- Models
- 38
- listed and live
- Location
- Non-EU
- where requests are served
- Trains on prompts
- Not declared
- nothing published yet
- Keeps prompts
- Not declared
- nothing published yet
Models
What DeepInfra serves on llm.buzz, at its own prices.
| Model | Input | Output | Cache read | Context | Latency | Uptime (3d) |
|---|---|---|---|---|---|---|
baai/bge-base-en-v1.5 | $0.005 | n/a | n/a | 512 | n/a | n/a |
baai/bge-large-en-v1.5 | $0.01 | n/a | n/a | 512 | n/a | n/a |
baai/bge-m3 | $0.01 | n/a | n/a | 8K | n/a | n/a |
black-forest-labs/flux.2-klein-4b | n/a | $0.014/image | n/a | n/a | n/a | n/a |
black-forest-labs/flux.2-max | n/a | $0.07/image | n/a | n/a | n/a | n/a |
black-forest-labs/flux.2-pro | n/a | $0.03/image | n/a | n/a | n/a | n/a |
 deepseek/deepseek-v4-flash-0731 | $0.06 | $0.18 | $0.015 | 1M | 0.69 s | 100% |
deepseek/deepseek-v4-flash-vision-exp | $0.44 | $1.32 | $0.014 | 1M | 0.83 s | 100% |
deepseek/deepseek-v4-pro-0813 | $1.30 | $2.60 | $0.10 | 1M | 1.20 s | 100% |
deepseek/deepseek-v4.1-flash | $0.20 | $0.60 | $0.006 | 1M | 0.58 s | 100% |
deepseek/deepseek-v4.1-flash-1017 | $0.20 | $0.60 | $0.006 | 1M | 0.69 s | 98.6% |
 google/gemini-3-pro-image | n/a | $0.1344/image | n/a | n/a | n/a | n/a |
google/gemini-3.1-flash-image | n/a | $0.0672/image | n/a | n/a | n/a | n/a |
google/gemini-3.1-flash-lite-image | n/a | $0.0336/image | n/a | n/a | n/a | n/a |
google/gemma-4-26b-a4b-it | $0.07 | $0.34 | n/a | 256K | 0.69 s | 100% |
google/gemma-4-31b-it | $0.20 | $0.40 | n/a | 256K | 0.69 s | 100% |
hexgrad/kokoro-82m | $0.99/M characters | n/a | n/a | n/a | n/a | n/a |
intfloat/e5-base-v2 | $0.005 | n/a | n/a | 512 | n/a | n/a |
intfloat/e5-large-v2 | $0.01 | n/a | n/a | 512 | n/a | n/a |
intfloat/multilingual-e5-large | $0.01 | n/a | n/a | 512 | n/a | n/a |
 moonshotai/kimi-k3 | $2.85 | $14.25 | $0.285 | 1M | 0.83 s | 100% |
 nvidia/nemotron-3-super-120b-a12b | $0.085 | $0.40 | n/a | 256K | 1.44 s | 52.1% |
 openai/whisper-large-v3 | $7.50/M seconds | n/a | n/a | n/a | n/a | n/a |
openai/whisper-large-v3-turbo | $3.33/M seconds | n/a | n/a | n/a | n/a | n/a |
 qwen/qwen3-embedding-4b | $0.02 | n/a | n/a | 32K | n/a | n/a |
qwen/qwen3-embedding-8b | $0.01 | n/a | n/a | 32K | n/a | n/a |
qwen/qwen3.6-35b-a3b | $0.10 | $0.95 | n/a | 256K | 0.69 s | 100% |
qwen/qwen3.8-27b | $0.20 | $2.50 | $0.05 | 256K | 0.83 s | 93% |
sentence-transformers/all-minilm-l12-v2 | $0.005 | n/a | n/a | 512 | n/a | n/a |
sentence-transformers/all-minilm-l6-v2 | $0.005 | n/a | n/a | 512 | n/a | n/a |
sentence-transformers/all-mpnet-base-v2 | $0.005 | n/a | n/a | 512 | n/a | n/a |
sentence-transformers/multi-qa-mpnet-base-dot-v1 | $0.005 | n/a | n/a | 512 | n/a | n/a |
sentence-transformers/paraphrase-minilm-l6-v2 | $0.005 | n/a | n/a | 512 | n/a | n/a |
thenlper/gte-base | $0.005 | n/a | n/a | 512 | n/a | n/a |
thenlper/gte-large | $0.01 | n/a | n/a | 512 | n/a | n/a |
 xiaomi/mimo-v2.6-flash | $0.14 | $0.28 | $0.0028 | 1M | 8.89 s | 97.3% |
xiaomi/mimo-v2.6-pro | $0.43 | $0.87 | $0.0036 | 1M | 1.20 s | 95.8% |
 z-ai/glm-5.3-flash | $0.15 | $0.50 | $0.03 | 1M | 0.83 s | 93% |
DeepInfra's own prices, in USD per million tokens unless a price names another unit. Latency is the median time to first token over 24 hours.
Call DeepInfra's models with one keyThe same key reaches every provider here; each request pays the price of the provider that answered it.