Together AI API pricing
84 Together AI models: text, embeddings, rerank, from price book 2026-10-22.
Billing rules Veqen applies
- Token models: cached input at the cache-read rate, cache writes at the write rate; batch and service tiers at their own rates where published; long-context rates once the full prompt passes the threshold.
- Rerank models: per query.
Also recognized as: together_ai, togetherai (framework, gateway and OpenTelemetry names).
Reconcile your bill
Together AI doesn't offer a cost API, so Veqen's ledger is your running record of spend. Enter each month's bill to reconcile it and book it in the close. How reconciliation works.
Prices come from Together AI's pricing page. Negotiated rates or committed-use discounts can be set as custom prices.
Text 82 models
| Model | Input | Output | Cached input | Batch input | Context | Status |
|---|---|---|---|---|---|---|
| Prism-ML/Ternary-Bonsai-27B | $0.00 | $0.00 | — | — | 262.1K | |
| Qwen/Qwen2-1.5B-Instruct | $0.02 | $0.02 | — | — | 32.8K | |
| Tev1-4B-experimental | $0.042 | $0.00 | — | — | 32.8K | |
| arcee-ai/trinity-mini | $0.045 | $0.15 | — | — | 128K | |
| meta-llama/Llama-3.2-1B-Instruct | $0.06 | $0.06 | — | — | 131.1K | |
| meta-llama/Llama-3.2-3B-Instruct | $0.06 | $0.06 | — | — | 131.1K | |
| arize-ai/qwen-2-1.5b-instruct | $0.10 | $0.10 | — | — | 32.8K | |
| Qwen/Qwen3.8-Flash | $0.15 | $0.47 | — | — | 1M | |
| nvidia/NVIDIA-Nemotron-3.5-Super-VL | $0.15 | $0.50 | $0.02 | — | 262.1K | |
| openai/gpt-oss-120b | $0.15 | $0.60 | — | — | 131.1K | |
| zai-org/GLM-5.3-Flash | $0.15 | $0.50 | $0.03 | — | 1M | |
| Qwen/Qwen3.5-9B | $0.17 | $0.25 | — | — | 262.1K | |
| meta-llama/Meta-Llama-3.1-8B | $0.20 | $0.20 | — | — | 16.4K | |
| mistralai/Ministral-3-14B-Instruct-2512 | $0.20 | $0.20 | — | — | 262.1K | |
| mistralai/Mistral-7B-Instruct-v0.3 | $0.20 | $0.20 | — | — | 32.8K | |
| MiniMaxAI/MiniMax-M2.7 | $0.30 | $1.20 | $0.06 | — | 196.6K | |
| MiniMaxAI/MiniMax-M3 | $0.30 | $1.20 | $0.06 | — | 524.3K | |
| Qwen/Qwen2.5-7B-Instruct-Turbo | $0.30 | $0.30 | — | — | 32.8K | |
| deepseek-ai/DeepSeek-V4.1-Flash | $0.30 | $1.20 | $0.006 | — | 1M | |
| deepseek-ai/DeepSeek-V4.1-Flash-1017 | $0.30 | $1.20 | $0.006 | — | 1M | |
| Qwen/Qwen3.7-Plus | $0.32 | $1.28 | — | — | 1M | |
| meta-models/Muse-Glimmer-30B | $0.35 | $1.50 | $0.04 | — | 131.1K | |
| reflection/Beam-1.0-501B-A23B | $0.40 | $1.20 | $0.04 | — | 1M | |
| Qwen/Qwen3.6-Plus | $0.50 | $3.00 | — | — | 1M | |
| moonshotai/Kimi-K2.5-fp4 | $0.50 | $2.80 | — | — | 262.1K | |
| zai-org/GLM-4.6 | $0.60 | $2.20 | — | — | 202.8K | |
| Qwen/Qwen2.5-14B-Instruct | $0.80 | $0.80 | — | — | 32.8K | |
| moonshotai/Kimi-K2-Instruct | $1.00 | $3.00 | — | — | — | |
| thinkingmachines/Inkling | $1.00 | $4.05 | $0.17 | — | 524.3K | |
| Qwen/Qwen2.5-72B-Instruct | $1.20 | $1.20 | — | — | 32.8K | |
| deepseek-ai/DeepSeek-V3 | $1.25 | $1.25 | — | — | 65.5K | |
| meta-models/Muse-Spark-Open-816B-A42B | $1.25 | $4.25 | $0.15 | — | 1M | |
| deepseek-ai/DeepSeek-V4-Pro-0813 | $1.32 | $3.96 | $0.13 | — | 1M | |
| zai-org/GLM-5.2 | $1.40 | $4.40 | $0.26 | — | 1M | |
| zai-org/GLM-5.3 | $1.40 | $4.40 | $0.26 | — | 1M | |
| Qwen/Qwen3.7-Max | $1.50 | $4.50 | $0.30 | — | 1M | |
| Qwen/Qwen3.8-2.4T-A95B | $2.00 | $6.00 | $0.25 | — | 1M | |
| deepseek-ai/DeepSeek-R1-0528 | $3.00 | $7.00 | — | — | 163.8K | |
| moonshotai/Kimi-K3 | $3.00 | $15.00 | $0.30 | — | 1M | |
| meta-llama/Llama-3.1-405B-Instruct | $3.50 | $3.50 | — | — | 4.1K | |
| openai/gpt-oss-20b | $0.05 | $0.20 | — | — | 131.1K | Retired 2026-09-15 |
| nvidia/NVIDIA-Nemotron-Nano-9B-v2 | $0.06 | $0.25 | — | — | 131.1K | Retired 2026-02-25 |
| mistralai/Mistral-Small-24B-Instruct-2501 | $0.10 | $0.30 | — | — | 32.8K | Retired 2026-04-02 |
| deepseek-ai/DeepSeek-V4-Flash-0731 | $0.14 | $0.28 | $0.03 | — | 1M | Retired 2026-10-22 |
| Qwen/Qwen3-Next-80B-A3B-Instruct | $0.15 | $1.50 | — | — | 262.1K | Retired 2026-04-02 |
| Qwen/Qwen3-Next-80B-A3B-Thinking | $0.15 | $1.50 | — | — | 262.1K | Retired 2026-02-25 |
| Qwen/Qwen3-VL-8B-Instruct | $0.18 | $0.68 | — | — | 262.1K | Retired 2026-04-16 |
| deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B | $0.18 | $0.18 | — | — | 131.1K | Retired 2025-08-28 |
| meta-llama/Llama-4-Scout-17B-16E-Instruct | $0.18 | $0.59 | — | — | 1M | Retired 2026-02-06 |
| meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo | $0.18 | $0.18 | — | — | 131.1K | Retired 2026-03-06 |
| meta-llama/Llama-3-8b-chat-hf | $0.20 | $0.20 | — | — | 8.2K | Retired 2025-08-28 |
| meta-llama/Meta-Llama-3-8B-Instruct | $0.20 | $0.20 | — | — | 8.2K | Retired 2025-08-28 |
| mistralai/Mistral-7B-Instruct-v0.1 | $0.20 | $0.20 | — | — | 32.8K | Retired 2025-11-13 |
| zai-org/GLM-4.5-Air-FP8 | $0.20 | $1.10 | — | — | 131.1K | Retired 2026-04-02 |
| google/gemma-4-31B-it | $0.39 | $0.97 | — | — | 262.1K | Retired 2026-09-15 |
| zai-org/GLM-4.7 | $0.45 | $2.00 | — | — | 202.8K | Retired 2026-04-02 |
| Qwen/Qwen3-Coder-Next-FP8 | $0.50 | $1.20 | — | — | 262.1K | Retired 2026-05-14 |
| Qwen/Qwen3-VL-32B-Instruct | $0.50 | $1.50 | — | — | 262.1K | Retired 2026-02-25 |
| NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO | $0.60 | $0.60 | — | — | 32.8K | Retired 2025-08-28 |
| Qwen/Qwen3.5-397B-A17B | $0.60 | $3.60 | $0.35 | — | 262.1K | Retired 2026-06-29 |
| deepseek-ai/DeepSeek-V3.1 | $0.60 | $1.70 | — | — | 131.1K | Retired 2026-05-14 |
| mistralai/Mixtral-8x7B-Instruct-v0.1 | $0.60 | $0.60 | — | — | 32.8K | Retired 2026-04-16 |
| nvidia/nemotron-3-ultra-550b-a55b | $0.60 | $3.60 | $0.20 | — | 512.3K | Retired 2026-08-27 |
| Qwen/Qwen2.5-Coder-32B-Instruct | $0.80 | $0.80 | — | — | 16.4K | Retired 2025-11-13 |
| deepseek-ai/deepseek-coder-33b-instruct | $0.80 | $0.80 | — | — | 16.4K | Retired 2024-08-22 |
| google/gemma-2-27b-it | $0.80 | $0.80 | — | — | 8.2K | Retired 2025-08-28 |
| meta-llama/Meta-Llama-3-70B-Instruct-Turbo | $0.88 | $0.88 | — | — | 8.2K | Retired 2025-12-23 |
| meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo | $0.88 | $0.88 | — | — | 131.1K | Retired 2026-02-25 |
| nvidia/Llama-3.1-Nemotron-70B-Instruct-HF | $0.88 | $0.88 | — | — | 32.8K | Retired 2025-08-28 |
| Qwen/Qwen2-72B-Instruct | $0.90 | $0.90 | — | — | 32.8K | Retired 2025-08-28 |
| moonshotai/Kimi-K2.7-Code | $0.95 | $4.00 | $0.19 | — | 262.1K | Retired 2026-08-27 |
| zai-org/GLM-5 | $1.00 | $3.20 | — | — | 202.8K | Retired 2026-06-22 |
| meta-llama/Llama-3.3-70B-Instruct-Turbo | $1.04 | $1.04 | — | — | 131.1K | Retired 2026-10-22 |
| Qwen/QwQ-32B | $1.20 | $1.20 | — | — | 131.1K | Retired 2025-11-13 |
| Qwen/Qwen2-VL-72B-Instruct | $1.20 | $1.20 | — | — | 32.8K | Retired 2025-08-28 |
| Qwen/Qwen2.5-72B-Instruct-Turbo | $1.20 | $1.20 | — | — | 131.1K | Retired 2026-02-06 |
| moonshotai/Kimi-K2.6 | $1.20 | $4.50 | $0.20 | — | 262.1K | Retired 2026-08-19 |
| zai-org/GLM-5.1 | $1.40 | $4.40 | $0.26 | — | 202.8K | Retired 2026-07-10 |
| deepseek-ai/DeepSeek-R1-Distill-Qwen-14B | $1.60 | $1.60 | — | — | 131.1K | Retired 2025-11-13 |
| Qwen/Qwen2.5-VL-72B-Instruct | $1.95 | $8.00 | — | — | 32.8K | Retired 2026-01-05 |
| Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8 | $2.00 | $2.00 | — | — | 262.1K | Retired 2026-06-04 |
| deepseek-ai/DeepSeek-R1-Distill-Llama-70B | $2.00 | $2.00 | — | — | 131.1K | Retired 2025-12-23 |
Embeddings 1 model
| Model | Price | Status |
|---|---|---|
| BAAI/bge-base-en-v1.5 | $0.008 per 1M tokens |
Rerank 1 model
| Model | Price | Status |
|---|---|---|
| Salesforce/Llama-Rank-V1 | $0.10 in · $0.00 out per 1M | Retired 2026-02-06 |