LLM Models
Compare ModelsThese are the official models supported by Glama Gateway and their rates. Glama does not charge extra fees for using these models.
| Provider | Model (alias) | Latency | Released | Max Tokens | USD / M Tokens | ||
|---|---|---|---|---|---|---|---|
| Input | Output | Input | Output | ||||
| 1m 10.6s | 1M | 1M | $3 | $15 | |||
| 28.1s | 1M | 128K | $1* | $6* | |||
| 30s | 1M | 128K | $2.5* | $15* | |||
gpt-5.6-solgpt-5.6 | 15.5s | 1M | 128K | $5* | $30* | ||
| 16.1s | 500K | - | $2* | $6* | |||
| 18.4s | 1M | 128K | $3 | $15 | |||
| 17.2s | 1M | 131K | $1.4 | $4.4 | |||
| 23.1s | 262K | - | $1.9 | $8 | |||
| 1m 22.8s | 262K | - | $0.95 | $4 | |||
| 27.5s | 1M | 128K | $10 | $50 | |||
| 29.1s | 256K | - | $1* | $2* | |||
| 14.3s | 1M | 128K | $5 | $25 | |||
| 1m 26.2s | 1M | - | $1.3* | $2.5* | |||
mistral-medium-2604mistral-medium | 24.2s | 256K | - | $1.5 | $7.5 | ||
gpt-5.5-2026-04-23gpt-5.5 | 20s | 1M | 128K | $5* | $30* | ||
| 2m 55.2s | 1M | 384K | $0.14 | $0.28 | |||
| 2m 58.3s | 1M | 384K | $1.7 | $3.5 | |||
kimi-k2.6kimi-k2 | 1m 20.9s | 262K | 66K | $0.95 | $4 | ||
| 21.4s | 1M | 128K | $5 | $25 | |||
| 1m 15.7s | 200K | 131K | $1.4 | $4.4 | |||
gpt-5.4-mini-2026-03-17gpt-5.4-mini | 1m 25s | 400K | 128K | $0.75 | $4.5 | ||
gpt-5.4-nano-2026-03-17gpt-5.4-nano | 1m 19.3s | 400K | 128K | $0.2 | $1.3 | ||
mistral-small-2603mistral-small | 16.8s | 256K | - | $0.15 | $0.6 | ||
| 17.5s | 200K | 131K | $1.2 | $4 | |||
grok-4.20-0309-non-reasoninggrok-4.20-non-reasoning | 24.5s | 1M | - | $1.3* | $2.5* | ||
grok-4.20-0309-reasoninggrok-4.20 | 11.8s | 1M | - | $1.3* | $2.5* | ||
| 33.5s | 1M | 128K | $2.5* | $15* | |||
| 27.6s | 1M | 66K | $2 | $12 | |||
| 1m 19.8s | 1M | 128K | $3 | $15 | |||
| 30.3s | 200K | 131K | $1 | $3.2 | |||
| 16.3s | 1M | 128K | $5 | $25 | |||
| 1m 9.6s | 262K | 96K | $0.45 | $2.3 | |||
| 1m 20.6s | 262K | 96K | $0.6 | $3 | |||
| 19.4s | 200K | 131K | $0.07 | $0.4 | |||
| 1m 4.4s | 200K | 131K | $0.07 | $0.4 | |||
| 30s | 1M | 66K | $0.5 | $3 | |||
| 35.3s | 200K | 128K | $0.6 | $2.2 | |||
gpt-5.2-2025-12-11gpt-5.2 | 21.9s | 400K | 128K | $1.8 | $14 | ||
ministral-3b-2512ministral-3-3b | 18.9s | 128K | - | $0.1 | $0.1 | ||
ministral-8b-2512ministral-3-8b | 24.4s | 256K | - | $0.15 | $0.15 | ||
mistral-large-2512mistral-large | 33.4s | 256K | - | $0.5 | $1.5 | ||
ministral-14b-2512ministral-3-14b | 58.2s | 256K | - | $0.2 | $0.2 | ||
| 1m 2.1s | 400K | 128K | $1.3 | $10 | |||
claude-opus-4-5-20251101claude-opus-4-5 | 34.4s | 200K | 64K | $5 | $25 | ||
claude-haiku-4-5-20251001claude-haiku-4-5 | 35.5s | 200K | 64K | $1 | $5 | ||
| 19.4s | 200K | - | $0.6 | $2.2 | |||
claude-sonnet-4-5-20250929claude-sonnet-4-5 | 27.3s | 200K | 64K | $3 | $15 | ||
qwen3-coder-plus-2025-09-23qwen3-coder-plus | 14.8s | 1M | 66K | $6 | $60 | ||
| 15.8s | 2M | - | $0.2 | $0.5 | |||
| 13.2s | 2M | - | $0.2 | $0.5 | |||
grok-code-fast-1-0825grok-code-fast-1 | 27.8s | 256K | - | $0.2 | $1.5 | ||
| 15.5s | 128K | - | $0.6 | $2.2 | |||
gpt-5-2025-08-07gpt-5 | 36.9s | 400K | 128K | $1.3 | $10 | ||
gpt-5-mini-2025-08-07gpt-5-mini | 36.2s | 400K | 128K | $0.25 | $2 | ||
gpt-5-nano-2025-08-07gpt-5-nano | 34.9s | 400K | 128K | $0.5 | $0.4 | ||
claude-opus-4-1-20250805claude-opus-4-1 | 15s | 200K | 8K | $15 | $75 | ||
codestral-2508codestral | 26.5s | 256K | - | $0.3 | $0.9 | ||
| 12s | 1M | 66K | $1.6 | $9.6 | |||
qwen-flash-2025-07-28qwen-flash | 12.2s | 1M | 33K | $0.25 | $2 | ||
| 1m 26.1s | 128K | 128K | $2 | $5 | |||
| 19.2s | 33K | 32K | $1 | $3 | |||
| 19.4s | 8K | 8K | $0.2 | $2 | |||
grok-4-0709grok-4 | 32.4s | 256K | 256K | $3 | $15 | ||
| 22.1s | 1M | 66K | $0.15 | $0.6 | |||
| 57.6s | 1M | 66K | $1.3 | $10 | |||
gemini-2.5-pro-preview-05-06discontinued | - | 1M | 66K | $1.3 | $10 | ||
gemini-2.5-pro-preview-05-06discontinued | - | 1M | 66K | $1.3 | $10 | ||
gemini-2.5-flash-preview-04-17discontinued | - | 1M | 66K | $0.15 | $0.6 | ||
gemini-2.5-flash-preview-04-17discontinued | - | 1M | 66K | $0.15 | $0.6 | ||
| 18.2s | 200K | 100K | $2 | $8 | |||
o4-mini-2025-04-16o4-mini | 19.2s | 200K | 100K | $1.1 | $4.4 | ||
gpt-4.1-2025-04-14gpt-4.1 | 27.3s | 1M | 33K | $2 | $8 | ||
gpt-4.1-mini-2025-04-14gpt-4.1-mini | 1m 16.3s | 1M | 33K | $0.4 | $1.6 | ||
gpt-4.1-nano-2025-04-14gpt-4.1-nano | 1m 27.7s | 1M | 33K | $0.1 | $0.4 | ||
gemini-2.5-pro-exp-03-25discontinued | - | 1M | 66K | $1.3 | $5 | ||
grok-3grok | 25s | 131K | 131K | $2 | $10 | ||
command-a-03-2025command-a | 31.4s | 256K | - | $2.5 | $10 | ||
| - | 128K | 16K | $75 | $150 | |||
| - | 128K | - | $1 | $1 | |||
| - | 2M | 8K | $0.00 | $0.00 | |||
| 30.1s | 200K | 100K | $1 | $4.4 | |||
o3-mini-2025-01-31o3-mini | 29.9s | 200K | 100K | $1 | $4.4 | ||
| 15.1s | 32K | 32K | $1 | $3 | |||
deepseek-chat-v3deepseek-chat | 2m 27.9s | 64K | 8K | $0.14 | $0.28 | ||
| 1m 6.9s | 200K | 100K | $15 | $60 | |||
command-r7b-12-2024command-r7b | 1m 1.8s | 128K | 4K | $0.038 | $0.15 | ||
gemini-2.0-flash-expdiscontinued | - | 1M | 8K | $0.00 | $0.00 | ||
| 1m 10.1s | 33K | 512 | $0.17 | $0.7 | |||
gpt-4o-2024-11-20gpt-4o | 16.6s | 128K | 16K | $2.5 | $10 | ||
| - | 200K | 8K | $3 | $15 | |||
grok-betadiscontinued | - | 131K | 131K | $5 | $15 | ||
| 17.4s | 262K | 2K | $1.6 | $6.4 | |||
qwen-plus-2025-07-28qwen-plus | 16.7s | 1M | 8K | $0.4 | $1.2 | ||
| 28.4s | 128K | 128K | $0.15 | $0.15 | |||
ministral-3b-2410ministral-3b | 26.5s | 128K | 4K | $0.04 | $0.04 | ||
ministral-8b-2410ministral-8b | 1m 11.7s | 128K | 128K | $0.1 | $0.1 | ||
command-r-plus-08-2024command-r-plus | 29.6s | 128K | 4K | $2.4 | $9.5 | ||
command-r-08-2024command-r | 59.4s | 128K | 4K | $0.14 | $0.57 | ||
| - | 131K | 131K | $2 | $10 | |||
| 1m 31.4s | 128K | 16K | $2.5 | $10 | |||
gpt-4o-mini-2024-07-18gpt-4o-mini | 1m 42.4s | 128K | 16K | $0.15 | $0.6 | ||
claude-3-5-sonnet-20240620discontinued | - | 200K | 8K | $3 | $15 | ||
gemini-1.5-flash-001discontinued | - | 1M | 8K | $0.075 | $0.3 | ||
gemini-1.5-pro-001discontinued | - | 1M | 8K | $1.3 | $5 | ||
| 1m 33.4s | 128K | 4K | $5 | $15 | |||
| 28.6s | 131K | 131K | $3 | $15 | |||
| 22.4s | 131K | 131K | $5 | $25 | |||
| 31.6s | 131K | 131K | $0.3 | $0.5 | |||
| 31.6s | 131K | 131K | $0.6 | $4 | |||
| 27.3s | 64K | 4K | $2 | $6 | |||
| 17.6s | 32K | 32K | $1 | $3 | |||
| 24.7s | 33K | 4K | $0.7 | $0.7 | |||
| 11.1s | 33K | 8K | $0.25 | $0.25 | |||
| 11.3s | 8K | 8K | $0.2 | $2 | |||
| 30.6s | 128K | 128K | $2 | $5 | |||
| 25.3s | 128K | 8K | $0.5 | $4.9 | |||
| 2m 12.8s | 64K | 8K | $0.55 | $2.2 | |||