra $0.20 $0.88 gemma-4-31B-it DeepInfra $0.20 $0.40 Nemotron-Content-Safety-3.5 DeepInfra $0.20 $0.20 deepseek-ai/DeepSeek-V4-Flash-Vision-Exp DeepInfra $0.2156 $0.6468 DeepSeek-V3.1 DeepInfra $0.25 $0.95 gemini-3.1-flash-lite DeepInfra $0.25 $1.50 DeepSeek-V3.2 DeepInfra $0.26 $0.38 Qwen3.5-27B DeepInfra $0.26 $2.60 gemma-4-31B-it-Ultra DeepInfra $0.27 $0.76 Qwen3-Coder-480B-A35B-Instruct-Turbo DeepInfra $0.30 $1 gemini-2.5-flash DeepInfra $0.30 $2.50 DeepSeek-V3 DeepInfra $0.32 $0.89 Qwen3.6-27B DeepInfra $0.32 $3.20 Qwen2.5-72B-Instruct DeepInfra $0.36 $0.40 Meta-Llama-3.1-70B-Instruct-Turbo DeepInfra $0.40 $0.40 Qwen3.5-397B-A17B DeepInfra $0.45 $3 DeepSeek-R1-0528 DeepInfra $0.50 $2.15 NVIDIA-Nemotron-3-Ultra-550B-A55B DeepInfra $0.50 $2.20 Kimi-K2.6 DeepInfra $0.75 $3.50 claude-haiku-4-5 DeepInfra $1 $5 gemini-2.5-pro DeepInfra $1.25 $10 DeepSeek-V4-Pro DeepInfra $1.30 $2.60 gemini-3.5-flash DeepInfra $1.50 $9 Qwen3.8-Max DeepInfra $1.65 $4.951 gemini-3.1-pro DeepInfra $2 $12 Qwen3.7-Max DeepInfra $2.50 $7.50 Kimi-K3 DeepInfra $2.85 $14.25 claude-sonnet-5 DeepInfra $3 $15 claude-sonnet-4-6 DeepInfra $3 $15 claude-opus-5 DeepInfra $5 $25 claude-opus-4-7 DeepInfra $5 $25 claude-opus-4-8 DeepInfra $5 $25 claude-fable-5 DeepInfra $10 $50
Models are compared by name and price, never by position. Pick one model per service, or "Cheapest model", in the cost table above.
Tiers, aligned by position Tiers of Cerebras Inference and DeepInfra aligned by position: free, entry, mid, top Position Cerebras Inference DeepInfra Free no tier no tier Entry unlisted Developer* no tier Mid no tier no tier Top Contact sales Enterprise no tier
Tightest rate limit Tightest documented rate limit of each service Measure Cerebras Inference DeepInfra Tightest limit unlisted unlisted
Changes in the last 90 days No changes recorded.
No change detected for either service in the last 90 days.