Fireworks AI API pricing
Checked 12 Sept 2026 LLMs
262 models from US. Blended cost runs from $0.087 to $9.00 per million tokens. LLM vendors run no affiliate programmes, so nothing on this page earns Pikkly anything.
Every model
Ranked by blended cost at 3:1 input to output.
| Source | ||||||
|---|---|---|---|---|---|---|
| nemotron-lightning-3p5-30b-a3b Best value | $0.050 | $0.200 | $0.010 | 262,144 | $0.087 | ↗ |
| codegemma-2b | $0.100 | $0.100 | — | 8,192 | $0.100 | ↗ |
| cogito-v1-preview-llama-3b | $0.100 | $0.100 | — | 131,072 | $0.100 | ↗ |
| deepseek-coder-1b-base | $0.100 | $0.100 | — | 16,384 | $0.100 | ↗ |
| deepseek-r1-distill-qwen-1p5b | $0.100 | $0.100 | — | 131,072 | $0.100 | ↗ |
| ernie-4p5-21b-a3b-pt | $0.100 | $0.100 | — | 4,096 | $0.100 | ↗ |
| ernie-4p5-300b-a47b-pt | $0.100 | $0.100 | — | 4,096 | $0.100 | ↗ |
| gemma-2b-it | $0.100 | $0.100 | — | 8,192 | $0.100 | ↗ |
| llama-v2-70b | $0.100 | $0.100 | — | 4,096 | $0.100 | ↗ |
| llama-v3p1-405b-instruct-long | $0.100 | $0.100 | — | 4,096 | $0.100 | ↗ |
| llama-v3p1-70b-instruct-1b | $0.100 | $0.100 | — | 4,096 | $0.100 | ↗ |
| llama-v3p1-8b-instruct | $0.100 | $0.100 | — | 16,384 | $0.100 | ↗ |
| llama-v3p2-1b | $0.100 | $0.100 | — | 131,072 | $0.100 | ↗ |
| llama-v3p2-1b-instruct | $0.100 | $0.100 | — | 16,384 | $0.100 | ↗ |
| llama-v3p2-3b | $0.100 | $0.100 | — | 131,072 | $0.100 | ↗ |
| llama-v3p2-3b-instruct | $0.100 | $0.100 | — | 16,384 | $0.100 | ↗ |
| minimax-m1-80k | $0.100 | $0.100 | — | 4,096 | $0.100 | ↗ |
| ministral-3-3b-instruct-2512 | $0.100 | $0.100 | — | 256,000 | $0.100 | ↗ |
| nemotron-nano-v2-12b-vl | $0.100 | $0.100 | — | 4,096 | $0.100 | ↗ |
| phi-2-3b | $0.100 | $0.100 | — | 2,048 | $0.100 | ↗ |
| phi-3-mini-128k-instruct | $0.100 | $0.100 | — | 131,072 | $0.100 | ↗ |
| qwen2-vl-2b-instruct | $0.100 | $0.100 | — | 32,768 | $0.100 | ↗ |
| qwen2p5-0p5b-instruct | $0.100 | $0.100 | — | 32,768 | $0.100 | ↗ |
| qwen2p5-1p5b-instruct | $0.100 | $0.100 | — | 32,768 | $0.100 | ↗ |
| qwen2p5-coder-0p5b | $0.100 | $0.100 | — | 32,768 | $0.100 | ↗ |
| qwen2p5-coder-0p5b-instruct | $0.100 | $0.100 | — | 32,768 | $0.100 | ↗ |
| qwen2p5-coder-1p5b | $0.100 | $0.100 | — | 32,768 | $0.100 | ↗ |
| qwen2p5-coder-1p5b-instruct | $0.100 | $0.100 | — | 32,768 | $0.100 | ↗ |
| qwen2p5-coder-3b | $0.100 | $0.100 | — | 32,768 | $0.100 | ↗ |
| qwen2p5-coder-3b-instruct | $0.100 | $0.100 | — | 32,768 | $0.100 | ↗ |
| qwen3-0p6b | $0.100 | $0.100 | — | 40,960 | $0.100 | ↗ |
| qwen3-1p7b | $0.100 | $0.100 | — | 131,072 | $0.100 | ↗ |
| qwen3-1p7b-fp8-draft | $0.100 | $0.100 | — | 262,144 | $0.100 | ↗ |
| qwen3-1p7b-fp8-draft-131072 | $0.100 | $0.100 | — | 131,072 | $0.100 | ↗ |
| qwen3-1p7b-fp8-draft-40960 | $0.100 | $0.100 | — | 40,960 | $0.100 | ↗ |
| stablecode-3b | $0.100 | $0.100 | — | 4,096 | $0.100 | ↗ |
| starcoder2-3b | $0.100 | $0.100 | — | 16,384 | $0.100 | ↗ |
| gpt-oss-20b | $0.070 | $0.300 | $0.035 | 131,072 | $0.128 | ↗ |
| deepseek-v4-flash | $0.140 | $0.280 | $0.028 | 1,048,576 | $0.175 | ↗ |
| chronos-hermes-13b-v2 | $0.200 | $0.200 | — | 4,096 | $0.200 | ↗ |
| code-llama-13b | $0.200 | $0.200 | — | 16,384 | $0.200 | ↗ |
| code-llama-13b-instruct | $0.200 | $0.200 | — | 16,384 | $0.200 | ↗ |
| code-llama-13b-python | $0.200 | $0.200 | — | 16,384 | $0.200 | ↗ |
| code-llama-7b | $0.200 | $0.200 | — | 16,384 | $0.200 | ↗ |
| code-llama-7b-instruct | $0.200 | $0.200 | — | 16,384 | $0.200 | ↗ |
| code-llama-7b-python | $0.200 | $0.200 | — | 16,384 | $0.200 | ↗ |
| code-qwen-1p5-7b | $0.200 | $0.200 | — | 65,536 | $0.200 | ↗ |
| codegemma-7b | $0.200 | $0.200 | — | 8,192 | $0.200 | ↗ |
| cogito-v1-preview-llama-8b | $0.200 | $0.200 | — | 131,072 | $0.200 | ↗ |
| cogito-v1-preview-qwen-14b | $0.200 | $0.200 | — | 131,072 | $0.200 | ↗ |
| deepseek-coder-7b-base | $0.200 | $0.200 | — | 4,096 | $0.200 | ↗ |
| deepseek-coder-7b-base-v1p5 | $0.200 | $0.200 | — | 4,096 | $0.200 | ↗ |
| deepseek-coder-7b-instruct-v1p5 | $0.200 | $0.200 | — | 4,096 | $0.200 | ↗ |
| deepseek-r1-0528-distill-qwen3-8b | $0.200 | $0.200 | — | 131,072 | $0.200 | ↗ |
| deepseek-r1-distill-llama-8b | $0.200 | $0.200 | — | 131,072 | $0.200 | ↗ |
| deepseek-r1-distill-qwen-14b | $0.200 | $0.200 | — | 131,072 | $0.200 | ↗ |
| deepseek-r1-distill-qwen-7b | $0.200 | $0.200 | — | 131,072 | $0.200 | ↗ |
| dobby-mini-unhinged-plus-llama-3-1-8b | $0.200 | $0.200 | — | 131,072 | $0.200 | ↗ |
| firellava-13b | $0.200 | $0.200 | — | 4,096 | $0.200 | ↗ |
| firesearch-ocr-v6 | $0.200 | $0.200 | — | 8,192 | $0.200 | ↗ |
| gemma-7b | $0.200 | $0.200 | — | 8,192 | $0.200 | ↗ |
| gemma-7b-it | $0.200 | $0.200 | — | 8,192 | $0.200 | ↗ |
| gemma2-9b-it | $0.200 | $0.200 | — | 8,192 | $0.200 | ↗ |
| hermes-2-pro-mistral-7b | $0.200 | $0.200 | — | 32,768 | $0.200 | ↗ |
| internvl3-8b | $0.200 | $0.200 | — | 16,384 | $0.200 | ↗ |
| llama-v2-13b | $0.200 | $0.200 | — | 4,096 | $0.200 | ↗ |
| llama-v2-13b-chat | $0.200 | $0.200 | — | 4,096 | $0.200 | ↗ |
| llama-v2-7b | $0.200 | $0.200 | — | 4,096 | $0.200 | ↗ |
| llama-v2-7b-chat | $0.200 | $0.200 | — | 4,096 | $0.200 | ↗ |
| llama-v3-8b | $0.200 | $0.200 | — | 8,192 | $0.200 | ↗ |
| llama-v3-8b-instruct-hf | $0.200 | $0.200 | — | 8,192 | $0.200 | ↗ |
| llama-v3p2-11b-vision-instruct | $0.200 | $0.200 | — | 16,384 | $0.200 | ↗ |
| llamaguard-7b | $0.200 | $0.200 | — | 4,096 | $0.200 | ↗ |
| ministral-3-14b-instruct-2512 | $0.200 | $0.200 | — | 256,000 | $0.200 | ↗ |
| ministral-3-8b-instruct-2512 | $0.200 | $0.200 | — | 256,000 | $0.200 | ↗ |
| mistral-7b | $0.200 | $0.200 | — | 32,768 | $0.200 | ↗ |
| mistral-7b-instruct-4k | $0.200 | $0.200 | — | 32,768 | $0.200 | ↗ |
| mistral-7b-instruct-v0p2 | $0.200 | $0.200 | — | 32,768 | $0.200 | ↗ |
| mistral-7b-instruct-v3 | $0.200 | $0.200 | — | 32,768 | $0.200 | ↗ |
| mistral-7b-v0p2 | $0.200 | $0.200 | — | 32,768 | $0.200 | ↗ |
| mistral-nemo-base-2407 | $0.200 | $0.200 | — | 128,000 | $0.200 | ↗ |
| mistral-nemo-instruct-2407 | $0.200 | $0.200 | — | 128,000 | $0.200 | ↗ |
| mythomax-l2-13b | $0.200 | $0.200 | — | 4,096 | $0.200 | ↗ |
| nous-capybara-7b-v1p9 | $0.200 | $0.200 | — | 32,768 | $0.200 | ↗ |
| nous-hermes-llama2-13b | $0.200 | $0.200 | — | 4,096 | $0.200 | ↗ |
| nous-hermes-llama2-7b | $0.200 | $0.200 | — | 4,096 | $0.200 | ↗ |
| nvidia-nemotron-nano-12b-v2 | $0.200 | $0.200 | — | 131,072 | $0.200 | ↗ |
| nvidia-nemotron-nano-9b-v2 | $0.200 | $0.200 | — | 131,072 | $0.200 | ↗ |
| openchat-3p5-0106-7b | $0.200 | $0.200 | — | 8,192 | $0.200 | ↗ |
| openhermes-2-mistral-7b | $0.200 | $0.200 | — | 32,768 | $0.200 | ↗ |
| openhermes-2p5-mistral-7b | $0.200 | $0.200 | — | 32,768 | $0.200 | ↗ |
| openorca-7b | $0.200 | $0.200 | — | 32,768 | $0.200 | ↗ |
| phi-3-vision-128k-instruct | $0.200 | $0.200 | — | 32,064 | $0.200 | ↗ |
| pythia-12b | $0.200 | $0.200 | — | 2,048 | $0.200 | ↗ |
| qwen-v2p5-14b-instruct | $0.200 | $0.200 | — | 32,768 | $0.200 | ↗ |
| qwen-v2p5-7b | $0.200 | $0.200 | — | 131,072 | $0.200 | ↗ |
| qwen2-7b-instruct | $0.200 | $0.200 | — | 32,768 | $0.200 | ↗ |
| qwen2-vl-7b-instruct | $0.200 | $0.200 | — | 32,768 | $0.200 | ↗ |
| qwen2p5-14b | $0.200 | $0.200 | — | 131,072 | $0.200 | ↗ |
| qwen2p5-7b-instruct | $0.200 | $0.200 | — | 32,768 | $0.200 | ↗ |
| qwen2p5-coder-14b | $0.200 | $0.200 | — | 32,768 | $0.200 | ↗ |
| qwen2p5-coder-14b-instruct | $0.200 | $0.200 | — | 32,768 | $0.200 | ↗ |
| qwen2p5-coder-7b | $0.200 | $0.200 | — | 32,768 | $0.200 | ↗ |
| qwen2p5-coder-7b-instruct | $0.200 | $0.200 | — | 32,768 | $0.200 | ↗ |
| qwen2p5-vl-3b-instruct | $0.200 | $0.200 | — | 128,000 | $0.200 | ↗ |
| qwen2p5-vl-7b-instruct | $0.200 | $0.200 | — | 128,000 | $0.200 | ↗ |
| qwen3-14b | $0.200 | $0.200 | — | 40,960 | $0.200 | ↗ |
| qwen3-4b | $0.200 | $0.200 | — | 40,960 | $0.200 | ↗ |
| qwen3-4b-instruct-2507 | $0.200 | $0.200 | — | 262,144 | $0.200 | ↗ |
| qwen3-8b | $0.200 | $0.200 | — | 40,960 | $0.200 | ↗ |
| qwen3-vl-8b-instruct | $0.200 | $0.200 | — | 4,096 | $0.200 | ↗ |
| rolm-ocr | $0.200 | $0.200 | — | 128,000 | $0.200 | ↗ |
| snorkel-mistral-7b-pairrm-dpo | $0.200 | $0.200 | — | 32,768 | $0.200 | ↗ |
| starcoder-16b | $0.200 | $0.200 | — | 8,192 | $0.200 | ↗ |
| starcoder-7b | $0.200 | $0.200 | — | 8,192 | $0.200 | ↗ |
| starcoder2-15b | $0.200 | $0.200 | — | 16,384 | $0.200 | ↗ |
| starcoder2-7b | $0.200 | $0.200 | — | 16,384 | $0.200 | ↗ |
| toppy-m-7b | $0.200 | $0.200 | — | 32,768 | $0.200 | ↗ |
| yi-6b | $0.200 | $0.200 | — | 4,096 | $0.200 | ↗ |
| zephyr-7b-beta | $0.200 | $0.200 | — | 32,768 | $0.200 | ↗ |
| glm-5p3-flash | $0.150 | $0.500 | $0.030 | 1,048,576 | $0.237 | ↗ |
| gpt-oss-120b | $0.150 | $0.600 | $0.015 | 131,072 | $0.263 | ↗ |
| llama4-scout-instruct-basic | $0.150 | $0.600 | — | 131,072 | $0.263 | ↗ |
| qwen3-30b-a3b | $0.150 | $0.600 | — | 131,072 | $0.263 | ↗ |
| qwen3-coder-30b-a3b-instruct | $0.150 | $0.600 | — | 262,144 | $0.263 | ↗ |
| qwen3-vl-30b-a3b-instruct | $0.150 | $0.600 | — | 262,144 | $0.263 | ↗ |
| qwen3-vl-30b-a3b-thinking | $0.150 | $0.600 | — | 262,144 | $0.263 | ↗ |
| deepseek-v4-flash-0731 | $0.220 | $0.660 | $0.007 | 1,048,576 | $0.330 | ↗ |
| deepseek-v4-flash-vision-exp | $0.220 | $0.660 | $0.007 | 1,048,576 | $0.330 | ↗ |
| glm-4p5-air | $0.220 | $0.880 | — | 128,000 | $0.385 | ↗ |
| llama4-maverick-instruct-basic | $0.220 | $0.880 | — | 131,072 | $0.385 | ↗ |
| qwen3-235b-a22b | $0.220 | $0.880 | — | 131,072 | $0.385 | ↗ |
| qwen3-235b-a22b-instruct-2507 | $0.220 | $0.880 | — | 262,144 | $0.385 | ↗ |
| qwen3-235b-a22b-thinking-2507 | $0.220 | $0.880 | — | 262,144 | $0.385 | ↗ |
| qwen3-vl-235b-a22b-instruct | $0.220 | $0.880 | — | 262,144 | $0.385 | ↗ |
| qwen3-vl-235b-a22b-thinking | $0.220 | $0.880 | — | 262,144 | $0.385 | ↗ |
| deepseek-coder-v2-lite-base | $0.500 | $0.500 | — | 163,840 | $0.500 | ↗ |
| deepseek-coder-v2-lite-instruct | $0.500 | $0.500 | — | 163,840 | $0.500 | ↗ |
| deepseek-v2-lite-chat | $0.500 | $0.500 | — | 163,840 | $0.500 | ↗ |
| dolphin-2p6-mixtral-8x7b | $0.500 | $0.500 | — | 32,768 | $0.500 | ↗ |
| firefunction-v1 | $0.500 | $0.500 | — | 32,768 | $0.500 | ↗ |
| gpt-oss-safeguard-20b | $0.500 | $0.500 | — | 131,072 | $0.500 | ↗ |
| mixtral-8x7b | $0.500 | $0.500 | — | 32,768 | $0.500 | ↗ |
| mixtral-8x7b-instruct | $0.500 | $0.500 | — | 32,768 | $0.500 | ↗ |
| mixtral-8x7b-instruct-hf | $0.500 | $0.500 | — | 32,768 | $0.500 | ↗ |
| nous-hermes-2-mixtral-8x7b-dpo | $0.500 | $0.500 | — | 32,768 | $0.500 | ↗ |
| qwen3-30b-a3b-instruct-2507 | $0.500 | $0.500 | — | 262,144 | $0.500 | ↗ |
| minimax-m2 | $0.300 | $1.20 | — | 4,096 | $0.525 | ↗ |
| minimax-m2p1 | $0.300 | $1.20 | $0.030 | 204,800 | $0.525 | ↗ |
| minimax-m2p7 | $0.300 | $1.20 | $0.060 | 196,608 | $0.525 | ↗ |
| minimax-m3 | $0.300 | $1.20 | $0.060 | 512,000 | $0.525 | ↗ |
| muse-glimmer-30b | $0.350 | $1.50 | $0.040 | 131,072 | $0.637 | ↗ |
| qwen3p7-plus | $0.400 | $1.60 | $0.080 | 262,144 | $0.700 | ↗ |
| qwen3-coder-480b-a35b-instruct | $0.450 | $1.80 | — | 262,144 | $0.787 | ↗ |
| deepseek-v3p1 | $0.560 | $1.68 | — | 128,000 | $0.840 | ↗ |
| deepseek-v3p1-terminus | $0.560 | $1.68 | — | 128,000 | $0.840 | ↗ |
| deepseek-v3p2 | $0.560 | $1.68 | — | 163,840 | $0.840 | ↗ |
| code-llama-34b | $0.900 | $0.900 | — | 16,384 | $0.900 | ↗ |
| code-llama-34b-instruct | $0.900 | $0.900 | — | 16,384 | $0.900 | ↗ |
| code-llama-34b-python | $0.900 | $0.900 | — | 16,384 | $0.900 | ↗ |
| code-llama-70b | $0.900 | $0.900 | — | 4,096 | $0.900 | ↗ |
| code-llama-70b-instruct | $0.900 | $0.900 | — | 4,096 | $0.900 | ↗ |
| code-llama-70b-python | $0.900 | $0.900 | — | 4,096 | $0.900 | ↗ |
| cogito-v1-preview-llama-70b | $0.900 | $0.900 | — | 131,072 | $0.900 | ↗ |
| cogito-v1-preview-qwen-32b | $0.900 | $0.900 | — | 131,072 | $0.900 | ↗ |
| deepseek-coder-33b-instruct | $0.900 | $0.900 | — | 16,384 | $0.900 | ↗ |
| deepseek-r1-distill-llama-70b | $0.900 | $0.900 | — | 131,072 | $0.900 | ↗ |
| deepseek-r1-distill-qwen-32b | $0.900 | $0.900 | — | 131,072 | $0.900 | ↗ |
| deepseek-v3 | $0.900 | $0.900 | — | 128,000 | $0.900 | ↗ |
| deepseek-v3-0324 | $0.900 | $0.900 | — | 163,840 | $0.900 | ↗ |
| devstral-small-2505 | $0.900 | $0.900 | — | 131,072 | $0.900 | ↗ |
| dobby-unhinged-llama-3-3-70b-new | $0.900 | $0.900 | — | 131,072 | $0.900 | ↗ |
| dolphin-2-9-2-qwen2-72b | $0.900 | $0.900 | — | 131,072 | $0.900 | ↗ |
| fare-20b | $0.900 | $0.900 | — | 131,072 | $0.900 | ↗ |
| firefunction-v2 | $0.900 | $0.900 | — | 8,192 | $0.900 | ↗ |
| gemma-3-27b-it | $0.900 | $0.900 | — | 131,072 | $0.900 | ↗ |
| internvl3-38b | $0.900 | $0.900 | — | 16,384 | $0.900 | ↗ |
| internvl3-78b | $0.900 | $0.900 | — | 16,384 | $0.900 | ↗ |
| kat-coder | $0.900 | $0.900 | — | 262,144 | $0.900 | ↗ |
| kat-dev-32b | $0.900 | $0.900 | — | 131,072 | $0.900 | ↗ |
| kat-dev-72b-exp | $0.900 | $0.900 | — | 131,072 | $0.900 | ↗ |
| llama-v2-70b-chat | $0.900 | $0.900 | — | 2,048 | $0.900 | ↗ |
| llama-v3-70b-instruct | $0.900 | $0.900 | — | 8,192 | $0.900 | ↗ |
| llama-v3-70b-instruct-hf | $0.900 | $0.900 | — | 8,192 | $0.900 | ↗ |
| llama-v3p1-70b-instruct | $0.900 | $0.900 | — | 131,072 | $0.900 | ↗ |
| llama-v3p1-nemotron-70b-instruct | $0.900 | $0.900 | — | 131,072 | $0.900 | ↗ |
| llama-v3p2-90b-vision-instruct | $0.900 | $0.900 | — | 16,384 | $0.900 | ↗ |
| llama-v3p3-70b-instruct | $0.900 | $0.900 | — | 131,072 | $0.900 | ↗ |
| llava-yi-34b | $0.900 | $0.900 | — | 4,096 | $0.900 | ↗ |
| mistral-small-24b-instruct-2501 | $0.900 | $0.900 | — | 32,768 | $0.900 | ↗ |
| nous-hermes-2-yi-34b | $0.900 | $0.900 | — | 4,096 | $0.900 | ↗ |
| nous-hermes-llama2-70b | $0.900 | $0.900 | — | 4,096 | $0.900 | ↗ |
| phind-code-llama-34b-python-v1 | $0.900 | $0.900 | — | 16,384 | $0.900 | ↗ |
| phind-code-llama-34b-v1 | $0.900 | $0.900 | — | 16,384 | $0.900 | ↗ |
| phind-code-llama-34b-v2 | $0.900 | $0.900 | — | 16,384 | $0.900 | ↗ |
| qwen-qwq-32b-preview | $0.900 | $0.900 | — | 32,768 | $0.900 | ↗ |
| qwen1p5-72b-chat | $0.900 | $0.900 | — | 32,768 | $0.900 | ↗ |
| qwen2-72b-instruct | $0.900 | $0.900 | — | 32,768 | $0.900 | ↗ |
| qwen2-vl-72b-instruct | $0.900 | $0.900 | — | 32,768 | $0.900 | ↗ |
| qwen2p5-32b | $0.900 | $0.900 | — | 131,072 | $0.900 | ↗ |
| qwen2p5-32b-instruct | $0.900 | $0.900 | — | 32,768 | $0.900 | ↗ |
| qwen2p5-72b | $0.900 | $0.900 | — | 131,072 | $0.900 | ↗ |
| qwen2p5-72b-instruct | $0.900 | $0.900 | — | 32,768 | $0.900 | ↗ |
| qwen2p5-coder-32b | $0.900 | $0.900 | — | 32,768 | $0.900 | ↗ |
| qwen2p5-coder-32b-instruct | $0.900 | $0.900 | — | 4,096 | $0.900 | ↗ |
| qwen2p5-coder-32b-instruct-128k | $0.900 | $0.900 | — | 131,072 | $0.900 | ↗ |
| qwen2p5-coder-32b-instruct-32k-rope | $0.900 | $0.900 | — | 32,768 | $0.900 | ↗ |
| qwen2p5-coder-32b-instruct-64k | $0.900 | $0.900 | — | 65,536 | $0.900 | ↗ |
| qwen2p5-math-72b-instruct | $0.900 | $0.900 | — | 4,096 | $0.900 | ↗ |
| qwen2p5-vl-32b-instruct | $0.900 | $0.900 | — | 128,000 | $0.900 | ↗ |
| qwen2p5-vl-72b-instruct | $0.900 | $0.900 | — | 128,000 | $0.900 | ↗ |
| qwen3-30b-a3b-thinking-2507 | $0.900 | $0.900 | — | 262,144 | $0.900 | ↗ |
| qwen3-32b | $0.900 | $0.900 | — | 131,072 | $0.900 | ↗ |
| qwen3-coder-480b-instruct-bf16 | $0.900 | $0.900 | — | 4,096 | $0.900 | ↗ |
| qwen3-next-80b-a3b-instruct | $0.900 | $0.900 | — | 4,096 | $0.900 | ↗ |
| qwen3-next-80b-a3b-thinking | $0.900 | $0.900 | — | 4,096 | $0.900 | ↗ |
| qwen3-vl-32b-instruct | $0.900 | $0.900 | — | 4,096 | $0.900 | ↗ |
| qwq-32b | $0.900 | $0.900 | — | 131,072 | $0.900 | ↗ |
| yi-34b | $0.900 | $0.900 | — | 4,096 | $0.900 | ↗ |
| yi-34b-200k-capybara | $0.900 | $0.900 | — | 200,000 | $0.900 | ↗ |
| yi-34b-chat | $0.900 | $0.900 | — | 4,096 | $0.900 | ↗ |
| deepseek-r1-basic | $0.550 | $2.19 | — | 128,000 | $0.960 | ↗ |
| glm-4p5 | $0.550 | $2.19 | — | 128,000 | $0.960 | ↗ |
| glm-4p6 | $0.550 | $2.19 | — | 202,800 | $0.960 | ↗ |
| glm-4p7 | $0.600 | $2.20 | $0.300 | 202,800 | $1.00 | ↗ |
| nemotron-3-ultra-nvfp4 | $0.600 | $2.40 | $0.120 | 262,144 | $1.05 | ↗ |
| kimi-k2-instruct | $0.600 | $2.50 | — | 131,072 | $1.08 | ↗ |
| kimi-k2-instruct-0905 | $0.600 | $2.50 | — | 262,144 | $1.08 | ↗ |
| kimi-k2-thinking | $0.600 | $2.50 | — | 262,144 | $1.08 | ↗ |
| cogito-671b-v2-p1 | $1.20 | $1.20 | — | 163,840 | $1.20 | ↗ |
| dbrx-instruct | $1.20 | $1.20 | — | 32,768 | $1.20 | ↗ |
| deepseek-coder-v2-instruct | $1.20 | $1.20 | — | 65,536 | $1.20 | ↗ |
| deepseek-prover-v2 | $1.20 | $1.20 | — | 163,840 | $1.20 | ↗ |
| deepseek-v2p5 | $1.20 | $1.20 | — | 32,768 | $1.20 | ↗ |
| glm-4p5v | $1.20 | $1.20 | — | 131,072 | $1.20 | ↗ |
| gpt-oss-safeguard-120b | $1.20 | $1.20 | — | 131,072 | $1.20 | ↗ |
| kimi-k2p5 | $0.600 | $3.00 | $0.100 | 262,144 | $1.20 | ↗ |
| mistral-large-3-fp8 | $1.20 | $1.20 | — | 256,000 | $1.20 | ↗ |
| mixtral-8x22b | $1.20 | $1.20 | — | 65,536 | $1.20 | ↗ |
| mixtral-8x22b-instruct | $1.20 | $1.20 | — | 65,536 | $1.20 | ↗ |
| mixtral-8x22b-instruct-hf | $1.20 | $1.20 | — | 65,536 | $1.20 | ↗ |
| kimi-k2p6 | $0.950 | $4.00 | $0.160 | 262,144 | $1.71 | ↗ |
| kimi-k2p7-code | $0.950 | $4.00 | $0.190 | 262,144 | $1.71 | ↗ |
| inkling | $1.00 | $4.05 | $0.170 | 1,048,576 | $1.76 | ↗ |
| deepseek-v4-pro-0813 | $1.32 | $3.96 | $0.044 | 1,048,576 | $1.98 | ↗ |
| glm-5p1 | $1.40 | $4.40 | $0.260 | 202,800 | $2.15 | ↗ |
| glm-5p2 | $1.40 | $4.40 | $0.140 | 1,048,576 | $2.15 | ↗ |
| glm-5p3 | $1.40 | $4.40 | $0.260 | 1,048,576 | $2.15 | ↗ |
| deepseek-v4-pro | $1.74 | $3.48 | $0.145 | 1,048,576 | $2.18 | ↗ |
| llama-v3p1-405b-instruct | $3.00 | $3.00 | — | 128,000 | $3.00 | ↗ |
| qwen3p8-max | $2.00 | $6.00 | $0.250 | 262,144 | $3.00 | ↗ |
| yi-large | $3.00 | $3.00 | — | 32,768 | $3.00 | ↗ |
| glm-5p2-fast | $2.10 | $6.60 | $0.210 | 1,048,576 | $3.23 | ↗ |
| glm-5p2-fast-us | $2.10 | $6.60 | $0.210 | 1,048,576 | $3.23 | ↗ |
| kimi-k2p7-code-fast | $1.90 | $8.00 | $0.380 | 262,144 | $3.43 | ↗ |
| kimi-k2p6-fast | $2.00 | $8.00 | $0.300 | 262,144 | $3.50 | ↗ |
| deepseek-r1 | $3.00 | $8.00 | — | 128,000 | $4.25 | ↗ |
| deepseek-r1-0528 | $3.00 | $8.00 | — | 160,000 | $4.25 | ↗ |
| glm-5p1-fast | $2.80 | $8.80 | $0.520 | 202,800 | $4.30 | ↗ |
| kimi-k3 | $3.00 | $15.00 | $0.300 | 1,048,576 | $6.00 | ↗ |
| kimi-k3-us | $3.30 | $16.50 | $0.330 | 1,048,576 | $6.60 | ↗ |
| kimi-k3-fast | $4.50 | $22.50 | $0.450 | 1,048,576 | $9.00 | ↗ |
Last checked . Methodology
All models · deepseek-v3p1 · deepseek-v3p1-terminus · deepseek-v3p2 · deepseek-v3 · deepseek-v3-0324 · Run your own on a GPU