| text-embedding-3-large | azure | azure | – | 0.13n/a | freen/a | 0.0975n/a | –n/a | –n/a | –n/a | –n/a | 8191 | – | – | aggregator | modelsdev |
| text-embedding-3-large | azure | openai | – | 0.13n/a | freen/a | 0.0975n/a | –n/a | –n/a | –n/a | –n/a | 8191 | – | – | aggregator | modelsdev |
| Reka Edge | openrouter | openrouter | – | 0.10n/a | 0.10n/a | 0.10n/a | –n/a | –n/a | –n/a | –n/a | 16384 | – | – | api | openrouter |
| Mistral: Ministral 3 3B 2512 | openrouter | openrouter | – | 0.100.0356 | 0.100.0356 | 0.100.0356 | 0.01000.0036 | –n/a | –n/a | –n/a | 131072 | mistral | – | api | openrouter |
| OpenAI: GPT-6 Luna Pro | openrouter | openai | unknown | 0.05000.0141 | 0.250.0704 | 0.100.0282 | 0.00500.0014 | 0.06250.0176 | –n/a | –n/a | 1050000 | o200k | – | api | openrouter |
| GPT-6 Luna | openai | openai | unknown | 0.05000.0141 | 0.250.0704 | 0.100.0282 | 0.00500.0014 | 0.06250.0176 | –n/a | –n/a | – | o200k | – | api | openrouter |
| Reka Edge | openrouter | reka | unknown | 0.10n/a | 0.10n/a | 0.10n/a | –n/a | –n/a | –n/a | –n/a | 16384 | – | – | api | openrouter |
| Mistral: Ministral 3 3B 2512 | openrouter | mistral | unknown | 0.100.0356 | 0.100.0356 | 0.100.0356 | 0.01000.0036 | –n/a | –n/a | –n/a | 131072 | mistral | – | api | openrouter |
| Mistral: Ministral 3 3B 2512 | openrouter | mistral | unknown | 0.100.0356 | 0.100.0356 | 0.100.0356 | 0.01000.0036 | –n/a | –n/a | –n/a | 131072 | mistral | – | api | openrouter |
| gpt-oss-120b | openrouter | crusoe | – | 0.05000.0141 | 0.250.0704 | 0.100.0282 | 0.05000.0141 | –n/a | –n/a | –n/a | 131072 | o200k | – | api | openrouter |
| gpt-oss-120b | openrouter | novita | fp4 | 0.05000.0141 | 0.250.0704 | 0.100.0282 | –n/a | –n/a | –n/a | –n/a | 131072 | o200k | – | api | openrouter |
| Gemma-3-27b-it | openrouter | deepinfra | fp8 | 0.0800n/a | 0.16n/a | 0.10n/a | –n/a | –n/a | –n/a | –n/a | 131072 | gemini | – | api | openrouter |
| FW-Nemotron-Lightning-3.5-30B-A3B | azure | azure | – | 0.0600n/a | 0.22n/a | 0.10n/a | 0.0100n/a | –n/a | –n/a | –n/a | 262144 | – | – | aggregator | litellm |
| llama3.1-8b | meta | cerebras | – | 0.10n/a | 0.10n/a | 0.10n/a | –n/a | –n/a | –n/a | –n/a | 128000 | – | – | aggregator | litellm |
| Gemma-3-27b-it | openrouter | deepinfra | – | 0.0800n/a | 0.16n/a | 0.10n/a | –n/a | –n/a | –n/a | –n/a | 131072 | gemini | 2026-08-27 ↓ | aggregator | litellm |
| accounts/fireworks/models/llama-v3p1-8b-instruct | meta | fireworks | – | 0.10n/a | 0.10n/a | 0.10n/a | –n/a | –n/a | –n/a | –n/a | 16384 | – | – | aggregator | litellm |
| accounts/fireworks/models/llama-v3p2-1b-instruct | meta | fireworks | – | 0.10n/a | 0.10n/a | 0.10n/a | –n/a | –n/a | –n/a | –n/a | 16384 | – | – | aggregator | litellm |
| accounts/fireworks/models/llama-v3p2-3b-instruct | meta | fireworks | – | 0.10n/a | 0.10n/a | 0.10n/a | –n/a | –n/a | –n/a | –n/a | 16384 | – | – | aggregator | litellm |
| eu.meta.llama3-2-1b-instruct-v1:0 | meta | aws-bedrock | – | 0.10n/a | 0.10n/a | 0.10n/a | –n/a | –n/a | –n/a | –n/a | 128000 | – | – | aggregator | litellm |
| Ministral 3 3B | mistral | aws-bedrock | – | 0.10n/a | 0.10n/a | 0.10n/a | –n/a | –n/a | –n/a | –n/a | 256000 | – | – | aggregator | litellm |
| ministral-3b-2512 | mistral | mistral | – | 0.10n/a | 0.10n/a | 0.10n/a | 0.0100n/a | –n/a | –n/a | –n/a | 131072 | – | – | aggregator | litellm |
| ministral-3b-latest | mistral | mistral | – | 0.10n/a | 0.10n/a | 0.10n/a | 0.0100n/a | –n/a | –n/a | –n/a | 131072 | – | – | aggregator | litellm |
| ministral-3-3b-2512 | mistral | mistral | – | 0.10n/a | 0.10n/a | 0.10n/a | 0.0100n/a | –n/a | –n/a | –n/a | 131072 | – | – | aggregator | litellm |
| together-ai-up-to-4b | together | together | – | 0.10n/a | 0.10n/a | 0.10n/a | –n/a | –n/a | –n/a | –n/a | – | – | – | aggregator | litellm |
| arize-ai/qwen-2-1.5b-instruct | alibaba | together | – | 0.10n/a | 0.10n/a | 0.10n/a | –n/a | –n/a | –n/a | –n/a | 32768 | – | – | aggregator | litellm |
| eu.meta.llama3-2-1b-instruct-v1:0 | meta | aws-bedrock | – | 0.10n/a | 0.10n/a | 0.10n/a | –n/a | –n/a | –n/a | –n/a | 128000 | – | – | aggregator | litellm |
| glm-4-32b-0414-128k | zhipu | zhipu | – | 0.10n/a | 0.10n/a | 0.10n/a | –n/a | –n/a | –n/a | –n/a | 128000 | – | – | aggregator | litellm |
| accounts/fireworks/models/codegemma-2b | fireworks | fireworks | – | 0.10n/a | 0.10n/a | 0.10n/a | –n/a | –n/a | –n/a | –n/a | 8192 | – | – | aggregator | litellm |
| accounts/fireworks/models/cogito-v1-preview-llama-3b | fireworks | fireworks | – | 0.10n/a | 0.10n/a | 0.10n/a | –n/a | –n/a | –n/a | –n/a | 131072 | – | – | aggregator | litellm |
| accounts/fireworks/models/deepseek-coder-1b-base | deepseek | fireworks | – | 0.10n/a | 0.10n/a | 0.10n/a | –n/a | –n/a | –n/a | –n/a | 16384 | – | – | aggregator | litellm |
| accounts/fireworks/models/deepseek-r1-distill-qwen-1p5b | deepseek | fireworks | – | 0.10n/a | 0.10n/a | 0.10n/a | –n/a | –n/a | –n/a | –n/a | 131072 | – | – | aggregator | litellm |
| accounts/fireworks/models/ernie-4p5-21b-a3b-pt | fireworks | fireworks | – | 0.10n/a | 0.10n/a | 0.10n/a | –n/a | –n/a | –n/a | –n/a | 4096 | – | – | aggregator | litellm |
| accounts/fireworks/models/ernie-4p5-300b-a47b-pt | fireworks | fireworks | – | 0.10n/a | 0.10n/a | 0.10n/a | –n/a | –n/a | –n/a | –n/a | 4096 | – | – | aggregator | litellm |
| accounts/fireworks/models/flux-1-dev | fireworks | fireworks | – | 0.10n/a | 0.10n/a | 0.10n/a | –n/a | –n/a | –n/a | –n/a | 4096 | – | – | aggregator | litellm |
| accounts/fireworks/models/flux-1-schnell | fireworks | fireworks | – | 0.10n/a | 0.10n/a | 0.10n/a | –n/a | –n/a | –n/a | –n/a | 4096 | – | – | aggregator | litellm |
| accounts/fireworks/models/gemma-2b-it | google | fireworks | – | 0.10n/a | 0.10n/a | 0.10n/a | –n/a | –n/a | –n/a | –n/a | 8192 | – | – | aggregator | litellm |
| accounts/fireworks/models/llama-guard-3-1b | meta | fireworks | – | 0.10n/a | 0.10n/a | 0.10n/a | –n/a | –n/a | –n/a | –n/a | 131072 | – | – | aggregator | litellm |
| accounts/fireworks/models/llama-v2-70b | meta | fireworks | – | 0.10n/a | 0.10n/a | 0.10n/a | –n/a | –n/a | –n/a | –n/a | 4096 | – | – | aggregator | litellm |
| accounts/fireworks/models/llama-v3p1-405b-instruct-long | meta | fireworks | – | 0.10n/a | 0.10n/a | 0.10n/a | –n/a | –n/a | –n/a | –n/a | 4096 | – | – | aggregator | litellm |
| accounts/fireworks/models/llama-v3p1-70b-instruct-1b | meta | fireworks | – | 0.10n/a | 0.10n/a | 0.10n/a | –n/a | –n/a | –n/a | –n/a | 4096 | – | – | aggregator | litellm |
| accounts/fireworks/models/llama-v3p2-1b | meta | fireworks | – | 0.10n/a | 0.10n/a | 0.10n/a | –n/a | –n/a | –n/a | –n/a | 131072 | – | – | aggregator | litellm |
| accounts/fireworks/models/llama-v3p2-3b | meta | fireworks | – | 0.10n/a | 0.10n/a | 0.10n/a | –n/a | –n/a | –n/a | –n/a | 131072 | – | – | aggregator | litellm |
| MiniMax-M1 | minimax | fireworks | – | 0.10n/a | 0.10n/a | 0.10n/a | –n/a | –n/a | –n/a | –n/a | 1000000 | – | – | aggregator | litellm |
| accounts/fireworks/models/ministral-3-3b-instruct-2512 | fireworks | fireworks | – | 0.10n/a | 0.10n/a | 0.10n/a | –n/a | –n/a | –n/a | –n/a | 256000 | – | – | aggregator | litellm |
| accounts/fireworks/models/nemotron-nano-v2-12b-vl | nvidia | fireworks | – | 0.10n/a | 0.10n/a | 0.10n/a | –n/a | –n/a | –n/a | –n/a | 4096 | – | – | aggregator | litellm |
| accounts/fireworks/models/phi-2-3b | microsoft | fireworks | – | 0.10n/a | 0.10n/a | 0.10n/a | –n/a | –n/a | –n/a | –n/a | 2048 | – | – | aggregator | litellm |
| accounts/fireworks/models/phi-3-mini-128k-instruct | microsoft | fireworks | – | 0.10n/a | 0.10n/a | 0.10n/a | –n/a | –n/a | –n/a | –n/a | 131072 | – | – | aggregator | litellm |
| accounts/fireworks/models/qwen2-vl-2b-instruct | alibaba | fireworks | – | 0.10n/a | 0.10n/a | 0.10n/a | –n/a | –n/a | –n/a | –n/a | 32768 | – | – | aggregator | litellm |
| accounts/fireworks/models/qwen2p5-0p5b-instruct | alibaba | fireworks | – | 0.10n/a | 0.10n/a | 0.10n/a | –n/a | –n/a | –n/a | –n/a | 32768 | – | – | aggregator | litellm |
| accounts/fireworks/models/qwen2p5-1p5b-instruct | alibaba | fireworks | – | 0.10n/a | 0.10n/a | 0.10n/a | –n/a | –n/a | –n/a | –n/a | 32768 | – | – | aggregator | litellm |