vsDeepInfra vs Fireworks AI
Compare pricing across 36 shared models. DeepInfra offers 68 models, Fireworks AI offers 213.
8 Ways to Use Fewer Tokens
Get the free PDF guide — practical tips to cut your token usage and API costs. Subscribe to the Price Per Token newsletter and download instantly.
36
Shared Models
28
DeepInfra Cheaper
7
Fireworks AI Cheaper
1
Same Price
Price Comparison — Shared Models
| Model ↑ | DeepInfra Input | Fireworks AI Input | DeepInfra Output | Fireworks AI Output | Cheaper |
|---|---|---|---|---|---|
| DeepSeek V4 Flash (Non-Reasoning) | $0.135 | $0.070 | $0.270 | $0.140 | Fireworks AI |
| DeepSeek V4.1 Flash | $0.200 | $0.300 | $0.600 | $1.20 | DeepInfra |
| deepseek-deepseek-v4.1-flash-1017 | $0.098 | $0.300 | $0.294 | $1.20 | DeepInfra |
| Gemma 3 12B | $0.075 | $0.200 | $0.225 | $0.200 | DeepInfra |
| Gemma 3 27B | $0.080 | $0.900 | $0.160 | $0.900 | DeepInfra |
| Gemma 3 4B | $0.050 | $0.200 | $0.100 | $0.200 | DeepInfra |
| Gemma 4 26B A4B Instruct | $0.070 | $0.900 | $0.340 | $0.900 | DeepInfra |
| Gemma 4 31B Instruct | $0.300 | $0.900 | $0.600 | $0.900 | DeepInfra |
| GLM-5.3 | $0.563 | $1.40 | $2.50 | $4.40 | DeepInfra |
| GLM-5.3 Flash | $0.101 | $0.225 | $0.335 | $0.750 | DeepInfra |
| GPT-OSS-120b | $0.037 | $0.100 | $0.170 | $0.100 | Fireworks AI |
| GPT-OSS-20b | $0.030 | $0.100 | $0.140 | $0.100 | DeepInfra |
| Kimi K3 | $2.85 | $3.00 | $14.25 | $15.00 | DeepInfra |
| Kimi K3.1 Pro | $2.00 | $2.00 | $10.00 | $10.00 | Same |
| Llama 3.1 8B Instruct | $0.020 | $0.200 | $0.040 | $0.200 | DeepInfra |
| Llama 3.3 70B Instruct | $0.100 | $0.900 | $0.320 | $0.900 | DeepInfra |
| Mistral Small 24B Instruct 2501 | $0.040 | $0.900 | $0.064 | $0.900 | DeepInfra |
| Muse Glimmer 30B | $0.300 | $0.900 | $1.20 | $0.900 | DeepInfra |
| Nemotron 3 Super 120B A12B | $0.075 | $0.900 | $0.400 | $0.900 | DeepInfra |
| Nemotron 3.5 Lightning | $0.060 | $0.050 | $0.160 | $0.200 | DeepInfra |
| Qwen2.5 72B Instruct | $0.288 | $0.900 | $0.320 | $0.900 | DeepInfra |
| Qwen3 14B | $0.180 | $0.200 | $0.360 | $0.200 | Fireworks AI |
| Qwen3 235B A22B Instruct 2507 | $0.135 | $0.900 | $0.825 | $0.900 | DeepInfra |
| Qwen3 30B A3B | $0.180 | $0.900 | $0.750 | $0.900 | DeepInfra |
| Qwen3 32B | $0.064 | $0.900 | $0.224 | $0.900 | DeepInfra |
| Qwen3 Coder 480B A35B (exacto) | $0.300 | $0.900 | $1.00 | $0.900 | DeepInfra |
| Qwen3 Next 80B A3B Instruct | $0.090 | $0.900 | $1.10 | $0.900 | DeepInfra |
| Qwen3 VL 235B A22B Instruct | $0.200 | $0.900 | $0.880 | $0.900 | DeepInfra |
| Qwen3 VL 30B A3B Instruct | $0.150 | $0.900 | $0.600 | $0.900 | DeepInfra |
| Qwen3.5 397B A17B | $0.675 | $0.900 | $4.50 | $0.900 | Fireworks AI |
| Qwen3.5 9B | $0.080 | $0.200 | $0.120 | $0.200 | DeepInfra |
| Qwen3.5-27B | $0.260 | $0.900 | $2.60 | $0.900 | Fireworks AI |
| Qwen3.5-35B-A3B | $0.112 | $0.900 | $0.800 | $0.900 | DeepInfra |
| Qwen3.6 27B | $0.480 | $0.900 | $4.80 | $0.900 | Fireworks AI |
| Qwen3.6 35B A3B | $0.100 | $0.900 | $0.950 | $0.900 | DeepInfra |
| Qwen3.8 27B | $0.150 | $0.900 | $1.88 | $0.900 | Fireworks AI |
Model Coverage
Only on DeepInfra(32)DeepSeek V3$0.320/M
DeepSeek V3.1$0.250/M
DeepSeek V3.2$0.260/M
DeepSeek V4 Pro$1.30/M
deepseek-deepseek-v4-flash-0731$0.060/M
GLM 4.6$0.500/M
GLM 4.7$0.320/M
GLM-5.2$0.750/M
Granite 4.2 8B$0.060/M
HY4 Preview$0.834/M
Inkling 2 Small$0.285/M
Inkling Small$0.450/M
Kimi K2.6$0.750/M
Ling 3.0 Flash$0.060/M
Ling 3.0 Flash VL$0.060/M
Llama 3 8B Lunaris$0.040/M
Llama 3.1 Euryale 70B v2.2$0.850/M
Llama 4 Scout$0.150/M
meta-llama-llama-guard-4-12b$0.270/M
MiMo v2.6 Flash$0.140/M
MiMo v2.6 Pro$0.430/M
MiniMax M3$0.280/M
Mistral Nemo$0.029/M
Mistral Small 3.2 24B$0.075/M
Nemotron 3 Ultra 550B A55B$0.400/M
Nemotron 3.5 Super VL$0.150/M
Nemotron-3 Super 120B A12B$0.075/M
Phi 4$0.070/M
R1 0528$0.500/M
Shared(36)
36
models available on both
DeepInfraFireworks AI
68 total212 total
Chronos Hermes 13B v2$0.200/M
Code Llama 13B$0.200/M
Code Llama 13B Instruct$0.200/M
Code Llama 13B Python$0.200/M
Code Llama 34B$0.900/M
Code Llama 34B Instruct$0.900/M
Code Llama 34B Python$0.900/M
Code Llama 70B$0.900/M
Code Llama 70B Instruct$0.900/M
Code Llama 70B Python$0.900/M
Code Llama 7B$0.200/M
Code Llama 7B Instruct$0.200/M
CodeGemma 2B$0.100/M
CodeGemma 7B$0.200/M
CodeQwen 1.5 7B$0.200/M
Cogito v1 Preview Llama 3B$0.100/M
Cogito v1 Preview Llama 70B$0.900/M
Cogito v1 Preview Llama 8B$0.200/M
Cogito v1 Preview Qwen 14B$0.200/M
Cogito v1 Preview Qwen 32B$0.900/M
Cogito v2.1 671B$0.900/M
DeepSeek Coder 1.3B Base$0.100/M
DeepSeek Coder 33B Instruct$0.900/M
DeepSeek Coder 7B Base$0.200/M
DeepSeek Coder 7B Base v1.5$0.200/M
DeepSeek Coder 7B Instruct v1.5$0.200/M
DeepSeek R1 0528 Qwen3 8B$0.200/M
Devstral 2 2512$0.900/M
Dolphin 2.6 Mixtral 8x7B$0.500/M
Dolphin 2.9.2 Qwen2 72B$0.900/M
Ember 1$3.00/M
ERNIE 4.5 21B A3B$0.900/M
ERNIE 4.5 300B A47B$0.900/M
FARE 20B$0.900/M
Gemma 2 9B$0.200/M
Gemma 2B$0.100/M
Gemma 3 1B$0.100/M
Gemma 4 E4B IT$0.200/M
Gemma 7B$0.200/M
Gemma 7B Instruct$0.200/M
Hermes 2 Pro Mistral 7B$0.200/M
InternVL3 38B$0.900/M
InternVL3 78B$0.900/M
InternVL3 8B$0.200/M
KAT Dev 32B$0.900/M
Kimi K2 Thinking$0.600/M
Llama 2 13B$0.200/M
Llama 2 13B Chat$0.200/M
Llama 2 70B$0.900/M
Llama 2 7B$0.200/M
Llama 2 7B Chat$0.200/M
Llama 3 70B Instruct$0.900/M
Llama 3 70B Instruct (HF)$0.900/M
Llama 3 8B$0.200/M
Llama 3 8B Instruct$0.200/M
Llama 3 8B Instruct (HF)$0.200/M
Llama 3.1 70B Instruct$0.900/M
Llama 3.1 70B Instruct 1B$0.900/M
Llama 3.1 Nemotron 70B Instruct$0.900/M
Llama 3.2 11B Vision Instruct$0.200/M
Llama 3.2 1B$0.100/M
Llama 3.2 1B Instruct$0.100/M
Llama 3.2 3B$0.100/M
Llama 3.2 3B Instruct$0.100/M
Llama 3.2 90B Vision Instruct$0.900/M
MedGemma 27B$0.900/M
meta-llama-llama-guard-2-8b$0.200/M
meta-llama-llama-guard-3-1b$0.100/M
meta-llama-llama-guard-3-8b$0.200/M
meta-llama-llamaguard-7b$0.200/M
MiniMax-M3.1 Flash$0.150/M
Ministral 3 14B 2512$0.200/M
Ministral 3 3B 2512$0.100/M
Ministral 3 8B 2512$0.200/M
Mistral 7B$0.200/M
Mistral 7B Instruct v0.2$0.200/M
Mistral 7B Instruct v0.3$0.200/M
Mistral 7B OpenOrca$0.200/M
Mistral 7B v0.2$0.200/M
Mixtral 8x22B$1.20/M
Mixtral 8x22B Instruct$1.20/M
Mixtral 8x7B$0.500/M
Mixtral 8x7B Instruct$0.500/M
Mixtral 8x7B Instruct (HF)$0.500/M
Molmo 2 4B$0.200/M
Molmo 2 8B$0.200/M
Muse Spark Open$1.25/M
MythoMax 13B$0.200/M
Nemotron 3 Nano 30B A3B$0.900/M
Nemotron Nano 12B 2 VL$0.200/M
Nemotron Nano 12B V2$0.200/M
Nemotron Nano 9B V2$0.200/M
Nous Capybara 7B v1.9$0.200/M
Nous Hermes 2 Mixtral 8x7B DPO$0.500/M
Nous Hermes Llama 2 13B$0.200/M
Nous Hermes Llama 2 70B$0.900/M
Nous Hermes Llama 2 7B$0.200/M
nvidia-nemotron-3-embed-8b-bf16$0.200/M
openai-gpt-oss-safeguard-120b$0.900/M
openai-gpt-oss-safeguard-20b$0.900/M
OpenChat 3.5 0106$0.200/M
OpenHermes 2 Mistral 7B$0.200/M
OpenHermes 2.5 Mistral 7B$0.200/M
Phind CodeLlama 34B Python v1$0.900/M
Phind CodeLlama 34B v1$0.900/M
Phind CodeLlama 34B v2$0.900/M
Pythia 12B$0.200/M
Qwen 1.5 72B Chat$0.900/M
Qwen2 72B Instruct$0.900/M
Qwen2 7B Instruct$0.200/M
Qwen2 VL 2B Instruct$0.100/M
Qwen2 VL 72B Instruct$0.900/M
Qwen2 VL 7B Instruct$0.200/M
Qwen2.5 0.5B Instruct$0.200/M
Qwen2.5 1.5B Instruct$0.200/M
Qwen2.5 14B$0.200/M
Qwen2.5 14B Instruct$0.200/M
Qwen2.5 32B$0.900/M
Qwen2.5 32B Instruct$0.900/M
Qwen2.5 72B$0.900/M
Qwen2.5 7B$0.200/M
Qwen2.5 7B Instruct$0.200/M
Qwen2.5 Coder 0.5B$0.200/M
Qwen2.5 Coder 0.5B Instruct$0.200/M
Qwen2.5 Coder 1.5B$0.200/M
Qwen2.5 Coder 1.5B Instruct$0.200/M
Qwen2.5 Coder 14B$0.200/M
Qwen2.5 Coder 14B Instruct$0.200/M
Qwen2.5 Coder 32B$0.900/M
Qwen2.5 Coder 32B Instruct$0.900/M
Qwen2.5 Coder 32B Instruct 128K$0.900/M
Qwen2.5 Coder 32B Instruct 64K$0.900/M
Qwen2.5 Coder 3B$0.100/M
Qwen2.5 Coder 3B Instruct$0.100/M
Qwen2.5 Coder 7B$0.200/M
Qwen2.5 Coder 7B Instruct$0.200/M
Qwen2.5 Math 72B Instruct$0.900/M
Qwen2.5 VL 32B Instruct$0.900/M
Qwen2.5 VL 3B Instruct$0.100/M
Qwen2.5 VL 72B Instruct$0.900/M
Qwen2.5-VL 7B Instruct$0.200/M
Qwen3 0.6B$0.200/M
Qwen3 1.7B$0.200/M
Qwen3 235B A22B$0.900/M
Qwen3 235B A22B Thinking 2507$0.900/M
Qwen3 30B A3B Instruct 2507$0.900/M
Qwen3 30B A3B Thinking 2507$0.900/M
Qwen3 4B$0.200/M
Qwen3 4B Instruct 2507$0.200/M
Qwen3 8B$0.200/M
Qwen3 Coder 30B A3B Instruct$0.900/M
Qwen3 Coder 480B Instruct BF16$0.900/M
Qwen3 Next 80B A3B Thinking$0.900/M
Qwen3 Omni 30B A3B Instruct$0.900/M
Qwen3 VL 235B A22B Thinking$0.900/M
Qwen3 VL 30B A3B Thinking$0.900/M
Qwen3 VL 32B Instruct$0.900/M
Qwen3 VL 8B Instruct$0.200/M
Qwen3.5 4B (Non-reasoning)$0.200/M
Qwen3.5-122B-A10B$0.900/M
Qwen3.8 2.4T-A95B$0.900/M
QwQ 32B$0.900/M
QwQ 32B Preview$0.900/M
R1 Distill Llama 70B$0.900/M
R1 Distill Llama 8B$0.200/M
R1 Distill Qwen 1.5B$0.200/M
R1 Distill Qwen 14B$0.200/M
R1 Distill Qwen 32B$0.900/M
R1 Distill Qwen 7B$0.200/M
reflection/Beam-1.0$0.900/M
ricursiveai/ripple-65b-preview$0.900/M
Seed OSS 36B Instruct$0.900/M
Snorkel Mistral PairRM DPO$0.200/M
Toppy M 7B$0.200/M
Zephyr 7B Beta$0.200/M
Full Provider Pricing
Frequently Asked Questions
Built by @aellman
Also from the founder: BlobCap, a price index for AI training data deals, showing what AI labs actually pay for data.
Tools
Directories
Models & Pricing
Endpoints
Rankings
- All Rankings
- All Benchmarks
- Best LLM for Coding
- Best LLM for Math
- Best LLM for Writing
- Best LLM for RAG
- Best Local LLM
- Best LLM for OpenClaw
- Best LLM for Cursor
- Best LLM for Windsurf
- Best LLM for Cline
- Best LLM for Aider
- Best LLM for GitHub Copilot
- Best LLM for Bolt
- Best LLM for Continue.dev
- MMLU-Pro
- GPQA
- LiveCodeBench
- Aider
- AIME
- MATH (Hard)
- Big-Bench Hard
2026 68 Ventures, LLC. All rights reserved.