Model catalog
Models and list rates
Published API prices, in US dollars per million tokens, so you can compare models. tokenstat does not charge these rates. Your subscription bill is separate. The table also shows who lists each model, and whether it can do tools, vision, or reasoning. Recommended order puts known labs first, then newer releases. Free and $0 rows stay hidden unless you ask. Measure real sessions with the app or the CLI.
Showing 40 of 2,200 matches · page 46 of 46 · 320 free/$0 rows hidden (show them)
| Model | Input | Output | Context | Offers |
|---|---|---|---|---|
Gpt 4 1106 Previewazure/gpt-4-1106-preview | $10LiteLLM | $30 | N/A | 2 |
Gpt 4 32kazure/gpt-4-32k | $60LiteLLM | $120 | N/A | 2 |
Gpt 4 32k 0613azure/gpt-4-32k-0613 | $60LiteLLM | $120 | N/A | 2 |
Gpt 4 Turbo 2024 04 09azure/gpt-4-turbo-2024-04-09 | $10LiteLLM | $30 | N/A | 2 |
Gpt 4 Turbo Vision Previewazure/gpt-4-turbo-vision-preview | $10LiteLLM | $30 | N/A | 2 |
Gpt 4.5 Previewazure/gpt-4.5-preview | $75LiteLLM | $150 | N/A | 2 |
Us Gov.Anthropic.Claude 3 Haiku 20240307 V1:0us-gov.anthropic.claude-3-haiku-20240307-v1:0 | $0.3LiteLLM | $1.50 | N/A | 1 |
Codellama 7bllamagate/codellama-7b | $0.06LiteLLM | $0.12 | N/A | 2 |
Databricks Mpt 7b Instructdatabricks/mpt-7b-instruct | $0.5LiteLLM | $0 | N/A | 2 |
Deepseek Coder 6.7bllamagate/deepseek-coder-6.7b | $0.06LiteLLM | $0.12 | N/A | 2 |
Dolphin3 8bllamagate/dolphin3-8b | $0.08LiteLLM | $0.15 | N/A | 2 |
Fireworks Ai 4.1b To 16bfireworks-ai-4.1b-to-16b | $0.2LiteLLM | $0.2 | N/A | 1 |
Granite 3 8b Instructibm/granite-3-8b-instruct | $0.2LiteLLM | $0.2 | N/A | 3 |
Granite 3.3 8b Instructreplicate/ibm-granite/granite-3.3-8b-instruct | $0.03LiteLLM | $0.25 | N/A | 6 |
Granite Guardian 3 3 8bibm/granite-guardian-3-3-8b | $0.2LiteLLM | $0.2 | N/A | 3 |
Hermes 3 8b Teelibertai/hermes-3-8b-tee | $0.15LiteLLM | $0.6 | N/A | 2 |
Hermes3 8blambda_ai/hermes3-8b | $0.025LiteLLM | $0.04 | N/A | 2 |
L3 8B Lunaris V1 Turbodeepinfra/Sao10K/L3-8B-Lunaris-v1-Turbo | $0.04LiteLLM | $0.05 | N/A | 3 |
Lfm 7blambda_ai/lfm-7b | $0.025LiteLLM | $0.04 | N/A | 2 |
Llama3 2 1b Instruct V1:0llama3-2-1b-instruct-v1:0 | $0.1LiteLLM | $0.1 | N/A | 4 |
Llama3 2 3b Instruct V1:0llama3-2-3b-instruct-v1:0 | $0.15LiteLLM | $0.15 | N/A | 4 |
Llama3.1 8bsnowflake/llama3.1-8b | $0.1LiteLLM | $0.1 | N/A | 3 |
Llama3.1 8b Instructlambda_ai/llama3.1-8b-instruct | $0.025LiteLLM | $0.04 | N/A | 2 |
Llama3.2 3b Instructlambda_ai/llama3.2-3b-instruct | $0.015LiteLLM | $0.025 | N/A | 2 |
Llava 7bllamagate/llava-7b | $0.1LiteLLM | $0.2 | N/A | 2 |
Llava V1.6 Mistral 7b Hfovhcloud/llava-v1.6-mistral-7b-hf | $0.29LiteLLM | $0.29 | N/A | 2 |
Meta Llama Guard 3 8Bsambanova/Meta-Llama-Guard-3-8B | $0.3LiteLLM | $0.3 | N/A | 2 |
Meta.Llama3 8b Instruct V1:0bedrock/eu-west-1/meta.llama3-8b-instruct-v1:0 | $0.3LiteLLM | $0.6 | N/A | 18 |
Mistral 7b V0.3llamagate/mistral-7b-v0.3 | $0.1LiteLLM | $0.15 | N/A | 2 |
OlmOCR 7B 0725 FP8deepinfra/allenai/olmOCR-7B-0725-FP8 | $0.27LiteLLM | $1.50 | N/A | 3 |
Openthinker 7bllamagate/openthinker-7b | $0.08LiteLLM | $0.15 | N/A | 2 |
Palmyra Vision 7bpalmyra-vision-7b | $0.15LiteLLM | $0.6 | N/A | 1 |
Together Ai 21.1b 41btogether-ai-21.1b-41b | $0.8LiteLLM | $0.8 | N/A | 1 |
Together Ai 4.1b 8btogether-ai-4.1b-8b | $0.2LiteLLM | $0.2 | N/A | 1 |
Together Ai 41.1b 80btogether-ai-41.1b-80b | $0.9LiteLLM | $0.9 | N/A | 1 |
Together Ai 8.1b 21btogether-ai-8.1b-21b | $0.3LiteLLM | $0.3 | N/A | 1 |
Together Ai 81.1b 110btogether-ai-81.1b-110b | $1.80LiteLLM | $1.80 | N/A | 1 |
Writer.Palmyra Vision 7bwriter.palmyra-vision-7b | $0.15LiteLLM | $0.6 | N/A | 1 |
Qwen2 Audio 7B Instructsambanova/Qwen2-Audio-7B-Instruct | $0.5LiteLLM | $100 | N/A | 2 |
Codellama 7b Instruct Awqcloudflare/@hf/thebloke/codellama-7b-instruct-awq | $1.92LiteLLM | $1.92 | N/A | 3 |
See these prices on your own sessions
tokenstat reads the logs your coding tools already write and prices the tokens at the published API rate. Work your subscription already covered is not an extra bill.