LLM API prices
Compare input and output prices separately. This table covers 43 models at Together AI, Fireworks AI and Nebius Token Factory. It is not a survey of every API provider. Each row keeps one provider’s input and output rates together.
Checked 13 October 2026. USD per million tokens, before taxes. Sorted by input price, then output price. Compare API usage with renting a GPU.
- MiniMax M3$0.3 in · $1.2 out, per 1M tokensCheapest of 4 rates: Together AI
- Kimi K3$3 in · $15 out, per 1M tokensCheapest of 7 rates: Together AI
- Qwen3.8-2.4T-A95B$2 in · $6 out, per 1M tokensCheapest of 1 rate: Together AI
- Muse Glimmer 30B$0.35 in · $1.5 out, per 1M tokensCheapest of 1 rate: Together AI
- DeepSeek V4 Pro 0813$1.32 in · $3.96 out, per 1M tokensCheapest of 2 rates: Together AI
- GLM-5.3$1.4 in · $4.4 out, per 1M tokensCheapest of 7 rates: Together AI
- GLM-5.3-Flash$0.15 in · $0.5 out, per 1M tokensCheapest of 6 rates: Together AI
- DeepSeek V4.1 Flash$0.3 in · $1.2 out, per 1M tokensCheapest of 6 rates: Together AI
- Tev1 4B Experimental$0.04 in · $0 out, per 1M tokensCheapest of 1 rate: Together AI
- Gemma 4 31B$0.39 in · $0.97 out, per 1M tokensCheapest of 1 rate: Together AI
- Qwen3.7-Plus$0.32 in · $1.28 out, per 1M tokensCheapest of 1 rate: Together AI
- GLM-5.2$1.4 in · $4.4 out, per 1M tokensCheapest of 2 rates: Together AI
- Ternary Bonsai 27B$0 in · $0 out, per 1M tokensCheapest of 1 rate: Together AI
- Inkling$1 in · $4.05 out, per 1M tokensCheapest of 1 rate: Together AI
- DeepSeek V4 Flash 0731$0.14 in · $0.28 out, per 1M tokensCheapest of 2 rates: Together AI
- Qwen3.8 Flash$0.15 in · $0.47 out, per 1M tokensCheapest of 1 rate: Together AI
- Qwen3.7-Max$1.5 in · $4.5 out, per 1M tokensCheapest of 1 rate: Together AI
- gpt-oss-120B$0.15 in · $0.6 out, per 1M tokensCheapest of 4 rates: Together AI
- Qwen3.5-397B-A17B$0.6 in · $3.6 out, per 1M tokensCheapest of 2 rates: Together AI
- Qwen3.5 9B$0.17 in · $0.25 out, per 1M tokensCheapest of 1 rate: Together AI
- Cogito v2.1 671B$1.25 in · $1.25 out, per 1M tokensCheapest of 1 rate: Together AI
- Rnj-1 Instruct$0.15 in · $0.15 out, per 1M tokensCheapest of 1 rate: Together AI
- Llama 3.3 70B$1.04 in · $1.04 out, per 1M tokensCheapest of 1 rate: Together AI
- MiniMax M2.7$0.3 in · $1.2 out, per 1M tokensCheapest of 1 rate: Together AI
- Qwen3.6-Plus$0.5 in · $3 out, per 1M tokensCheapest of 1 rate: Together AI
- Qwen2.5 7B Instruct Turbo$0.3 in · $0.3 out, per 1M tokensCheapest of 1 rate: Together AI
- Llama 3 8B Instruct Lite$0.14 in · $0.14 out, per 1M tokensCheapest of 1 rate: Together AI
- Qwen3 235B A22B Instruct 2507$0.2 in · $0.6 out, per 1M tokensCheapest of 2 rates: Together AI · FP8 Throughput
- Ember-1$3 in · $15 out, per 1M tokensCheapest of 2 rates: Fireworks AI · Standard
- Qwen 3.8 Max$2 in · $6 out, per 1M tokensCheapest of 2 rates: Fireworks AI · Standard
- NVIDIA Nemotron 3.5 Lightning 30B A3B$0.05 in · $0.2 out, per 1M tokensCheapest of 3 rates: Fireworks AI · Standard
- NVIDIA Nemotron 3 Ultra (Preview)$0.6 in · $2.4 out, per 1M tokensCheapest of 2 rates: Fireworks AI · Standard
- MiniCPM-V-4_5$0.658 in · $1.11 out, per 1M tokensCheapest of 1 rate: Nebius Token Factory · FP16 · eu-north1
- GLM-5.1$1.4 in · $4.4 out, per 1M tokensCheapest of 1 rate: Nebius Token Factory · FP8 · eu-north1
- DeepSeek-V4-Pro$1.75 in · $3.5 out, per 1M tokensCheapest of 1 rate: Nebius Token Factory · FP8 · uk-south1
- Hermes-4-405B$1 in · $3 out, per 1M tokensCheapest of 1 rate: Nebius Token Factory · FP8 · eu-north1
- Qwen3-30B-A3B-Instruct-2507$0.1 in · $0.3 out, per 1M tokensCheapest of 1 rate: Nebius Token Factory · FP8 · eu-north1
- Gemma-3-27b-it$0.1 in · $0.3 out, per 1M tokensCheapest of 1 rate: Nebius Token Factory · FP8 · eu-north1
- Nemotron-3-Nano-30B-A3B$0.06 in · $0.24 out, per 1M tokensCheapest of 1 rate: Nebius Token Factory · FP8 · eu-north1
- Qwen3.8-27B$0.45 in · $3 out, per 1M tokensCheapest of 1 rate: Nebius Token Factory · FP4 · us-central1
- Nemotron-3-Ultra-550b-a55b$1 in · $3 out, per 1M tokensCheapest of 1 rate: Nebius Token Factory · FP4 · us-central1
- Kimi-K2.7-Code$0.95 in · $4 out, per 1M tokensCheapest of 1 rate: Nebius Token Factory · FP4 · us-central1
- Kimi-K2.6$0.95 in · $4 out, per 1M tokensCheapest of 1 rate: Nebius Token Factory · INT4 · us-central1
All API rates
| Model / provider / tier | Input / 1M | Output / 1M | Cached input / 1M |
|---|---|---|---|
| Ternary Bonsai 27B Together AI Checked 13 October 2026 | $0.000 | $0.000 | Not published in this rate table |
| Tev1 4B Experimental Together AI Checked 13 October 2026 | $0.040 | $0.000 | Not published in this rate table |
| NVIDIA Nemotron 3.5 Lightning 30B A3B Fireworks AI · Standard Checked 13 October 2026 | $0.050 | $0.200 | $0.010 |
| Nemotron-3.5-Lightning Nebius Token Factory · BF16 · eu-north1 Checked 13 October 2026 | $0.060 | $0.240 | Not published in this rate table |
| Nemotron-3-Nano-30B-A3B Nebius Token Factory · FP8 · eu-north1 Checked 13 October 2026 | $0.060 | $0.240 | Not published in this rate table |
| NVIDIA Nemotron 3.5 Lightning 30B A3B Fireworks AI · Priority Checked 13 October 2026 | $0.063 | $0.250 | $0.013 |
| Qwen3-30B-A3B-Instruct-2507 Nebius Token Factory · FP8 · eu-north1 Checked 13 October 2026 | $0.100 | $0.300 | Not published in this rate table |
| Gemma-3-27b-it Nebius Token Factory · FP8 · eu-north1 Checked 13 October 2026 | $0.100 | $0.300 | Not published in this rate table |
| Llama 3 8B Instruct Lite Together AI Checked 13 October 2026 | $0.140 | $0.140 | Not published in this rate table |
| DeepSeek V4 Flash 0731 Together AI Checked 13 October 2026 | $0.140 | $0.280 | $0.030 |
| DeepSeek-V4-Flash-0731 Nebius Token Factory · FP8 · us-central1 Checked 13 October 2026 | $0.140 | $0.280 | Not published in this rate table |
| Rnj-1 Instruct Together AI Checked 13 October 2026 | $0.150 | $0.150 | Not published in this rate table |
| Qwen3.8 Flash Together AI Checked 13 October 2026 | $0.150 | $0.470 | Not published in this rate table |
| GLM-5.3-Flash Together AI Checked 13 October 2026 | $0.150 | $0.500 | $0.030 |
| GLM 5.3 Flash Fireworks AI · Standard Checked 13 October 2026 | $0.150 | $0.500 | $0.030 |
| GLM-5.3-Flash Nebius Token Factory · FP4 · us-north1 Checked 13 October 2026 | $0.150 | $0.500 | Not published in this rate table |
| gpt-oss-120B Together AI Checked 13 October 2026 | $0.150 | $0.600 | Not published in this rate table |
| GPT OSS 120B Fireworks AI · Standard Checked 13 October 2026 | $0.150 | $0.600 | $0.015 |
| gpt-oss-120b Nebius Token Factory · FP4 · eu-north1 Checked 13 October 2026 | $0.150 | $0.600 | Not published in this rate table |
| Qwen3.5 9B Together AI Checked 13 October 2026 | $0.170 | $0.250 | Not published in this rate table |
| GPT OSS 120B Fireworks AI · Priority Checked 13 October 2026 | $0.180 | $0.720 | $0.018 |
| GLM 5.3 Flash Fireworks AI · Priority Checked 13 October 2026 | $0.188 | $0.625 | $0.037 |
| Qwen3 235B A22B Instruct 2507 Together AI · FP8 Throughput Checked 13 October 2026 | $0.200 | $0.600 | Not published in this rate table |
| Qwen3-235B-A22B-Instruct-2507 Nebius Token Factory · FP8 · eu-north1 Checked 13 October 2026 | $0.200 | $0.600 | Not published in this rate table |
| GLM 5.3 Flash Fireworks AI · Standard · US Checked 13 October 2026 | $0.225 | $0.750 | $0.045 |
| GLM 5.3 Flash Fireworks AI · Priority · US Checked 13 October 2026 | $0.281 | $0.938 | $0.056 |
| Qwen2.5 7B Instruct Turbo Together AI Checked 13 October 2026 | $0.300 | $0.300 | Not published in this rate table |
| MiniMax M3 Together AI Checked 13 October 2026 | $0.300 | $1.200 | $0.060 |
| DeepSeek V4.1 Flash Together AI Checked 13 October 2026 | $0.300 | $1.200 | $0.006 |
| MiniMax M2.7 Together AI Checked 13 October 2026 | $0.300 | $1.200 | $0.060 |
| DeepSeek V4.1 Flash Fireworks AI · Standard Checked 13 October 2026 | $0.300 | $1.200 | $0.006 |
| MiniMax M3 Fireworks AI · Standard Checked 13 October 2026 | $0.300 | $1.200 | $0.060 |
| MiniMax-M3 Nebius Token Factory · FP4 · us-central1 Checked 13 October 2026 | $0.300 | $1.200 | Not published in this rate table |
| DeepSeek V4.1 Flash Nebius Token Factory · FP8 · us-north1 Checked 13 October 2026 | $0.300 | $1.200 | Not published in this rate table |
| Qwen3.7-Plus Together AI Checked 13 October 2026 | $0.320 | $1.280 | Not published in this rate table |
| Muse Glimmer 30B Together AI Checked 13 October 2026 | $0.350 | $1.500 | $0.040 |
| DeepSeek V4.1 Flash Fireworks AI · Priority Checked 13 October 2026 | $0.375 | $1.500 | $0.007 |
| Gemma 4 31B Together AI Checked 13 October 2026 | $0.390 | $0.970 | Not published in this rate table |
| DeepSeek V4.1 Flash Fireworks AI · Standard · US Checked 13 October 2026 | $0.450 | $1.800 | $0.009 |
| MiniMax M3 Fireworks AI · Priority Checked 13 October 2026 | $0.450 | $1.800 | $0.090 |
| Qwen3.8-27B Nebius Token Factory · FP4 · us-central1 Checked 13 October 2026 | $0.450 | $3.000 | Not published in this rate table |
| Qwen3.6-Plus Together AI Checked 13 October 2026 | $0.500 | $3.000 | Not published in this rate table |
| DeepSeek V4.1 Flash Fireworks AI · Priority · US Checked 13 October 2026 | $0.563 | $2.250 | $0.011 |
| NVIDIA Nemotron 3 Ultra (Preview) Fireworks AI · Standard Checked 13 October 2026 | $0.600 | $2.400 | $0.120 |
| Qwen3.5-397B-A17B Together AI Checked 13 October 2026 | $0.600 | $3.600 | $0.350 |
| Qwen3.5-397B-A17B Nebius Token Factory · FP4 · us-central1 Checked 13 October 2026 | $0.600 | $3.600 | Not published in this rate table |
| MiniCPM-V-4_5 Nebius Token Factory · FP16 · eu-north1 Checked 13 October 2026 | $0.658 | $1.110 | Not published in this rate table |
| NVIDIA Nemotron 3 Ultra (Preview) Fireworks AI · Priority Checked 13 October 2026 | $0.750 | $3.000 | $0.150 |
| Kimi-K2.7-Code Nebius Token Factory · FP4 · us-central1 Checked 13 October 2026 | $0.950 | $4.000 | Not published in this rate table |
| Kimi-K2.6 Nebius Token Factory · INT4 · us-central1 Checked 13 October 2026 | $0.950 | $4.000 | Not published in this rate table |
| Hermes-4-405B Nebius Token Factory · FP8 · eu-north1 Checked 13 October 2026 | $1.000 | $3.000 | Not published in this rate table |
| Nemotron-3-Ultra-550b-a55b Nebius Token Factory · FP4 · us-central1 Checked 13 October 2026 | $1.000 | $3.000 | Not published in this rate table |
| Inkling Together AI Checked 13 October 2026 | $1.000 | $4.050 | $0.170 |
| Llama 3.3 70B Together AI Checked 13 October 2026 | $1.040 | $1.040 | Not published in this rate table |
| Cogito v2.1 671B Together AI Checked 13 October 2026 | $1.250 | $1.250 | Not published in this rate table |
| DeepSeek V4 Pro 0813 Together AI Checked 13 October 2026 | $1.320 | $3.960 | $0.130 |
| DeepSeek-V4-Pro-0813 Nebius Token Factory · FP8 · uk-south1 Checked 13 October 2026 | $1.320 | $3.960 | Not published in this rate table |
| GLM-5.3 Together AI Checked 13 October 2026 | $1.400 | $4.400 | $0.260 |
| GLM-5.2 Together AI Checked 13 October 2026 | $1.400 | $4.400 | $0.260 |
| GLM 5.3 Fireworks AI · Standard Checked 13 October 2026 | $1.400 | $4.400 | $0.260 |
| GLM-5.1 Nebius Token Factory · FP8 · eu-north1 Checked 13 October 2026 | $1.400 | $4.400 | Not published in this rate table |
| GLM-5.3 Nebius Token Factory · FP4 · us-north1 Checked 13 October 2026 | $1.400 | $4.400 | Not published in this rate table |
| GLM-5.2 Nebius Token Factory · FP4 · uk-south1 Checked 13 October 2026 | $1.400 | $4.400 | Not published in this rate table |
| Qwen3.7-Max Together AI Checked 13 October 2026 | $1.500 | $4.500 | $0.300 |
| DeepSeek-V4-Pro Nebius Token Factory · FP8 · uk-south1 Checked 13 October 2026 | $1.750 | $3.500 | Not published in this rate table |
| GLM 5.3 Fireworks AI · Priority Checked 13 October 2026 | $1.750 | $5.500 | $0.325 |
| Qwen3.8-2.4T-A95B Together AI Checked 13 October 2026 | $2.000 | $6.000 | $0.250 |
| Qwen 3.8 Max Fireworks AI · Standard Checked 13 October 2026 | $2.000 | $6.000 | $0.250 |
| GLM 5.3 Fireworks AI · Standard · US Checked 13 October 2026 | $2.100 | $6.600 | $0.390 |
| GLM 5.3 Fireworks AI · Standard Fast Checked 13 October 2026 | $2.100 | $6.600 | $0.390 |
| GLM 5.3 Fireworks AI · Priority · US Checked 13 October 2026 | $2.625 | $8.250 | $0.487 |
| Qwen 3.8 Max Fireworks AI · Priority Checked 13 October 2026 | $3.000 | $9.000 | $0.375 |
| Kimi K3 Together AI Checked 13 October 2026 | $3.000 | $15.000 | $0.270 |
| Ember-1 Fireworks AI · Standard Checked 13 October 2026 | $3.000 | $15.000 | $0.300 |
| Kimi K3 Fireworks AI · Standard Checked 13 October 2026 | $3.000 | $15.000 | $0.300 |
| Kimi-K3 Nebius Token Factory · FP4 · eu-west2 Checked 13 October 2026 | $3.000 | $15.000 | Not published in this rate table |
| Ember-1 Fireworks AI · Priority Checked 13 October 2026 | $3.750 | $18.750 | $0.375 |
| Kimi K3 Fireworks AI · Priority Checked 13 October 2026 | $3.750 | $18.750 | $0.375 |
| Kimi K3 Fireworks AI · Standard Fast Checked 13 October 2026 | $4.500 | $22.500 | $0.450 |
| Kimi K3 Fireworks AI · Standard · US Checked 13 October 2026 | $4.500 | $22.500 | $0.450 |
| Kimi K3 Fireworks AI · Priority · US Checked 13 October 2026 | $5.625 | $28.125 | $0.563 |
API rates exclude batch discounts, context-dependent surcharges and image inputs, audio and any separate reasoning-token charges. A zero listed rate is a provider’s current offer, not a promise that it will stay free.